Registration

Providers

Azure Blob Store

Register an Azure Blob Store provider.

Azure Blob Storage can be used as the storage component for Spark or the Featureform Pandas Runner.

Examples:

blob = ff.register_blob_store(
    name="azure-quickstart",
    container_name="my_company_container"
    root_path="custom/path/in/container"
    account_name=<azure_account_name>
    account_key=<azure_account_key>
    description="An azure blob store provider to store offline and inference data"
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of Azure blob store to be registered	required
container_name	str	(Immutable) Azure container name	required
root_path	str	(Immutable) A custom path in container to store data	required
account_name	str	(Immutable) Azure account name	required
account_key	str	(Mutable) Secret azure account key	required
description	str	(Mutable) Description of Azure Blob provider to be registered	''
team	str	(Mutable) The name of the team registering the filestore	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	None
properties	dict	(Mutable) Optional grouping mechanism for resources	None

Returns:

Name	Type	Description
blob	StorageProvider	Provider has all the functionality of OnlineProvider

BigQuery

Register a BigQuery provider.

Examples:

bigquery = ff.register_bigquery(
    name="bigquery-quickstart",
    description="A BigQuery deployment we created for the Featureform quickstart",
    project_id="quickstart-project",
    dataset_id="quickstart-dataset",
    credentials=GCPCredentials(...)
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of BigQuery provider to be registered	required
project_id	str	(Immutable) The Project name in GCP	required
dataset_id	str	(Immutable) The Dataset name in GCP under the Project Id	required
credentials	GCPCredentials	(Mutable) GCP credentials to access BigQuery	required
description	str	(Mutable) Description of BigQuery provider to be registered	''
team	str	(Mutable) Name of team	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	[]
properties	dict	(Mutable) Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
bigquery	OfflineSQLProvider	Provider

Source code in src/featureform/register.py

def register_bigquery(
    self,
    name: str,
    project_id: str,
    dataset_id: str,
    credentials: GCPCredentials,
    credentials_path: str = "",
    description: str = "",
    team: str = "",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a BigQuery provider.

    **Examples**:
    ```
    bigquery = ff.register_bigquery(
        name="bigquery-quickstart",
        description="A BigQuery deployment we created for the Featureform quickstart",
        project_id="quickstart-project",
        dataset_id="quickstart-dataset",
        credentials=GCPCredentials(...)
    )
    ```

    Args:
        name (str): (Immutable) Name of BigQuery provider to be registered
        project_id (str): (Immutable) The Project name in GCP
        dataset_id (str): (Immutable) The Dataset name in GCP under the Project Id
        credentials (GCPCredentials): (Mutable) GCP credentials to access BigQuery
        description (str): (Mutable) Description of BigQuery provider to be registered
        team (str): (Mutable) Name of team
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources

    Returns:
        bigquery (OfflineSQLProvider): Provider
    """
    tags, properties = set_tags_properties(tags, properties)

    config = BigQueryConfig(
        project_id=project_id,
        dataset_id=dataset_id,
        credentials=credentials,
    )
    provider = Provider(
        name=name,
        function="OFFLINE",
        description=description,
        team=team,
        config=config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return OfflineSQLProvider(self, provider)

Cassandra

Register a Cassandra provider.

Examples:

cassandra = ff.register_cassandra(
        name = "cassandra",
        description = "Example inference store",
        team = "Featureform",
        host = "0.0.0.0",
        port = 9042,
        username = "cassandra",
        password = "cassandra",
        consistency = "THREE",
        replication = 3
    )

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of Cassandra provider to be registered	required
host	str	(Immutable) DNS name of Cassandra	required
port	str	(Mutable) Port	required
username	str	(Mutable) Username	required
password	str	(Mutable) Password	required
consistency	str	(Mutable) Consistency	'THREE'
replication	int	(Mutable) Replication	3
description	str	(Mutable) Description of Cassandra provider to be registered	''
team	str	(Mutable) Name of team	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	[]
properties	dict	(Mutable) Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
cassandra	OnlineProvider	Provider

Source code in src/featureform/register.py

def register_cassandra(
    self,
    name: str,
    host: str,
    port: int,
    username: str,
    password: str,
    keyspace: str,
    consistency: str = "THREE",
    replication: int = 3,
    description: str = "",
    team: str = "",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a Cassandra provider.

    **Examples**:
    ```
    cassandra = ff.register_cassandra(
            name = "cassandra",
            description = "Example inference store",
            team = "Featureform",
            host = "0.0.0.0",
            port = 9042,
            username = "cassandra",
            password = "cassandra",
            consistency = "THREE",
            replication = 3
        )
    ```

    Args:
        name (str): (Immutable) Name of Cassandra provider to be registered
        host (str): (Immutable) DNS name of Cassandra
        port (str): (Mutable) Port
        username (str): (Mutable) Username
        password (str): (Mutable) Password
        consistency (str): (Mutable) Consistency
        replication (int): (Mutable) Replication
        description (str): (Mutable) Description of Cassandra provider to be registered
        team (str): (Mutable) Name of team
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources

    Returns:
        cassandra (OnlineProvider): Provider
    """
    config = CassandraConfig(
        host=host,
        port=port,
        username=username,
        password=password,
        keyspace=keyspace,
        consistency=consistency,
        replication=replication,
    )
    provider = Provider(
        name=name,
        function="ONLINE",
        description=description,
        team=team,
        config=config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return OnlineProvider(self, provider)

DynamoDB

Register a DynamoDB provider.

Examples:

dynamodb = ff.register_dynamodb(
    name="dynamodb-quickstart",
    description="A Dynamodb deployment we created for the Featureform quickstart",
    credentials=aws_creds,
    region="us-east-1"
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of DynamoDB provider to be registered	required
region	str	(Immutable) Region to create dynamo tables	required
credentials	AWSCredentials	(Mutable) AWS credentials with permissions to create DynamoDB tables	required
should_import_from_s3	bool	(Mutable) Determines whether feature materialization will occur via a direct import of data from S3 to new table (see docs for details)	False
description	str	(Mutable) Description of DynamoDB provider to be registered	''
team	str	(Mutable) Name of team	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	[]
properties	dict	(Mutable) Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
dynamodb	OnlineProvider	Provider

Source code in src/featureform/register.py

def register_dynamodb(
    self,
    name: str,
    credentials: AWSCredentials,
    region: str,
    should_import_from_s3: bool = False,
    description: str = "",
    team: str = "",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a DynamoDB provider.

    **Examples**:
    ```
    dynamodb = ff.register_dynamodb(
        name="dynamodb-quickstart",
        description="A Dynamodb deployment we created for the Featureform quickstart",
        credentials=aws_creds,
        region="us-east-1"
    )
    ```

    Args:
        name (str): (Immutable) Name of DynamoDB provider to be registered
        region (str): (Immutable) Region to create dynamo tables
        credentials (AWSCredentials): (Mutable) AWS credentials with permissions to create DynamoDB tables
        should_import_from_s3 (bool): (Mutable) Determines whether feature materialization will occur via a direct import of data from S3 to new table (see [docs](https://docs.aws.amazon.com/amazondynamodb/latest/developerguide/S3DataImport.HowItWorks.html) for details)
        description (str): (Mutable) Description of DynamoDB provider to be registered
        team (str): (Mutable) Name of team
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources

    Returns:
        dynamodb (OnlineProvider): Provider
    """
    tags, properties = set_tags_properties(tags, properties)
    config = DynamodbConfig(
        access_key=credentials.access_key,
        secret_key=credentials.secret_key,
        region=region,
        should_import_from_s3=should_import_from_s3,
    )
    provider = Provider(
        name=name,
        function="ONLINE",
        description=description,
        team=team,
        config=config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return OnlineProvider(self, provider)

Firestore

Register a Firestore provider.

Examples:

firestore = ff.register_firestore(
    name="firestore-quickstart",
    description="A Firestore deployment we created for the Featureform quickstart",
    project_id="quickstart-project",
    collection="quickstart-collection",
    credentials=ff.GCPCredentials(...)
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of Firestore provider to be registered	required
project_id	str	(Immutable) The Project name in GCP	required
collection	str	(Immutable) The Collection name in Firestore under the given project ID	required
credentials	GCPCredentials	(Mutable) GCP credentials to access Firestore	required
description	str	(Mutable) Description of Firestore provider to be registered	''
team	str	(Mutable) The name of the team registering the filestore	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	[]
properties	dict	(Mutable) Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
firestore	OfflineSQLProvider	Provider

Source code in src/featureform/register.py

def register_firestore(
    self,
    name: str,
    collection: str,
    project_id: str,
    credentials: GCPCredentials,
    credentials_path: str = "",
    description: str = "",
    team: str = "",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a Firestore provider.

    **Examples**:
    ```
    firestore = ff.register_firestore(
        name="firestore-quickstart",
        description="A Firestore deployment we created for the Featureform quickstart",
        project_id="quickstart-project",
        collection="quickstart-collection",
        credentials=ff.GCPCredentials(...)
    )
    ```

    Args:
        name (str): (Immutable) Name of Firestore provider to be registered
        project_id (str): (Immutable) The Project name in GCP
        collection (str): (Immutable) The Collection name in Firestore under the given project ID
        credentials (GCPCredentials): (Mutable) GCP credentials to access Firestore
        description (str): (Mutable) Description of Firestore provider to be registered
        team (str): (Mutable) The name of the team registering the filestore
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources

    Returns:
        firestore (OfflineSQLProvider): Provider
    """
    tags, properties = set_tags_properties(tags, properties)
    config = FirestoreConfig(
        collection=collection,
        project_id=project_id,
        credentials=credentials,
    )
    provider = Provider(
        name=name,
        function="ONLINE",
        description=description,
        team=team,
        config=config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return OnlineProvider(self, provider)

Google Cloud Storage

Register a GCS store provider.

Examples:

gcs = ff.register_gcs(
    name="gcs-quickstart",
    credentials=ff.GCPCredentials(...),
    bucket_name="bucket_name",
    root_path="featureform/path/",
    description="An gcs store provider to store offline"
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of GCS store to be registered	required
bucket_name	str	(Immutable) The bucket name	required
root_path	str	(Immutable) Custom path to be used by featureform	required
credentials	GCPCredentials	(Mutable) GCP credentials to access the bucket	required
description	str	(Mutable) Description of GCS provider to be registered	''
team	str	(Mutable) The name of the team registering the filestore	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	[]
properties	dict	(Mutable) Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
gcs	FileStoreProvider	Provider has all the functionality of OfflineProvider

Source code in src/featureform/register.py

def register_gcs(
    self,
    name: str,
    bucket_name: str,
    root_path: str,
    credentials: GCPCredentials,
    description: str = "",
    team: str = "",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a GCS store provider.

    **Examples**:
    ```
    gcs = ff.register_gcs(
        name="gcs-quickstart",
        credentials=ff.GCPCredentials(...),
        bucket_name="bucket_name",
        root_path="featureform/path/",
        description="An gcs store provider to store offline"
    )
    ```

    Args:
        name (str): (Immutable) Name of GCS store to be registered
        bucket_name (str): (Immutable) The bucket name
        root_path (str): (Immutable) Custom path to be used by featureform
        credentials (GCPCredentials): (Mutable) GCP credentials to access the bucket
        description (str): (Mutable) Description of GCS provider to be registered
        team (str): (Mutable) The name of the team registering the filestore
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources

    Returns:
        gcs (FileStoreProvider): Provider
            has all the functionality of OfflineProvider
    """
    tags, properties = set_tags_properties(tags, properties)

    if bucket_name == "":
        raise ValueError("bucket_name is required and cannot be empty string")

    bucket_name = bucket_name.replace("gs://", "")
    if "/" in bucket_name:
        raise ValueError(
            "bucket_name cannot contain '/'. bucket_name should be the name of the GCS bucket only."
        )

    gcs_config = GCSFileStoreConfig(
        bucket_name=bucket_name, bucket_path=root_path, credentials=credentials
    )
    provider = Provider(
        name=name,
        function="OFFLINE",
        description=description,
        team=team,
        config=gcs_config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return FileStoreProvider(self, provider, gcs_config, gcs_config.type())

HDFS

Register a HDFS store provider.

This has the functionality of an offline store and can be used as a parameter to a k8s or spark provider

Examples:

hdfs = ff.register_hdfs(
    name="hdfs-quickstart",
    host="<host>",
    port="<port>",
    path="<path>",
    username="<username>",
    description="An hdfs store provider to store offline"
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of HDFS store to be registered	required
host	str	(Immutable) The hostname for HDFS	required
path	str	(Immutable) A storage path within HDFS	''
port	str	(Mutable) The IPC port for the Namenode for HDFS. (Typically 8020 or 9000)	required
username	str	(Mutable) A Username for HDFS	''
description	str	(Mutable) Description of HDFS provider to be registered	''
team	str	(Mutable) The name of the team registering HDFS	''

Returns:

Name	Type	Description
hdfs	FileStoreProvider	Provider

Source code in src/featureform/register.py

def register_hdfs(
    self,
    name: str,
    host: str,
    port: str,
    username: str = "",
    path: str = "",
    description: str = "",
    team: str = "",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a HDFS store provider.

    This has the functionality of an offline store and can be used as a parameter
    to a k8s or spark provider

    **Examples**:
    ```
    hdfs = ff.register_hdfs(
        name="hdfs-quickstart",
        host="<host>",
        port="<port>",
        path="<path>",
        username="<username>",
        description="An hdfs store provider to store offline"
    )
    ```

    Args:
        name (str): (Immutable) Name of HDFS store to be registered
        host (str): (Immutable) The hostname for HDFS
        path (str): (Immutable) A storage path within HDFS
        port (str): (Mutable) The IPC port for the Namenode for HDFS. (Typically 8020 or 9000)
        username (str): (Mutable) A Username for HDFS
        description (str): (Mutable) Description of HDFS provider to be registered
        team (str): (Mutable) The name of the team registering HDFS

    Returns:
        hdfs (FileStoreProvider): Provider
    """

    hdfs_config = HDFSConfig(host=host, port=port, path=path, username=username)

    provider = Provider(
        name=name,
        function="OFFLINE",
        description=description,
        team=team,
        config=hdfs_config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return FileStoreProvider(self, provider, hdfs_config, hdfs_config.type())

MongoDB

Register a MongoDB provider.

Examples:

mongodb = ff.register_mongodb(
    name="mongodb-quickstart",
    description="A MongoDB deployment",
    username="my_username",
    password="myPassword",
    database="featureform_database"
    host="my-mongodb.host.com",
    port="10225",
    throughput=10000
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of MongoDB provider to be registered	required
database	str	(Immutable) MongoDB database	required
host	str	(Immutable) MongoDB hostname	required
port	str	(Immutable) MongoDB port	required
username	str	(Mutable) MongoDB username	required
password	str	(Mutable) MongoDB password	required
throughput	int	(Mutable) The maximum RU limit for autoscaling in CosmosDB	1000
description	str	(Mutable) Description of MongoDB provider to be registered	''
team	str	(Mutable) Name of team	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	[]
properties	dict	(Mutable) Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
mongodb	OnlineProvider	Provider

Source code in src/featureform/register.py

def register_mongodb(
    self,
    name: str,
    username: str,
    password: str,
    database: str,
    host: str,
    port: str,
    throughput: int = 1000,
    description: str = "",
    team: str = "",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a MongoDB provider.

    **Examples**:
    ```
    mongodb = ff.register_mongodb(
        name="mongodb-quickstart",
        description="A MongoDB deployment",
        username="my_username",
        password="myPassword",
        database="featureform_database"
        host="my-mongodb.host.com",
        port="10225",
        throughput=10000
    )
    ```

    Args:
        name (str): (Immutable) Name of MongoDB provider to be registered
        database (str): (Immutable) MongoDB database
        host (str): (Immutable) MongoDB hostname
        port (str): (Immutable) MongoDB port
        username (str): (Mutable) MongoDB username
        password (str): (Mutable) MongoDB password
        throughput (int): (Mutable) The maximum RU limit for autoscaling in CosmosDB
        description (str): (Mutable) Description of MongoDB provider to be registered
        team (str): (Mutable) Name of team
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources

    Returns:
        mongodb (OnlineProvider): Provider
    """
    tags, properties = set_tags_properties(tags, properties)
    config = MongoDBConfig(
        username=username,
        password=password,
        host=host,
        port=port,
        database=database,
        throughput=throughput,
    )
    provider = Provider(
        name=name,
        function="ONLINE",
        description=description,
        team=team,
        config=config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return OnlineProvider(self, provider)

Pinecone

Register a Pinecone provider.

Examples:

pinecone = ff.register_pinecone(
    name="pinecone-quickstart",
    project_id="2g13ek7",
    environment="us-west4-gcp-free",
    api_key="xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of Pinecone provider to be registered	required
project_id	str	(Immutable) Pinecone project id	required
environment	str	(Immutable) Pinecone environment	required
api_key	str	(Mutable) Pinecone api key	required
description	str	(Mutable) Description of Pinecone provider to be registered	''
team	str	(Mutable) Name of team	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	[]
properties	dict	(Mutable) Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
pinecone	OnlineProvider	Provider

Source code in src/featureform/register.py

def register_pinecone(
    self,
    name: str,
    project_id: str,
    environment: str,
    api_key: str,
    description: str = "",
    team: str = "",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a Pinecone provider.

    **Examples**:
    ```
    pinecone = ff.register_pinecone(
        name="pinecone-quickstart",
        project_id="2g13ek7",
        environment="us-west4-gcp-free",
        api_key="xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
    )
    ```

    Args:
        name (str): (Immutable) Name of Pinecone provider to be registered
        project_id (str): (Immutable) Pinecone project id
        environment (str): (Immutable) Pinecone environment
        api_key (str): (Mutable) Pinecone api key
        description (str): (Mutable) Description of Pinecone provider to be registered
        team (str): (Mutable) Name of team
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources

    Returns:
        pinecone (OnlineProvider): Provider
    """

    tags, properties = set_tags_properties(tags, properties)
    config = PineconeConfig(
        project_id=project_id, environment=environment, api_key=api_key
    )
    provider = Provider(
        name=name,
        function="ONLINE",
        description=description,
        team=team,
        config=config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return OnlineProvider(self, provider)

Postgres

Register a Postgres provider.

Examples:

postgres = ff.register_postgres(
    name="postgres-quickstart",
    description="A Postgres deployment we created for the Featureform quickstart",
    host="quickstart-postgres",  # The internal dns name for postgres
    port="5432",
    user="postgres",
    password="password", #pragma: allowlist secret
    database="postgres"
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of Postgres provider to be registered	required
host	str	(Immutable) Hostname for Postgres	required
database	str	(Immutable) Database	required
port	str	(Mutable) Port	'5432'
user	str	(Mutable) User	required
password	str	(Mutable) Password	required
sslmode	str	(Mutable) SSL mode	'disable'
description	str	(Mutable) Description of Postgres provider to be registered	''
team	str	(Mutable) Name of team	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	[]
properties	dict	(Mutable) Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
postgres	OfflineSQLProvider	Provider

Source code in src/featureform/register.py

def register_postgres(
    self,
    name: str,
    host: str,
    user: str,
    password: str,
    database: str,
    port: str = "5432",
    description: str = "",
    team: str = "",
    sslmode: str = "disable",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a Postgres provider.

    **Examples**:
    ```
    postgres = ff.register_postgres(
        name="postgres-quickstart",
        description="A Postgres deployment we created for the Featureform quickstart",
        host="quickstart-postgres",  # The internal dns name for postgres
        port="5432",
        user="postgres",
        password="password", #pragma: allowlist secret
        database="postgres"
    )
    ```

    Args:
        name (str): (Immutable) Name of Postgres provider to be registered
        host (str): (Immutable) Hostname for Postgres
        database (str): (Immutable) Database
        port (str): (Mutable) Port
        user (str): (Mutable) User
        password (str): (Mutable) Password
        sslmode (str): (Mutable) SSL mode
        description (str): (Mutable) Description of Postgres provider to be registered
        team (str): (Mutable) Name of team
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources

    Returns:
        postgres (OfflineSQLProvider): Provider
    """
    tags, properties = set_tags_properties(tags, properties)
    config = PostgresConfig(
        host=host,
        port=port,
        database=database,
        user=user,
        password=password,
        sslmode=sslmode,
    )
    provider = Provider(
        name=name,
        function="OFFLINE",
        description=description,
        team=team,
        config=config,
        tags=tags or [],
        properties=properties or {},
    )

    self.__resources.append(provider)
    return OfflineSQLProvider(self, provider)

Redis

Register a Redis provider.

Examples:

redis = ff.register_redis(
    name="redis-quickstart",
    host="quickstart-redis",
    port=6379,
    password="password",
    description="A Redis deployment we created for the Featureform quickstart"
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of Redis provider to be registered	required
host	str	(Immutable) Hostname for Redis	required
db	str	(Immutable) Redis database number	0
port	int	(Mutable) Redis port	6379
password	str	(Mutable) Redis password	''
description	str	(Mutable) Description of Redis provider to be registered	''
team	str	(Mutable) Name of team	''
tags	Optional[List[str]]	(Mutable) Optional grouping mechanism for resources	None
properties	Optional[dict]	(Mutable) Optional grouping mechanism for resources	None

Returns:

Name	Type	Description
redis	OnlineProvider	Provider

Source code in src/featureform/register.py

def register_redis(
    self,
    name: str,
    host: str,
    port: int = 6379,
    db: int = 0,
    password: str = "",
    description: str = "",
    team: str = "",
    tags: Optional[List[str]] = None,
    properties: Optional[dict] = None,
):
    """Register a Redis provider.

    **Examples**:
    ```
    redis = ff.register_redis(
        name="redis-quickstart",
        host="quickstart-redis",
        port=6379,
        password="password",
        description="A Redis deployment we created for the Featureform quickstart"
    )
    ```

    Args:
        name (str): (Immutable) Name of Redis provider to be registered
        host (str): (Immutable) Hostname for Redis
        db (str): (Immutable) Redis database number
        port (int): (Mutable) Redis port
        password (str): (Mutable) Redis password
        description (str): (Mutable) Description of Redis provider to be registered
        team (str): (Mutable) Name of team
        tags (Optional[List[str]]): (Mutable) Optional grouping mechanism for resources
        properties (Optional[dict]): (Mutable) Optional grouping mechanism for resources

    Returns:
        redis (OnlineProvider): Provider
    """
    tags, properties = set_tags_properties(tags, properties)
    config = RedisConfig(host=host, port=port, password=password, db=db)
    provider = Provider(
        name=name,
        function="ONLINE",
        description=description,
        team=team,
        config=config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return OnlineProvider(self, provider)

Redshift

Register a Redshift provider.

Examples:

redshift = ff.register_redshift(
    name="redshift-quickstart",
    description="A Redshift deployment we created for the Featureform quickstart",
    host="quickstart-redshift",  # The internal dns name for redshift
    port="5432",
    user="redshift",
    password="password", #pragma: allowlist secret
    database="dev"
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of Redshift provider to be registered	required
host	str	(Immutable) Hostname for Redshift	required
database	str	(Immutable) Redshift database	required
port	str	(Mutable) Port	required
user	str	(Mutable) User	required
password	str	(Mutable) Redshift password	required
sslmode	str	(Mutable) SSL mode	'disable'
description	str	(Mutable) Description of Redshift provider to be registered	''
team	str	(Mutable) Name of team	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	[]
properties	dict	(Mutable) Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
redshift	OfflineSQLProvider	Provider

Source code in src/featureform/register.py

def register_redshift(
    self,
    name: str,
    host: str,
    port: str,
    user: str,
    password: str,
    database: str,
    description: str = "",
    team: str = "",
    sslmode: str = "disable",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a Redshift provider.

    **Examples**:
    ```
    redshift = ff.register_redshift(
        name="redshift-quickstart",
        description="A Redshift deployment we created for the Featureform quickstart",
        host="quickstart-redshift",  # The internal dns name for redshift
        port="5432",
        user="redshift",
        password="password", #pragma: allowlist secret
        database="dev"
    )
    ```

    Args:
        name (str): (Immutable) Name of Redshift provider to be registered
        host (str): (Immutable) Hostname for Redshift
        database (str): (Immutable) Redshift database
        port (str): (Mutable) Port
        user (str): (Mutable) User
        password (str): (Mutable) Redshift password
        sslmode (str): (Mutable) SSL mode
        description (str): (Mutable) Description of Redshift provider to be registered
        team (str): (Mutable) Name of team
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources

    Returns:
        redshift (OfflineSQLProvider): Provider
    """
    tags, properties = set_tags_properties(tags, properties)
    config = RedshiftConfig(
        host=host,
        port=port,
        database=database,
        user=user,
        password=password,
        sslmode=sslmode,
    )
    provider = Provider(
        name=name,
        function="OFFLINE",
        description=description,
        team=team,
        config=config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return OfflineSQLProvider(self, provider)

ClickHouse

Register a ClickHouse provider.

Examples:

clickhouse = ff.register_clickhouse(
    name="clickhouse-quickstart",
    description="A ClickHouse deployment we created for the Featureform quickstart",
    host="quickstart-clickhouse",  # The internal dns name for clickhouse
    port=9000,
    user="default",
    password="", #pragma: allowlist secret
    database="default"
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of ClickHouse provider to be registered	required
host	str	(Immutable) Hostname for ClickHouse	required
database	str	(Immutable) ClickHouse database	required
port	int	(Mutable) Port	9000
ssl	bool	(Mutable) Enable SSL	False
user	str	(Mutable) User	required
password	str	(Mutable) ClickHouse password	required
description	str	(Mutable) Description of ClickHouse provider to be registered	''
team	str	(Mutable) Name of team	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	[]
properties	dict	(Mutable) Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
clickhouse	OfflineSQLProvider	Provider

Source code in src/featureform/register.py

def register_clickhouse(
    self,
    name: str,
    host: str,
    user: str,
    password: str,
    database: str,
    port: int = 9000,
    description: str = "",
    team: str = "",
    ssl: bool = False,
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a ClickHouse provider.

    **Examples**:
    ```
    clickhouse = ff.register_clickhouse(
        name="clickhouse-quickstart",
        description="A ClickHouse deployment we created for the Featureform quickstart",
        host="quickstart-clickhouse",  # The internal dns name for clickhouse
        port=9000,
        user="default",
        password="", #pragma: allowlist secret
        database="default"
    )
    ```

    Args:
        name (str): (Immutable) Name of ClickHouse provider to be registered
        host (str): (Immutable) Hostname for ClickHouse
        database (str): (Immutable) ClickHouse database
        port (int): (Mutable) Port
        ssl (bool): (Mutable) Enable SSL
        user (str): (Mutable) User
        password (str): (Mutable) ClickHouse password
        description (str): (Mutable) Description of ClickHouse provider to be registered
        team (str): (Mutable) Name of team
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources

    Returns:
        clickhouse (OfflineSQLProvider): Provider
    """
    tags, properties = set_tags_properties(tags, properties)
    config = ClickHouseConfig(
        host=host,
        port=port,
        database=database,
        user=user,
        password=password,
        ssl=ssl,
    )
    provider = Provider(
        name=name,
        function="OFFLINE",
        description=description,
        team=team,
        config=config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return OfflineSQLProvider(self, provider)

S3

Register a S3 store provider.

This has the functionality of an offline store and can be used as a parameter to a k8s or spark provider

Examples:

s3 = ff.register_s3(
    name="s3-quickstart",
    credentials=aws_creds,
    bucket_name="bucket_name",
    bucket_region=<bucket_region>,
    path="path/to/store/featureform_files/in/",
    description="An s3 store provider to store offline"
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of S3 store to be registered	required
bucket_name	str	(Immutable) AWS Bucket Name	required
bucket_region	str	(Immutable) AWS region the bucket is located in	required
path	str	(Immutable) The path used to store featureform files in	''
credentials	AWSCredentials	(Mutable) AWS credentials to access the bucket	required
description	str	(Mutable) Description of S3 provider to be registered	''
team	str	(Mutable) The name of the team registering the filestore	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	[]
properties	dict	(Mutable) Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
s3	FileStoreProvider	Provider has all the functionality of OfflineProvider

Source code in src/featureform/register.py

def register_s3(
    self,
    name: str,
    credentials: AWSCredentials,
    bucket_region: str,
    bucket_name: str,
    path: str = "",
    description: str = "",
    team: str = "",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a S3 store provider.

    This has the functionality of an offline store and can be used as a parameter
    to a k8s or spark provider

    **Examples**:
    ```
    s3 = ff.register_s3(
        name="s3-quickstart",
        credentials=aws_creds,
        bucket_name="bucket_name",
        bucket_region=<bucket_region>,
        path="path/to/store/featureform_files/in/",
        description="An s3 store provider to store offline"
    )
    ```

    Args:
        name (str): (Immutable) Name of S3 store to be registered
        bucket_name (str): (Immutable) AWS Bucket Name
        bucket_region (str): (Immutable) AWS region the bucket is located in
        path (str): (Immutable) The path used to store featureform files in
        credentials (AWSCredentials): (Mutable) AWS credentials to access the bucket
        description (str): (Mutable) Description of S3 provider to be registered
        team (str): (Mutable) The name of the team registering the filestore
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources

    Returns:
        s3 (FileStoreProvider): Provider
            has all the functionality of OfflineProvider
    """
    tags, properties = set_tags_properties(tags, properties)

    if bucket_name == "":
        raise ValueError("bucket_name is required and cannot be empty string")

    # TODO: add verification into S3StoreConfig
    bucket_name = bucket_name.replace("s3://", "").replace("s3a://", "")

    if "/" in bucket_name:
        raise ValueError(
            "bucket_name cannot contain '/'. bucket_name should be the name of the AWS S3 bucket only."
        )

    s3_config = S3StoreConfig(
        bucket_path=bucket_name,
        bucket_region=bucket_region,
        credentials=credentials,
        path=path,
    )

    provider = Provider(
        name=name,
        function="OFFLINE",
        description=description,
        team=team,
        config=s3_config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return FileStoreProvider(self, provider, s3_config, s3_config.type())

Snowflake

Current

Register a Snowflake provider.

Examples:

snowflake = ff.register_snowflake(
    name="snowflake-quickstart",
    username="snowflake",
    password="password", #pragma: allowlist secret
    account="account",
    organization="organization",
    database="snowflake",
    schema="PUBLIC",
    description="A Snowflake deployment we created for the Featureform quickstart"
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of Snowflake provider to be registered	required
account	str	(Immutable) Account	required
organization	str	(Immutable) Organization	required
database	str	(Immutable) Database	required
schema	str	(Immutable) Schema	'PUBLIC'
username	str	(Mutable) Username	required
password	str	(Mutable) Password	required
warehouse	str	(Mutable) Specifies the virtual warehouse to use by default for queries, loading, etc.	''
role	str	(Mutable) Specifies the role to use by default for accessing Snowflake objects in the client session	''
description	str	(Mutable) Description of Snowflake provider to be registered	''
team	str	(Mutable) Name of team	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	[]
properties	dict	(Mutable) Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
snowflake	OfflineSQLProvider	Provider

Source code in src/featureform/register.py

def register_snowflake(
    self,
    name: str,
    username: str,
    password: str,
    account: str,
    organization: str,
    database: str,
    schema: str = "PUBLIC",
    description: str = "",
    team: str = "",
    warehouse: str = "",
    role: str = "",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a Snowflake provider.

    **Examples**:
    ```
    snowflake = ff.register_snowflake(
        name="snowflake-quickstart",
        username="snowflake",
        password="password", #pragma: allowlist secret
        account="account",
        organization="organization",
        database="snowflake",
        schema="PUBLIC",
        description="A Snowflake deployment we created for the Featureform quickstart"
    )
    ```

    Args:
        name (str): (Immutable) Name of Snowflake provider to be registered
        account (str): (Immutable) Account
        organization (str): (Immutable) Organization
        database (str): (Immutable) Database
        schema (str): (Immutable) Schema
        username (str): (Mutable) Username
        password (str): (Mutable) Password
        warehouse (str): (Mutable) Specifies the virtual warehouse to use by default for queries, loading, etc.
        role (str): (Mutable) Specifies the role to use by default for accessing Snowflake objects in the client session
        description (str): (Mutable) Description of Snowflake provider to be registered
        team (str): (Mutable) Name of team
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources

    Returns:
        snowflake (OfflineSQLProvider): Provider
    """
    tags, properties = set_tags_properties(tags, properties)
    config = SnowflakeConfig(
        account=account,
        database=database,
        organization=organization,
        username=username,
        password=password,
        schema=schema,
        warehouse=warehouse,
        role=role,
    )
    provider = Provider(
        name=name,
        function="OFFLINE",
        description=description,
        team=team,
        config=config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return OfflineSQLProvider(self, provider)

Legacy

Register a Snowflake provider using legacy credentials.

Examples:

snowflake = ff.register_snowflake_legacy(
    name="snowflake-quickstart",
    username="snowflake",
    password="password",
    account_locator="account-locator",
    database="snowflake",
    schema="PUBLIC",
    description="A Snowflake deployment we created for the Featureform quickstart"
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of Snowflake provider to be registered	required
account_locator	str	(Immutable) Account Locator	required
schema	str	(Immutable) Schema	'PUBLIC'
database	str	(Immutable) Database	required
username	str	(Mutable) Username	required
password	str	(Mutable) Password	required
warehouse	str	(Mutable) Specifies the virtual warehouse to use by default for queries, loading, etc.	''
role	str	(Mutable) Specifies the role to use by default for accessing Snowflake objects in the client session	''
description	str	(Mutable) Description of Snowflake provider to be registered	''
team	str	(Mutable) Name of team	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	[]
properties	dict	(Mutable) Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
snowflake	OfflineSQLProvider	Provider

Source code in src/featureform/register.py

def register_snowflake_legacy(
    self,
    name: str,
    username: str,
    password: str,
    account_locator: str,
    database: str,
    schema: str = "PUBLIC",
    description: str = "",
    team: str = "",
    warehouse: str = "",
    role: str = "",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a Snowflake provider using legacy credentials.

    **Examples**:
    ```
    snowflake = ff.register_snowflake_legacy(
        name="snowflake-quickstart",
        username="snowflake",
        password="password",
        account_locator="account-locator",
        database="snowflake",
        schema="PUBLIC",
        description="A Snowflake deployment we created for the Featureform quickstart"
    )
    ```

    Args:
        name (str): (Immutable) Name of Snowflake provider to be registered
        account_locator (str): (Immutable) Account Locator
        schema (str): (Immutable) Schema
        database (str): (Immutable) Database
        username (str): (Mutable) Username
        password (str): (Mutable) Password
        warehouse (str): (Mutable) Specifies the virtual warehouse to use by default for queries, loading, etc.
        role (str): (Mutable) Specifies the role to use by default for accessing Snowflake objects in the client session
        description (str): (Mutable) Description of Snowflake provider to be registered
        team (str): (Mutable) Name of team
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources

    Returns:
        snowflake (OfflineSQLProvider): Provider
    """
    tags, properties = set_tags_properties(tags, properties)
    config = SnowflakeConfig(
        account_locator=account_locator,
        database=database,
        username=username,
        password=password,
        schema=schema,
        warehouse=warehouse,
        role=role,
    )
    provider = Provider(
        name=name,
        function="OFFLINE",
        description=description,
        team=team,
        config=config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return OfflineSQLProvider(self, provider)

Weaviate

Register a Weaviate provider.

Examples:

weaviate = ff.register_weaviate(
    name="weaviate-quickstart",
    url="https://<CLUSTER NAME>.weaviate.network",
    api_key="<API KEY>"
    description="A Weaviate project for using embeddings in Featureform"
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of Weaviate provider to be registered	required
url	str	(Immutable) Endpoint of Weaviate cluster, either in the cloud or via another deployment operation	required
api_key	str	(Mutable) Weaviate api key	required
description	str	(Mutable) Description of Weaviate provider to be registered	''
team	str	(Mutable) Name of team	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	[]
properties	dict	(Mutable) Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
weaviate	OnlineProvider	Provider

Source code in src/featureform/register.py

def register_weaviate(
    self,
    name: str,
    url: str,
    api_key: str,
    description: str = "",
    team: str = "",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a Weaviate provider.

    **Examples**:
    ```
    weaviate = ff.register_weaviate(
        name="weaviate-quickstart",
        url="https://<CLUSTER NAME>.weaviate.network",
        api_key="<API KEY>"
        description="A Weaviate project for using embeddings in Featureform"
    )
    ```

    Args:
        name (str): (Immutable) Name of Weaviate provider to be registered
        url (str): (Immutable) Endpoint of Weaviate cluster, either in the cloud or via another deployment operation
        api_key (str): (Mutable) Weaviate api key
        description (str): (Mutable) Description of Weaviate provider to be registered
        team (str): (Mutable) Name of team
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources

    Returns:
        weaviate (OnlineProvider): Provider
    """
    config = WeaviateConfig(url=url, api_key=api_key)
    provider = Provider(
        name=name,
        function="ONLINE",
        description=description,
        team=team,
        config=config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return OnlineProvider(self, provider)

Primary Sources

Register a SQL table as a primary data source.

Example

postgres = client.get_provider("my_postgres")
table =  postgres.register_table(
    name="transactions",
    variant="july_2023",
    table="transactions_table",
):

Parameters:

Name	Type	Description	Default
name	str	Name of table to be registered	required
variant	str	Name of variant to be registered	''
table	str	Name of SQL table	required
owner	Union[str, UserRegistrar]	Owner	''
description	str	Description of table to be registered	''

Returns:

Name	Type	Description
source	ColumnSourceRegistrar	source

Source code in src/featureform/register.py

def register_table(
    self,
    name: str,
    table: str,
    variant: str = "",
    owner: Union[str, UserRegistrar] = "",
    description: str = "",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a SQL table as a primary data source.

    **Example**

    ```
    postgres = client.get_provider("my_postgres")
    table =  postgres.register_table(
        name="transactions",
        variant="july_2023",
        table="transactions_table",
    ):
    ```

    Args:
        name (str): Name of table to be registered
        variant (str): Name of variant to be registered
        table (str): Name of SQL table
        owner (Union[str, UserRegistrar]): Owner
        description (str): Description of table to be registered

    Returns:
        source (ColumnSourceRegistrar): source
    """
    return self.__registrar.register_primary_data(
        name=name,
        variant=variant,
        location=SQLTable(table),
        owner=owner,
        provider=self.name(),
        description=description,
        tags=tags,
        properties=properties,
    )

Transformations

featureform.register.ResourceClient

The resource client is used to retrieve information on specific resources (entities, providers, features, labels, training sets, models, users).

Parameters:

Name	Type	Description	Default
host	str	The hostname of the Featureform instance.	None
insecure	bool	True if connecting to an insecure Featureform endpoint. False if using a self-signed or public TLS certificate	False
cert_path	str	The path to a public certificate if using a self-signed certificate.	None

Using the Resource Client:

definitions.py

import featureform as ff
from featureform import ResourceClient

rc = ResourceClient("localhost:8000")

# example query:
redis = client.get_provider("redis-quickstart")

Source code in src/featureform/register.py

class ResourceClient:
    """
    The resource client is used to retrieve information on specific resources
    (entities, providers, features, labels, training sets, models, users).

    Args:
        host (str): The hostname of the Featureform instance.
        insecure (bool): True if connecting to an insecure Featureform endpoint. False if using a self-signed or public TLS certificate
        cert_path (str): The path to a public certificate if using a self-signed certificate.

    **Using the Resource Client:**
    ``` py title="definitions.py"
    import featureform as ff
    from featureform import ResourceClient

    rc = ResourceClient("localhost:8000")

    # example query:
    redis = client.get_provider("redis-quickstart")
    ```
    """

    def __init__(
        self, host=None, local=False, insecure=False, cert_path=None, dry_run=False
    ):
        if local:
            raise Exception(
                "Local mode is not supported in this version. Use featureform <= 1.12.0 for localmode"
            )

        # This line ensures that the warning is only raised if ResourceClient is instantiated directly
        # TODO: Remove this check once ServingClient is deprecated
        is_instantiated_directed = inspect.stack()[1].function != "__init__"
        if is_instantiated_directed:
            warnings.warn(
                "ResourceClient is deprecated and will be removed in future versions; use Client instead.",
                PendingDeprecationWarning,
            )
        self._dry_run = dry_run
        self._stub = None
        self.local = local

        if dry_run:
            return

        host = host or os.getenv("FEATUREFORM_HOST")
        if host is None:
            raise RuntimeError(
                "If not in local mode then `host` must be passed or the environment"
                " variable FEATUREFORM_HOST must be set."
            )
        if insecure:
            channel = insecure_channel(host)
        else:
            channel = secure_channel(host, cert_path)
        self._stub = GrpcClient(ff_grpc.ApiStub(channel))
        self._host = host

    def apply(self, asynchronous=False, verbose=False):
        """
        Apply all definitions, creating and retrieving all specified resources.

        ```python
        import featureform as ff
        client = ff.Client()

        ff.register_postgres(
            host="localhost",
            port=5432,
        )

        client.apply()
        ```

        Args:
            asynchronous (bool): If True, apply will return immediately and not wait for resources to be created. If False, apply will wait for resources to be created and print out the status of each resource.

        """

        try:
            resource_state = state()
            if resource_state.is_empty():
                print("No resources to apply")
                return

            print(f"Applying Run: {get_run()}")

            if self._dry_run:
                print(resource_state.sorted_list())
                return

            resource_state.create_all(
                self._stub, global_registrar.get_client_objects_for_resource()
            )

            if not asynchronous and self._stub:
                resources = resource_state.sorted_list()
                display_statuses(self._stub, resources, verbose=verbose)
        finally:
            if feature_flag.is_enabled("FF_GET_EQUIVALENT_VARIANTS", True):
                set_run("")
            clear_state()

    def get_user(self, name, local=False):
        """Get a user. Prints out name of user, and all resources associated with the user.

        **Examples:**

        ``` py title="Input"
        featureformer = rc.get_user("featureformer")
        ```

        ``` json title="Output"
        // get_user prints out formatted information on user
        USER NAME:                     featureformer
        -----------------------------------------------

        NAME                           VARIANT                        TYPE
        avg_transactions               quickstart                     feature
        fraudulent                     quickstart                     label
        fraud_training                 quickstart                     training set
        transactions                   kaggle                         source
        average_user_transaction       quickstart                     source
        -----------------------------------------------
        ```

        ``` py title="Input"
        print(featureformer)
        ```

        ``` json title="Output"
        // get_user returns the User object

        name: "featureformer"
        features {
        name: "avg_transactions"
        variant: "quickstart"
        }
        labels {
        name: "fraudulent"
        variant: "quickstart"
        }
        trainingsets {
        name: "fraud_training"
        variant: "quickstart"
        }
        sources {
        name: "transactions"
        variant: "kaggle"
        }
        sources {
        name: "average_user_transaction"
        variant: "quickstart"
        }
        ```

        Args:
            name (str): Name of user to be retrieved

        Returns:
            user (User): User
        """
        return get_user_info(self._stub, name)

    def get_entity(self, name, local=False):
        """Get an entity. Prints out information on entity, and all resources associated with the entity.

        **Examples:**

        ``` py title="Input"
        entity = rc.get_entity("user")
        ```

        ``` json title="Output"
        // get_entity prints out formatted information on entity

        ENTITY NAME:                   user
        STATUS:                        NO_STATUS
        -----------------------------------------------

        NAME                           VARIANT                        TYPE
        avg_transactions               quickstart                     feature
        fraudulent                     quickstart                     label
        fraud_training                 quickstart                     training set
        -----------------------------------------------
        ```

        ``` py title="Input"
        print(postgres)
        ```

        ``` json title="Output"
        // get_entity returns the Entity object

        name: "user"
        features {
            name: "avg_transactions"
            variant: "quickstart"
        }
        labels {
            name: "fraudulent"
            variant: "quickstart"
        }
        trainingsets {
            name: "fraud_training"
            variant: "quickstart"
        }
        ```
        """
        return get_entity_info(self._stub, name)

    def get_model(self, name, local=False) -> Model:
        """Get a model. Prints out information on model, and all resources associated with the model.

        Args:
            name (str): Name of model to be retrieved

        Returns:
            model (Model): Model
        """
        model = None
        model_proto = get_resource_info(self._stub, "model", name)
        if model_proto is not None:
            model = Model(model_proto.name, description="", tags=[], properties={})

        return model

    def get_provider(self, name, local=False):
        """Get a provider. Prints out information on provider, and all resources associated with the provider.

        **Examples:**

        ``` py title="Input"
        postgres = client.get_provider("postgres-quickstart")
        ```

        ``` json title="Output"
        // get_provider prints out formatted information on provider

        NAME:                          postgres-quickstart
        DESCRIPTION:                   A Postgres deployment we created for the Featureform quickstart
        TYPE:                          POSTGRES_OFFLINE
        SOFTWARE:                      postgres
        STATUS:                        NO_STATUS
        -----------------------------------------------
        SOURCES:
        NAME                           VARIANT
        transactions                   kaggle
        average_user_transaction       quickstart
        -----------------------------------------------
        FEATURES:
        NAME                           VARIANT
        -----------------------------------------------
        LABELS:
        NAME                           VARIANT
        fraudulent                     quickstart
        -----------------------------------------------
        TRAINING SETS:
        NAME                           VARIANT
        fraud_training                 quickstart
        -----------------------------------------------
        ```

        ``` py title="Input"
        print(postgres)
        ```

        ``` json title="Output"
        // get_provider returns the Provider object

        name: "postgres-quickstart"
        description: "A Postgres deployment we created for the Featureform quickstart"
        type: "POSTGRES_OFFLINE"
        software: "postgres"
        serialized_config: "{\"Host\": \"quickstart-postgres\",
                            \"Port\": \"5432\",
                            \"Username\": \"postgres\",
                            \"Password\": \"password\",
                            \"Database\": \"postgres\"}"
        sources {
        name: "transactions"
        variant: "kaggle"
        }
        sources {
        name: "average_user_transaction"
        variant: "quickstart"
        }
        trainingsets {
        name: "fraud_training"
        variant: "quickstart"
        }
        labels {
        name: "fraudulent"
        variant: "quickstart"
        }
        ```

        Args:
            name (str): Name of provider to be retrieved

        Returns:
            provider (Provider): Provider
        """
        return get_provider_info(self._stub, name)

    def get_feature(self, name, variant):
        name_variant = metadata_pb2.NameVariant(name=name, variant=variant)
        feature = None
        for x in self._stub.GetFeatureVariants(iter([name_variant])):
            feature = x
            break

        return FeatureVariant(
            created=None,
            name=feature.name,
            variant=feature.variant,
            source=(feature.source.name, feature.source.variant),
            value_type=feature.type,
            entity=feature.entity,
            owner=feature.owner,
            provider=feature.provider,
            location=ResourceColumnMapping("", "", ""),
            description=feature.description,
            status=feature.status.Status._enum_type.values[feature.status.status].name,
        )

    def print_feature(self, name, variant=None, local=False):
        """Get a feature. Prints out information on feature, and all variants associated with the feature. If variant is included, print information on that specific variant and all resources associated with it.

        **Examples:**

        ``` py title="Input"
        avg_transactions = rc.get_feature("avg_transactions")
        ```

        ``` json title="Output"
        // get_feature prints out formatted information on feature

        NAME:                          avg_transactions
        STATUS:                        NO_STATUS
        -----------------------------------------------
        VARIANTS:
        quickstart                     default
        -----------------------------------------------
        ```

        ``` py title="Input"
        print(avg_transactions)
        ```

        ``` json title="Output"
        // get_feature returns the Feature object

        name: "avg_transactions"
        default_variant: "quickstart"
        variants: "quickstart"
        ```

        ``` py title="Input"
        avg_transactions_variant = ff.get_feature("avg_transactions", "quickstart")
        ```

        ``` json title="Output"
        // get_feature with variant provided prints out formatted information on feature variant

        NAME:                          avg_transactions
        VARIANT:                       quickstart
        TYPE:                          float32
        ENTITY:                        user
        OWNER:                         featureformer
        PROVIDER:                      redis-quickstart
        STATUS:                        NO_STATUS
        -----------------------------------------------
        SOURCE:
        NAME                           VARIANT
        average_user_transaction       quickstart
        -----------------------------------------------
        TRAINING SETS:
        NAME                           VARIANT
        fraud_training                 quickstart
        -----------------------------------------------
        ```

        ``` py title="Input"
        print(avg_transactions_variant)
        ```

        ``` json title="Output"
        // get_feature returns the FeatureVariant object

        name: "avg_transactions"
        variant: "quickstart"
        source {
        name: "average_user_transaction"
        variant: "quickstart"
        }
        type: "float32"
        entity: "user"
        created {
        seconds: 1658168552
        nanos: 142461900
        }
        owner: "featureformer"
        provider: "redis-quickstart"
        trainingsets {
        name: "fraud_training"
        variant: "quickstart"
        }
        columns {
        entity: "user_id"
        value: "avg_transaction_amt"
        }
        ```

        Args:
            name (str): Name of feature to be retrieved
            variant (str): Name of variant of feature

        Returns:
            feature (Union[Feature, FeatureVariant]): Feature or FeatureVariant
        """
        if not variant:
            return get_resource_info(self._stub, "feature", name)
        return get_feature_variant_info(self._stub, name, variant)

    def get_label(self, name, variant):
        name_variant = metadata_pb2.NameVariant(name=name, variant=variant)
        label = None
        for x in self._stub.GetLabelVariants(iter([name_variant])):
            label = x
            break

        return LabelVariant(
            name=label.name,
            variant=label.variant,
            source=(label.source.name, label.source.variant),
            value_type=label.type,
            entity=label.entity,
            owner=label.owner,
            provider=label.provider,
            location=ResourceColumnMapping("", "", ""),
            description=label.description,
            status=label.status.Status._enum_type.values[label.status.status].name,
        )

    def print_label(self, name, variant=None, local=False):
        """Get a label. Prints out information on label, and all variants associated with the label. If variant is included, print information on that specific variant and all resources associated with it.

        **Examples:**

        ``` py title="Input"
        fraudulent = rc.get_label("fraudulent")
        ```

        ``` json title="Output"
        // get_label prints out formatted information on label

        NAME:                          fraudulent
        STATUS:                        NO_STATUS
        -----------------------------------------------
        VARIANTS:
        quickstart                     default
        -----------------------------------------------
        ```

        ``` py title="Input"
        print(fraudulent)
        ```

        ``` json title="Output"
        // get_label returns the Label object

        name: "fraudulent"
        default_variant: "quickstart"
        variants: "quickstart"
        ```

        ``` py title="Input"
        fraudulent_variant = ff.get_label("fraudulent", "quickstart")
        ```

        ``` json title="Output"
        // get_label with variant provided prints out formatted information on label variant

        NAME:                          fraudulent
        VARIANT:                       quickstart
        TYPE:                          bool
        ENTITY:                        user
        OWNER:                         featureformer
        PROVIDER:                      postgres-quickstart
        STATUS:                        NO_STATUS
        -----------------------------------------------
        SOURCE:
        NAME                           VARIANT
        transactions                   kaggle
        -----------------------------------------------
        TRAINING SETS:
        NAME                           VARIANT
        fraud_training                 quickstart
        -----------------------------------------------
        ```

        ``` py title="Input"
        print(fraudulent_variant)
        ```

        ``` json title="Output"
        // get_label returns the LabelVariant object

        name: "fraudulent"
        variant: "quickstart"
        type: "bool"
        source {
        name: "transactions"
        variant: "kaggle"
        }
        entity: "user"
        created {
        seconds: 1658168552
        nanos: 154924300
        }
        owner: "featureformer"
        provider: "postgres-quickstart"
        trainingsets {
        name: "fraud_training"
        variant: "quickstart"
        }
        columns {
        entity: "customerid"
        value: "isfraud"
        }
        ```

        Args:
            name (str): Name of label to be retrieved
            variant (str): Name of variant of label

        Returns:
            label (Union[label, LabelVariant]): Label or LabelVariant
        """
        if not variant:
            return get_resource_info(self._stub, "label", name)
        return get_label_variant_info(self._stub, name, variant)

    def get_training_set(self, name, variant):
        name_variant = metadata_pb2.NameVariant(name=name, variant=variant)
        ts = None
        for x in self._stub.GetTrainingSetVariants(iter([name_variant])):
            ts = x
            break

        return TrainingSetVariant(
            created=None,
            name=ts.name,
            variant=ts.variant,
            owner=ts.owner,
            description=ts.description,
            status=ts.status.Status._enum_type.values[ts.status.status].name,
            label=(ts.label.name, ts.label.variant),
            features=[(f.name, f.variant) for f in ts.features],
            feature_lags=[],
            provider=ts.provider,
            # TODO: apply values from proto
            tags=[],
            properties={},
        )

    def print_training_set(self, name, variant=None, local=False):
        """Get a training set. Prints out information on training set, and all variants associated with the training set. If variant is included, print information on that specific variant and all resources associated with it.

        **Examples:**

        ``` py title="Input"
        fraud_training = rc.get_training_set("fraud_training")
        ```

        ``` json title="Output"
        // get_training_set prints out formatted information on training set

        NAME:                          fraud_training
        STATUS:                        NO_STATUS
        -----------------------------------------------
        VARIANTS:
        quickstart                     default
        -----------------------------------------------
        ```

        ``` py title="Input"
        print(fraud_training)
        ```

        ``` json title="Output"
        // get_training_set returns the TrainingSet object

        name: "fraud_training"
        default_variant: "quickstart"
        variants: "quickstart"
        ```

        ``` py title="Input"
        fraudulent_variant = ff.get_training set("fraudulent", "quickstart")
        ```

        ``` json title="Output"
        // get_training_set with variant provided prints out formatted information on training set variant

        NAME:                          fraud_training
        VARIANT:                       quickstart
        OWNER:                         featureformer
        PROVIDER:                      postgres-quickstart
        STATUS:                        NO_STATUS
        -----------------------------------------------
        LABEL:
        NAME                           VARIANT
        fraudulent                     quickstart
        -----------------------------------------------
        FEATURES:
        NAME                           VARIANT
        avg_transactions               quickstart
        -----------------------------------------------
        ```

        ``` py title="Input"
        print(fraudulent_variant)
        ```

        ``` json title="Output"
        // get_training_set returns the TrainingSetVariant object

        name: "fraud_training"
        variant: "quickstart"
        owner: "featureformer"
        created {
        seconds: 1658168552
        nanos: 157934800
        }
        provider: "postgres-quickstart"
        features {
        name: "avg_transactions"
        variant: "quickstart"
        }
        label {
        name: "fraudulent"
        variant: "quickstart"
        }
        ```

        Args:
            name (str): Name of training set to be retrieved
            variant (str): Name of variant of training set

        Returns:
            training_set (Union[TrainingSet, TrainingSetVariant]): TrainingSet or TrainingSetVariant
        """
        if not variant:
            return get_resource_info(self._stub, "training-set", name)
        return get_training_set_variant_info(self._stub, name, variant)

    def get_source(self, name, variant):
        name_variant = metadata_pb2.NameVariantRequest(
            name_variant=metadata_pb2.NameVariant(name=name, variant=variant)
        )
        source = None
        for x in self._stub.GetSourceVariants(iter([name_variant])):
            source = x
            break

        definition = self._get_source_definition(source)

        source_variant = SourceVariant(
            created=None,
            name=source.name,
            definition=definition,
            owner=source.owner,
            provider=source.provider,
            description=source.description,
            variant=source.variant,
            status=source.status.Status._enum_type.values[source.status.status].name,
            tags=[],
            properties={},
            source_text=(
                definition.source_text if type(definition) == DFTransformation else ""
            ),
        )
        return ColumnSourceRegistrar(self, source_variant)

    def _get_source_definition(self, source):
        if source.primaryData.table.name:
            return PrimaryData(SQLTable(source.primaryData.table.name))
        elif source.transformation:
            return self._get_transformation_definition(source)
        else:
            raise Exception(f"Invalid source type {source}")

    def _get_transformation_definition(self, source):
        if source.transformation.DFTransformation.query != bytes():
            transformation = source.transformation.DFTransformation
            return DFTransformation(
                query=transformation.query,
                inputs=[(input.name, input.variant) for input in transformation.inputs],
                source_text=transformation.source_text,
            )
        elif source.transformation.SQLTransformation.query != "":
            return SQLTransformation(source.transformation.SQLTransformation.query)
        else:
            raise Exception(f"Invalid transformation type {source}")

    def print_source(self, name, variant=None, local=False):
        """Get a source. Prints out information on source, and all variants associated with the source. If variant is included, print information on that specific variant and all resources associated with it.

        **Examples:**

        ``` py title="Input"
        transactions = rc.get_transactions("transactions")
        ```

        ``` json title="Output"
        // get_source prints out formatted information on source

        NAME:                          transactions
        STATUS:                        NO_STATUS
        -----------------------------------------------
        VARIANTS:
        kaggle                         default
        -----------------------------------------------
        ```

        ``` py title="Input"
        print(transactions)
        ```

        ``` json title="Output"
        // get_source returns the Source object

        name: "transactions"
        default_variant: "kaggle"
        variants: "kaggle"
        ```

        ``` py title="Input"
        transactions_variant = rc.get_source("transactions", "kaggle")
        ```

        ``` json title="Output"
        // get_source with variant provided prints out formatted information on source variant

        NAME:                          transactions
        VARIANT:                       kaggle
        OWNER:                         featureformer
        DESCRIPTION:                   Fraud Dataset From Kaggle
        PROVIDER:                      postgres-quickstart
        STATUS:                        NO_STATUS
        -----------------------------------------------
        DEFINITION:
        TRANSFORMATION

        -----------------------------------------------
        SOURCES
        NAME                           VARIANT
        -----------------------------------------------
        PRIMARY DATA
        Transactions
        FEATURES:
        NAME                           VARIANT
        -----------------------------------------------
        LABELS:
        NAME                           VARIANT
        fraudulent                     quickstart
        -----------------------------------------------
        TRAINING SETS:
        NAME                           VARIANT
        fraud_training                 quickstart
        -----------------------------------------------
        ```

        ``` py title="Input"
        print(transactions_variant)
        ```

        ``` json title="Output"
        // get_source returns the SourceVariant object

        name: "transactions"
        variant: "kaggle"
        owner: "featureformer"
        description: "Fraud Dataset From Kaggle"
        provider: "postgres-quickstart"
        created {
        seconds: 1658168552
        nanos: 128768000
        }
        trainingsets {
        name: "fraud_training"
        variant: "quickstart"
        }
        labels {
        name: "fraudulent"
        variant: "quickstart"
        }
        primaryData {
        table {
            name: "Transactions"
        }
        }
        ```

        Args:
            name (str): Name of source to be retrieved
            variant (str): Name of variant of source

        Returns:
            source (Union[Source, SourceVariant]): Source or SourceVariant
        """
        if not variant:
            return get_resource_info(self._stub, "source", name)
        return get_source_variant_info(self._stub, name, variant)

    def list_features(self, local=False):
        """List all features.

        **Examples:**
        ``` py title="Input"
        features_list = rc.list_features()
        ```

        ``` json title="Output"
        // list_features prints out formatted information on all features

        NAME                           VARIANT                        STATUS
        user_age                       quickstart (default)           READY
        avg_transactions               quickstart (default)           READY
        avg_transactions               production                     CREATED
        ```

        ``` py title="Input"
        print(features_list)
        ```

        ``` json title="Output"
        // list_features returns a list of Feature objects

        [name: "user_age"
        default_variant: "quickstart"
        variants: "quickstart"
        , name: "avg_transactions"
        default_variant: "quickstart"
        variants: "quickstart"
        variants: "production"
        ]
        ```

        Returns:
            features (List[Feature]): List of Feature Objects
        """
        return list_name_variant_status(self._stub, "feature")

    def list_labels(self, local=False):
        """List all labels.

        **Examples:**
        ``` py title="Input"
        features_list = rc.list_labels()
        ```

        ``` json title="Output"
        // list_labels prints out formatted information on all labels

        NAME                           VARIANT                        STATUS
        user_age                       quickstart (default)           READY
        avg_transactions               quickstart (default)           READY
        avg_transactions               production                     CREATED
        ```

        ``` py title="Input"
        print(label_list)
        ```

        ``` json title="Output"
        // list_features returns a list of Feature objects

        [name: "user_age"
        default_variant: "quickstart"
        variants: "quickstart"
        , name: "avg_transactions"
        default_variant: "quickstart"
        variants: "quickstart"
        variants: "production"
        ]
        ```

        Returns:
            labels (List[Label]): List of Label Objects
        """
        return list_name_variant_status(self._stub, "label")

    def list_users(self, local=False):
        """List all users. Prints a list of all users.

        **Examples:**
        ``` py title="Input"
        users_list = rc.list_users()
        ```

        ``` json title="Output"
        // list_users prints out formatted information on all users

        NAME                           STATUS
        featureformer                  NO_STATUS
        featureformers_friend          CREATED
        ```

        ``` py title="Input"
        print(features_list)
        ```

        ``` json title="Output"
        // list_features returns a list of Feature objects

        [name: "featureformer"
        features {
        name: "avg_transactions"
        variant: "quickstart"
        }
        labels {
        name: "fraudulent"
        variant: "quickstart"
        }
        trainingsets {
        name: "fraud_training"
        variant: "quickstart"
        }
        sources {
        name: "transactions"
        variant: "kaggle"
        }
        sources {
        name: "average_user_transaction"
        variant: "quickstart"
        },
        name: "featureformers_friend"
        features {
        name: "user_age"
        variant: "production"
        }
        sources {
        name: "user_profiles"
        variant: "production"
        }
        ]
        ```

        Returns:
            users (List[User]): List of User Objects
        """
        return list_name_status(self._stub, "user")

    def list_entities(self, local=False):
        """List all entities. Prints a list of all entities.

        **Examples:**
        ``` py title="Input"
        entities = rc.list_entities()
        ```

        ``` json title="Output"
        // list_entities prints out formatted information on all entities

        NAME                           STATUS
        user                           CREATED
        transaction                    CREATED
        ```

        ``` py title="Input"
        print(features_list)
        ```

        ``` json title="Output"
        // list_entities returns a list of Entity objects

        [name: "user"
        features {
        name: "avg_transactions"
        variant: "quickstart"
        }
        features {
        name: "avg_transactions"
        variant: "production"
        }
        features {
        name: "user_age"
        variant: "quickstart"
        }
        labels {
        name: "fraudulent"
        variant: "quickstart"
        }
        trainingsets {
        name: "fraud_training"
        variant: "quickstart"
        }
        ,
        name: "transaction"
        features {
        name: "amount_spent"
        variant: "production"
        }
        ]
        ```

        Returns:
            entities (List[Entity]): List of Entity Objects
        """
        return list_name_status(self._stub, "entity")

    def list_sources(self, local=False):
        """List all sources. Prints a list of all sources.

        **Examples:**
        ``` py title="Input"
        sources_list = rc.list_sources()
        ```

        ``` json title="Output"
        // list_sources prints out formatted information on all sources

        NAME                           VARIANT                        STATUS                         DESCRIPTION
        average_user_transaction       quickstart (default)           NO_STATUS                      the average transaction amount for a user
        transactions                   kaggle (default)               NO_STATUS                      Fraud Dataset From Kaggle
        ```

        ``` py title="Input"
        print(sources_list)
        ```

        ``` json title="Output"
        // list_sources returns a list of Source objects

        [name: "average_user_transaction"
        default_variant: "quickstart"
        variants: "quickstart"
        , name: "transactions"
        default_variant: "kaggle"
        variants: "kaggle"
        ]
        ```

        Returns:
            sources (List[Source]): List of Source Objects
        """
        return list_name_variant_status_desc(self._stub, "source")

    def list_training_sets(self, local=False):
        """List all training sets. Prints a list of all training sets.

        **Examples:**
        ``` py title="Input"
        training_sets_list = rc.list_training_sets()
        ```

        ``` json title="Output"
        // list_training_sets prints out formatted information on all training sets

        NAME                           VARIANT                        STATUS                         DESCRIPTION
        fraud_training                 quickstart (default)           READY                          Training set for fraud detection.
        fraud_training                 v2                             CREATED                        Improved training set for fraud detection.
        recommender                    v1 (default)                   CREATED                        Training set for recommender system.
        ```

        ``` py title="Input"
        print(training_sets_list)
        ```

        ``` json title="Output"
        // list_training_sets returns a list of TrainingSet objects

        [name: "fraud_training"
        default_variant: "quickstart"
        variants: "quickstart", "v2",
        name: "recommender"
        default_variant: "v1"
        variants: "v1"
        ]
        ```

        Returns:
            training_sets (List[TrainingSet]): List of TrainingSet Objects
        """
        return list_name_variant_status_desc(self._stub, "training-set")

    def list_models(self, local=False) -> List[Model]:
        """List all models. Prints a list of all models.

        Returns:
            models (List[Model]): List of Model Objects
        """
        model_protos = list_name(self._stub, "model")
        # TODO: apply values from proto
        models = [Model(proto.name, tags=[], properties={}) for proto in model_protos]

        return models

    def list_providers(self, local=False):
        """List all providers. Prints a list of all providers.

        **Examples:**
        ``` py title="Input"
        providers_list = rc.list_providers()
        ```

        ``` json title="Output"
        // list_providers prints out formatted information on all providers

        NAME                           STATUS                         DESCRIPTION
        redis-quickstart               CREATED                      A Redis deployment we created for the Featureform quickstart
        postgres-quickstart            CREATED                      A Postgres deployment we created for the Featureform quickst
        ```

        ``` py title="Input"
        print(providers_list)
        ```

        ``` json title="Output"
        // list_providers returns a list of Providers objects

        [name: "redis-quickstart"
        description: "A Redis deployment we created for the Featureform quickstart"
        type: "REDIS_ONLINE"
        software: "redis"
        serialized_config: "{\"Addr\": \"quickstart-redis:6379\", \"Password\": \"\", \"DB\": 0}"
        features {
        name: "avg_transactions"
        variant: "quickstart"
        }
        features {
        name: "avg_transactions"
        variant: "production"
        }
        features {
        name: "user_age"
        variant: "quickstart"
        }
        , name: "postgres-quickstart"
        description: "A Postgres deployment we created for the Featureform quickstart"
        type: "POSTGRES_OFFLINE"
        software: "postgres"
        serialized_config: "{\"Host\": \"quickstart-postgres\", \"Port\": \"5432\", \"Username\": \"postgres\", \"Password\": \"password\", \"Database\": \"postgres\"}"
        sources {
        name: "transactions"
        variant: "kaggle"
        }
        sources {
        name: "average_user_transaction"
        variant: "quickstart"
        }
        trainingsets {
        name: "fraud_training"
        variant: "quickstart"
        }
        labels {
        name: "fraudulent"
        variant: "quickstart"
        }
        ]
        ```

        Returns:
            providers (List[Provider]): List of Provider Objects
        """
        return list_name_status_desc(self._stub, "provider")

    def search(self, raw_query, local=False):
        """Search for registered resources. Prints a list of results.

        **Examples:**
        ``` py title="Input"
        providers_list = rc.search("transact")
        ```

        ``` json title="Output"
        // search prints out formatted information on all matches

        NAME                           VARIANT            TYPE
        avg_transactions               default            Source
        ```
        """
        if type(raw_query) != str or len(raw_query) == 0:
            raise Exception("query must be string and cannot be empty")
        processed_query = raw_query.translate({ord(i): None for i in ".,-@!*#"})
        return search(processed_query, self._host)

apply(asynchronous=False, verbose=False)

Apply all definitions, creating and retrieving all specified resources.

import featureform as ff
client = ff.Client()

ff.register_postgres(
    host="localhost",
    port=5432,
)

client.apply()

Parameters:

Name	Type	Description	Default
asynchronous	bool	If True, apply will return immediately and not wait for resources to be created. If False, apply will wait for resources to be created and print out the status of each resource.	False

Source code in src/featureform/register.py

def apply(self, asynchronous=False, verbose=False):
    """
    Apply all definitions, creating and retrieving all specified resources.

    ```python
    import featureform as ff
    client = ff.Client()

    ff.register_postgres(
        host="localhost",
        port=5432,
    )

    client.apply()
    ```

    Args:
        asynchronous (bool): If True, apply will return immediately and not wait for resources to be created. If False, apply will wait for resources to be created and print out the status of each resource.

    """

    try:
        resource_state = state()
        if resource_state.is_empty():
            print("No resources to apply")
            return

        print(f"Applying Run: {get_run()}")

        if self._dry_run:
            print(resource_state.sorted_list())
            return

        resource_state.create_all(
            self._stub, global_registrar.get_client_objects_for_resource()
        )

        if not asynchronous and self._stub:
            resources = resource_state.sorted_list()
            display_statuses(self._stub, resources, verbose=verbose)
    finally:
        if feature_flag.is_enabled("FF_GET_EQUIVALENT_VARIANTS", True):
            set_run("")
        clear_state()

get_entity(name, local=False)

Get an entity. Prints out information on entity, and all resources associated with the entity.

Examples:

Input

entity = rc.get_entity("user")

Output

// get_entity prints out formatted information on entity

ENTITY NAME:                   user
STATUS:                        NO_STATUS
-----------------------------------------------

NAME                           VARIANT                        TYPE
avg_transactions               quickstart                     feature
fraudulent                     quickstart                     label
fraud_training                 quickstart                     training set
-----------------------------------------------

Input

print(postgres)

Output

// get_entity returns the Entity object

name: "user"
features {
    name: "avg_transactions"
    variant: "quickstart"
}
labels {
    name: "fraudulent"
    variant: "quickstart"
}
trainingsets {
    name: "fraud_training"
    variant: "quickstart"
}

Source code in src/featureform/register.py

def get_entity(self, name, local=False):
    """Get an entity. Prints out information on entity, and all resources associated with the entity.

    **Examples:**

    ``` py title="Input"
    entity = rc.get_entity("user")
    ```

    ``` json title="Output"
    // get_entity prints out formatted information on entity

    ENTITY NAME:                   user
    STATUS:                        NO_STATUS
    -----------------------------------------------

    NAME                           VARIANT                        TYPE
    avg_transactions               quickstart                     feature
    fraudulent                     quickstart                     label
    fraud_training                 quickstart                     training set
    -----------------------------------------------
    ```

    ``` py title="Input"
    print(postgres)
    ```

    ``` json title="Output"
    // get_entity returns the Entity object

    name: "user"
    features {
        name: "avg_transactions"
        variant: "quickstart"
    }
    labels {
        name: "fraudulent"
        variant: "quickstart"
    }
    trainingsets {
        name: "fraud_training"
        variant: "quickstart"
    }
    ```
    """
    return get_entity_info(self._stub, name)

get_model(name, local=False)

Get a model. Prints out information on model, and all resources associated with the model.

Parameters:

Name	Type	Description	Default
name	str	Name of model to be retrieved	required

Returns:

Name	Type	Description
model	Model	Model

Source code in src/featureform/register.py

def get_model(self, name, local=False) -> Model:
    """Get a model. Prints out information on model, and all resources associated with the model.

    Args:
        name (str): Name of model to be retrieved

    Returns:
        model (Model): Model
    """
    model = None
    model_proto = get_resource_info(self._stub, "model", name)
    if model_proto is not None:
        model = Model(model_proto.name, description="", tags=[], properties={})

    return model

get_provider(name, local=False)

Get a provider. Prints out information on provider, and all resources associated with the provider.

Examples:

Input

postgres = client.get_provider("postgres-quickstart")

Output

// get_provider prints out formatted information on provider

NAME:                          postgres-quickstart
DESCRIPTION:                   A Postgres deployment we created for the Featureform quickstart
TYPE:                          POSTGRES_OFFLINE
SOFTWARE:                      postgres
STATUS:                        NO_STATUS
-----------------------------------------------
SOURCES:
NAME                           VARIANT
transactions                   kaggle
average_user_transaction       quickstart
-----------------------------------------------
FEATURES:
NAME                           VARIANT
-----------------------------------------------
LABELS:
NAME                           VARIANT
fraudulent                     quickstart
-----------------------------------------------
TRAINING SETS:
NAME                           VARIANT
fraud_training                 quickstart
-----------------------------------------------

Input

print(postgres)

Output

// get_provider returns the Provider object

name: "postgres-quickstart"
description: "A Postgres deployment we created for the Featureform quickstart"
type: "POSTGRES_OFFLINE"
software: "postgres"
serialized_config: "{"Host": "quickstart-postgres",
                    "Port": "5432",
                    "Username": "postgres",
                    "Password": "password",
                    "Database": "postgres"}"
sources {
name: "transactions"
variant: "kaggle"
}
sources {
name: "average_user_transaction"
variant: "quickstart"
}
trainingsets {
name: "fraud_training"
variant: "quickstart"
}
labels {
name: "fraudulent"
variant: "quickstart"
}

Parameters:

Name	Type	Description	Default
name	str	Name of provider to be retrieved	required

Returns:

Name	Type	Description
provider	Provider	Provider

Source code in src/featureform/register.py

def get_provider(self, name, local=False):
    """Get a provider. Prints out information on provider, and all resources associated with the provider.

    **Examples:**

    ``` py title="Input"
    postgres = client.get_provider("postgres-quickstart")
    ```

    ``` json title="Output"
    // get_provider prints out formatted information on provider

    NAME:                          postgres-quickstart
    DESCRIPTION:                   A Postgres deployment we created for the Featureform quickstart
    TYPE:                          POSTGRES_OFFLINE
    SOFTWARE:                      postgres
    STATUS:                        NO_STATUS
    -----------------------------------------------
    SOURCES:
    NAME                           VARIANT
    transactions                   kaggle
    average_user_transaction       quickstart
    -----------------------------------------------
    FEATURES:
    NAME                           VARIANT
    -----------------------------------------------
    LABELS:
    NAME                           VARIANT
    fraudulent                     quickstart
    -----------------------------------------------
    TRAINING SETS:
    NAME                           VARIANT
    fraud_training                 quickstart
    -----------------------------------------------
    ```

    ``` py title="Input"
    print(postgres)
    ```

    ``` json title="Output"
    // get_provider returns the Provider object

    name: "postgres-quickstart"
    description: "A Postgres deployment we created for the Featureform quickstart"
    type: "POSTGRES_OFFLINE"
    software: "postgres"
    serialized_config: "{\"Host\": \"quickstart-postgres\",
                        \"Port\": \"5432\",
                        \"Username\": \"postgres\",
                        \"Password\": \"password\",
                        \"Database\": \"postgres\"}"
    sources {
    name: "transactions"
    variant: "kaggle"
    }
    sources {
    name: "average_user_transaction"
    variant: "quickstart"
    }
    trainingsets {
    name: "fraud_training"
    variant: "quickstart"
    }
    labels {
    name: "fraudulent"
    variant: "quickstart"
    }
    ```

    Args:
        name (str): Name of provider to be retrieved

    Returns:
        provider (Provider): Provider
    """
    return get_provider_info(self._stub, name)

get_user(name, local=False)

Get a user. Prints out name of user, and all resources associated with the user.

Examples:

Input

featureformer = rc.get_user("featureformer")

Output

// get_user prints out formatted information on user
USER NAME:                     featureformer
-----------------------------------------------

NAME                           VARIANT                        TYPE
avg_transactions               quickstart                     feature
fraudulent                     quickstart                     label
fraud_training                 quickstart                     training set
transactions                   kaggle                         source
average_user_transaction       quickstart                     source
-----------------------------------------------

Input

print(featureformer)

Output

// get_user returns the User object

name: "featureformer"
features {
name: "avg_transactions"
variant: "quickstart"
}
labels {
name: "fraudulent"
variant: "quickstart"
}
trainingsets {
name: "fraud_training"
variant: "quickstart"
}
sources {
name: "transactions"
variant: "kaggle"
}
sources {
name: "average_user_transaction"
variant: "quickstart"
}

Parameters:

Name	Type	Description	Default
name	str	Name of user to be retrieved	required

Returns:

Name	Type	Description
user	User	User

Source code in src/featureform/register.py

def get_user(self, name, local=False):
    """Get a user. Prints out name of user, and all resources associated with the user.

    **Examples:**

    ``` py title="Input"
    featureformer = rc.get_user("featureformer")
    ```

    ``` json title="Output"
    // get_user prints out formatted information on user
    USER NAME:                     featureformer
    -----------------------------------------------

    NAME                           VARIANT                        TYPE
    avg_transactions               quickstart                     feature
    fraudulent                     quickstart                     label
    fraud_training                 quickstart                     training set
    transactions                   kaggle                         source
    average_user_transaction       quickstart                     source
    -----------------------------------------------
    ```

    ``` py title="Input"
    print(featureformer)
    ```

    ``` json title="Output"
    // get_user returns the User object

    name: "featureformer"
    features {
    name: "avg_transactions"
    variant: "quickstart"
    }
    labels {
    name: "fraudulent"
    variant: "quickstart"
    }
    trainingsets {
    name: "fraud_training"
    variant: "quickstart"
    }
    sources {
    name: "transactions"
    variant: "kaggle"
    }
    sources {
    name: "average_user_transaction"
    variant: "quickstart"
    }
    ```

    Args:
        name (str): Name of user to be retrieved

    Returns:
        user (User): User
    """
    return get_user_info(self._stub, name)

list_entities(local=False)

List all entities. Prints a list of all entities.

Examples:

Input

entities = rc.list_entities()

Output

// list_entities prints out formatted information on all entities

NAME                           STATUS
user                           CREATED
transaction                    CREATED

Input

print(features_list)

Output

// list_entities returns a list of Entity objects

[name: "user"
features {
name: "avg_transactions"
variant: "quickstart"
}
features {
name: "avg_transactions"
variant: "production"
}
features {
name: "user_age"
variant: "quickstart"
}
labels {
name: "fraudulent"
variant: "quickstart"
}
trainingsets {
name: "fraud_training"
variant: "quickstart"
}
,
name: "transaction"
features {
name: "amount_spent"
variant: "production"
}
]

Returns:

Name	Type	Description
entities	List[Entity]	List of Entity Objects

Source code in src/featureform/register.py

def list_entities(self, local=False):
    """List all entities. Prints a list of all entities.

    **Examples:**
    ``` py title="Input"
    entities = rc.list_entities()
    ```

    ``` json title="Output"
    // list_entities prints out formatted information on all entities

    NAME                           STATUS
    user                           CREATED
    transaction                    CREATED
    ```

    ``` py title="Input"
    print(features_list)
    ```

    ``` json title="Output"
    // list_entities returns a list of Entity objects

    [name: "user"
    features {
    name: "avg_transactions"
    variant: "quickstart"
    }
    features {
    name: "avg_transactions"
    variant: "production"
    }
    features {
    name: "user_age"
    variant: "quickstart"
    }
    labels {
    name: "fraudulent"
    variant: "quickstart"
    }
    trainingsets {
    name: "fraud_training"
    variant: "quickstart"
    }
    ,
    name: "transaction"
    features {
    name: "amount_spent"
    variant: "production"
    }
    ]
    ```

    Returns:
        entities (List[Entity]): List of Entity Objects
    """
    return list_name_status(self._stub, "entity")

list_features(local=False)

List all features.

Examples:

Input

features_list = rc.list_features()

Output

// list_features prints out formatted information on all features

NAME                           VARIANT                        STATUS
user_age                       quickstart (default)           READY
avg_transactions               quickstart (default)           READY
avg_transactions               production                     CREATED

Input

print(features_list)

Output

// list_features returns a list of Feature objects

[name: "user_age"
default_variant: "quickstart"
variants: "quickstart"
, name: "avg_transactions"
default_variant: "quickstart"
variants: "quickstart"
variants: "production"
]

Returns:

Name	Type	Description
features	List[Feature]	List of Feature Objects

Source code in src/featureform/register.py

def list_features(self, local=False):
    """List all features.

    **Examples:**
    ``` py title="Input"
    features_list = rc.list_features()
    ```

    ``` json title="Output"
    // list_features prints out formatted information on all features

    NAME                           VARIANT                        STATUS
    user_age                       quickstart (default)           READY
    avg_transactions               quickstart (default)           READY
    avg_transactions               production                     CREATED
    ```

    ``` py title="Input"
    print(features_list)
    ```

    ``` json title="Output"
    // list_features returns a list of Feature objects

    [name: "user_age"
    default_variant: "quickstart"
    variants: "quickstart"
    , name: "avg_transactions"
    default_variant: "quickstart"
    variants: "quickstart"
    variants: "production"
    ]
    ```

    Returns:
        features (List[Feature]): List of Feature Objects
    """
    return list_name_variant_status(self._stub, "feature")

list_labels(local=False)

List all labels.

Examples:

Input

features_list = rc.list_labels()

Output

// list_labels prints out formatted information on all labels

NAME                           VARIANT                        STATUS
user_age                       quickstart (default)           READY
avg_transactions               quickstart (default)           READY
avg_transactions               production                     CREATED

Input

print(label_list)

Output

// list_features returns a list of Feature objects

[name: "user_age"
default_variant: "quickstart"
variants: "quickstart"
, name: "avg_transactions"
default_variant: "quickstart"
variants: "quickstart"
variants: "production"
]

Returns:

Name	Type	Description
labels	List[Label]	List of Label Objects

Source code in src/featureform/register.py

def list_labels(self, local=False):
    """List all labels.

    **Examples:**
    ``` py title="Input"
    features_list = rc.list_labels()
    ```

    ``` json title="Output"
    // list_labels prints out formatted information on all labels

    NAME                           VARIANT                        STATUS
    user_age                       quickstart (default)           READY
    avg_transactions               quickstart (default)           READY
    avg_transactions               production                     CREATED
    ```

    ``` py title="Input"
    print(label_list)
    ```

    ``` json title="Output"
    // list_features returns a list of Feature objects

    [name: "user_age"
    default_variant: "quickstart"
    variants: "quickstart"
    , name: "avg_transactions"
    default_variant: "quickstart"
    variants: "quickstart"
    variants: "production"
    ]
    ```

    Returns:
        labels (List[Label]): List of Label Objects
    """
    return list_name_variant_status(self._stub, "label")

list_models(local=False)

List all models. Prints a list of all models.

Returns:

Name	Type	Description
models	List[Model]	List of Model Objects

Source code in src/featureform/register.py

def list_models(self, local=False) -> List[Model]:
    """List all models. Prints a list of all models.

    Returns:
        models (List[Model]): List of Model Objects
    """
    model_protos = list_name(self._stub, "model")
    # TODO: apply values from proto
    models = [Model(proto.name, tags=[], properties={}) for proto in model_protos]

    return models

list_providers(local=False)

List all providers. Prints a list of all providers.

Examples:

Input

providers_list = rc.list_providers()

Output

// list_providers prints out formatted information on all providers

NAME                           STATUS                         DESCRIPTION
redis-quickstart               CREATED                      A Redis deployment we created for the Featureform quickstart
postgres-quickstart            CREATED                      A Postgres deployment we created for the Featureform quickst

Input

print(providers_list)

Output

// list_providers returns a list of Providers objects

[name: "redis-quickstart"
description: "A Redis deployment we created for the Featureform quickstart"
type: "REDIS_ONLINE"
software: "redis"
serialized_config: "{"Addr": "quickstart-redis:6379", "Password": "", "DB": 0}"
features {
name: "avg_transactions"
variant: "quickstart"
}
features {
name: "avg_transactions"
variant: "production"
}
features {
name: "user_age"
variant: "quickstart"
}
, name: "postgres-quickstart"
description: "A Postgres deployment we created for the Featureform quickstart"
type: "POSTGRES_OFFLINE"
software: "postgres"
serialized_config: "{"Host": "quickstart-postgres", "Port": "5432", "Username": "postgres", "Password": "password", "Database": "postgres"}"
sources {
name: "transactions"
variant: "kaggle"
}
sources {
name: "average_user_transaction"
variant: "quickstart"
}
trainingsets {
name: "fraud_training"
variant: "quickstart"
}
labels {
name: "fraudulent"
variant: "quickstart"
}
]

Returns:

Name	Type	Description
providers	List[Provider]	List of Provider Objects

Source code in src/featureform/register.py

def list_providers(self, local=False):
    """List all providers. Prints a list of all providers.

    **Examples:**
    ``` py title="Input"
    providers_list = rc.list_providers()
    ```

    ``` json title="Output"
    // list_providers prints out formatted information on all providers

    NAME                           STATUS                         DESCRIPTION
    redis-quickstart               CREATED                      A Redis deployment we created for the Featureform quickstart
    postgres-quickstart            CREATED                      A Postgres deployment we created for the Featureform quickst
    ```

    ``` py title="Input"
    print(providers_list)
    ```

    ``` json title="Output"
    // list_providers returns a list of Providers objects

    [name: "redis-quickstart"
    description: "A Redis deployment we created for the Featureform quickstart"
    type: "REDIS_ONLINE"
    software: "redis"
    serialized_config: "{\"Addr\": \"quickstart-redis:6379\", \"Password\": \"\", \"DB\": 0}"
    features {
    name: "avg_transactions"
    variant: "quickstart"
    }
    features {
    name: "avg_transactions"
    variant: "production"
    }
    features {
    name: "user_age"
    variant: "quickstart"
    }
    , name: "postgres-quickstart"
    description: "A Postgres deployment we created for the Featureform quickstart"
    type: "POSTGRES_OFFLINE"
    software: "postgres"
    serialized_config: "{\"Host\": \"quickstart-postgres\", \"Port\": \"5432\", \"Username\": \"postgres\", \"Password\": \"password\", \"Database\": \"postgres\"}"
    sources {
    name: "transactions"
    variant: "kaggle"
    }
    sources {
    name: "average_user_transaction"
    variant: "quickstart"
    }
    trainingsets {
    name: "fraud_training"
    variant: "quickstart"
    }
    labels {
    name: "fraudulent"
    variant: "quickstart"
    }
    ]
    ```

    Returns:
        providers (List[Provider]): List of Provider Objects
    """
    return list_name_status_desc(self._stub, "provider")

list_sources(local=False)

List all sources. Prints a list of all sources.

Examples:

Input

sources_list = rc.list_sources()

Output

// list_sources prints out formatted information on all sources

NAME                           VARIANT                        STATUS                         DESCRIPTION
average_user_transaction       quickstart (default)           NO_STATUS                      the average transaction amount for a user
transactions                   kaggle (default)               NO_STATUS                      Fraud Dataset From Kaggle

Input

print(sources_list)

Output

// list_sources returns a list of Source objects

[name: "average_user_transaction"
default_variant: "quickstart"
variants: "quickstart"
, name: "transactions"
default_variant: "kaggle"
variants: "kaggle"
]

Returns:

Name	Type	Description
sources	List[Source]	List of Source Objects

Source code in src/featureform/register.py

def list_sources(self, local=False):
    """List all sources. Prints a list of all sources.

    **Examples:**
    ``` py title="Input"
    sources_list = rc.list_sources()
    ```

    ``` json title="Output"
    // list_sources prints out formatted information on all sources

    NAME                           VARIANT                        STATUS                         DESCRIPTION
    average_user_transaction       quickstart (default)           NO_STATUS                      the average transaction amount for a user
    transactions                   kaggle (default)               NO_STATUS                      Fraud Dataset From Kaggle
    ```

    ``` py title="Input"
    print(sources_list)
    ```

    ``` json title="Output"
    // list_sources returns a list of Source objects

    [name: "average_user_transaction"
    default_variant: "quickstart"
    variants: "quickstart"
    , name: "transactions"
    default_variant: "kaggle"
    variants: "kaggle"
    ]
    ```

    Returns:
        sources (List[Source]): List of Source Objects
    """
    return list_name_variant_status_desc(self._stub, "source")

list_training_sets(local=False)

List all training sets. Prints a list of all training sets.

Examples:

Input

training_sets_list = rc.list_training_sets()

Output

// list_training_sets prints out formatted information on all training sets

NAME                           VARIANT                        STATUS                         DESCRIPTION
fraud_training                 quickstart (default)           READY                          Training set for fraud detection.
fraud_training                 v2                             CREATED                        Improved training set for fraud detection.
recommender                    v1 (default)                   CREATED                        Training set for recommender system.

Input

print(training_sets_list)

Output

// list_training_sets returns a list of TrainingSet objects

[name: "fraud_training"
default_variant: "quickstart"
variants: "quickstart", "v2",
name: "recommender"
default_variant: "v1"
variants: "v1"
]

Returns:

Name	Type	Description
training_sets	List[TrainingSet]	List of TrainingSet Objects

Source code in src/featureform/register.py

def list_training_sets(self, local=False):
    """List all training sets. Prints a list of all training sets.

    **Examples:**
    ``` py title="Input"
    training_sets_list = rc.list_training_sets()
    ```

    ``` json title="Output"
    // list_training_sets prints out formatted information on all training sets

    NAME                           VARIANT                        STATUS                         DESCRIPTION
    fraud_training                 quickstart (default)           READY                          Training set for fraud detection.
    fraud_training                 v2                             CREATED                        Improved training set for fraud detection.
    recommender                    v1 (default)                   CREATED                        Training set for recommender system.
    ```

    ``` py title="Input"
    print(training_sets_list)
    ```

    ``` json title="Output"
    // list_training_sets returns a list of TrainingSet objects

    [name: "fraud_training"
    default_variant: "quickstart"
    variants: "quickstart", "v2",
    name: "recommender"
    default_variant: "v1"
    variants: "v1"
    ]
    ```

    Returns:
        training_sets (List[TrainingSet]): List of TrainingSet Objects
    """
    return list_name_variant_status_desc(self._stub, "training-set")

list_users(local=False)

List all users. Prints a list of all users.

Examples:

Input

users_list = rc.list_users()

Output

// list_users prints out formatted information on all users

NAME                           STATUS
featureformer                  NO_STATUS
featureformers_friend          CREATED

Input

print(features_list)

Output

// list_features returns a list of Feature objects

[name: "featureformer"
features {
name: "avg_transactions"
variant: "quickstart"
}
labels {
name: "fraudulent"
variant: "quickstart"
}
trainingsets {
name: "fraud_training"
variant: "quickstart"
}
sources {
name: "transactions"
variant: "kaggle"
}
sources {
name: "average_user_transaction"
variant: "quickstart"
},
name: "featureformers_friend"
features {
name: "user_age"
variant: "production"
}
sources {
name: "user_profiles"
variant: "production"
}
]

Returns:

Name	Type	Description
users	List[User]	List of User Objects

Source code in src/featureform/register.py

def list_users(self, local=False):
    """List all users. Prints a list of all users.

    **Examples:**
    ``` py title="Input"
    users_list = rc.list_users()
    ```

    ``` json title="Output"
    // list_users prints out formatted information on all users

    NAME                           STATUS
    featureformer                  NO_STATUS
    featureformers_friend          CREATED
    ```

    ``` py title="Input"
    print(features_list)
    ```

    ``` json title="Output"
    // list_features returns a list of Feature objects

    [name: "featureformer"
    features {
    name: "avg_transactions"
    variant: "quickstart"
    }
    labels {
    name: "fraudulent"
    variant: "quickstart"
    }
    trainingsets {
    name: "fraud_training"
    variant: "quickstart"
    }
    sources {
    name: "transactions"
    variant: "kaggle"
    }
    sources {
    name: "average_user_transaction"
    variant: "quickstart"
    },
    name: "featureformers_friend"
    features {
    name: "user_age"
    variant: "production"
    }
    sources {
    name: "user_profiles"
    variant: "production"
    }
    ]
    ```

    Returns:
        users (List[User]): List of User Objects
    """
    return list_name_status(self._stub, "user")

print_feature(name, variant=None, local=False)

Get a feature. Prints out information on feature, and all variants associated with the feature. If variant is included, print information on that specific variant and all resources associated with it.

Examples:

Input

avg_transactions = rc.get_feature("avg_transactions")

Output

// get_feature prints out formatted information on feature

NAME:                          avg_transactions
STATUS:                        NO_STATUS
-----------------------------------------------
VARIANTS:
quickstart                     default
-----------------------------------------------

Input

print(avg_transactions)

Output

// get_feature returns the Feature object

name: "avg_transactions"
default_variant: "quickstart"
variants: "quickstart"

Input

avg_transactions_variant = ff.get_feature("avg_transactions", "quickstart")

Output

// get_feature with variant provided prints out formatted information on feature variant

NAME:                          avg_transactions
VARIANT:                       quickstart
TYPE:                          float32
ENTITY:                        user
OWNER:                         featureformer
PROVIDER:                      redis-quickstart
STATUS:                        NO_STATUS
-----------------------------------------------
SOURCE:
NAME                           VARIANT
average_user_transaction       quickstart
-----------------------------------------------
TRAINING SETS:
NAME                           VARIANT
fraud_training                 quickstart
-----------------------------------------------

Input

print(avg_transactions_variant)

Output

// get_feature returns the FeatureVariant object

name: "avg_transactions"
variant: "quickstart"
source {
name: "average_user_transaction"
variant: "quickstart"
}
type: "float32"
entity: "user"
created {
seconds: 1658168552
nanos: 142461900
}
owner: "featureformer"
provider: "redis-quickstart"
trainingsets {
name: "fraud_training"
variant: "quickstart"
}
columns {
entity: "user_id"
value: "avg_transaction_amt"
}

Parameters:

Name	Type	Description	Default
name	str	Name of feature to be retrieved	required
variant	str	Name of variant of feature	None

Returns:

Name	Type	Description
feature	Union[Feature, FeatureVariant]	Feature or FeatureVariant

Source code in src/featureform/register.py

def print_feature(self, name, variant=None, local=False):
    """Get a feature. Prints out information on feature, and all variants associated with the feature. If variant is included, print information on that specific variant and all resources associated with it.

    **Examples:**

    ``` py title="Input"
    avg_transactions = rc.get_feature("avg_transactions")
    ```

    ``` json title="Output"
    // get_feature prints out formatted information on feature

    NAME:                          avg_transactions
    STATUS:                        NO_STATUS
    -----------------------------------------------
    VARIANTS:
    quickstart                     default
    -----------------------------------------------
    ```

    ``` py title="Input"
    print(avg_transactions)
    ```

    ``` json title="Output"
    // get_feature returns the Feature object

    name: "avg_transactions"
    default_variant: "quickstart"
    variants: "quickstart"
    ```

    ``` py title="Input"
    avg_transactions_variant = ff.get_feature("avg_transactions", "quickstart")
    ```

    ``` json title="Output"
    // get_feature with variant provided prints out formatted information on feature variant

    NAME:                          avg_transactions
    VARIANT:                       quickstart
    TYPE:                          float32
    ENTITY:                        user
    OWNER:                         featureformer
    PROVIDER:                      redis-quickstart
    STATUS:                        NO_STATUS
    -----------------------------------------------
    SOURCE:
    NAME                           VARIANT
    average_user_transaction       quickstart
    -----------------------------------------------
    TRAINING SETS:
    NAME                           VARIANT
    fraud_training                 quickstart
    -----------------------------------------------
    ```

    ``` py title="Input"
    print(avg_transactions_variant)
    ```

    ``` json title="Output"
    // get_feature returns the FeatureVariant object

    name: "avg_transactions"
    variant: "quickstart"
    source {
    name: "average_user_transaction"
    variant: "quickstart"
    }
    type: "float32"
    entity: "user"
    created {
    seconds: 1658168552
    nanos: 142461900
    }
    owner: "featureformer"
    provider: "redis-quickstart"
    trainingsets {
    name: "fraud_training"
    variant: "quickstart"
    }
    columns {
    entity: "user_id"
    value: "avg_transaction_amt"
    }
    ```

    Args:
        name (str): Name of feature to be retrieved
        variant (str): Name of variant of feature

    Returns:
        feature (Union[Feature, FeatureVariant]): Feature or FeatureVariant
    """
    if not variant:
        return get_resource_info(self._stub, "feature", name)
    return get_feature_variant_info(self._stub, name, variant)

print_label(name, variant=None, local=False)

Get a label. Prints out information on label, and all variants associated with the label. If variant is included, print information on that specific variant and all resources associated with it.

Examples:

Input

fraudulent = rc.get_label("fraudulent")

Output

// get_label prints out formatted information on label

NAME:                          fraudulent
STATUS:                        NO_STATUS
-----------------------------------------------
VARIANTS:
quickstart                     default
-----------------------------------------------

Input

print(fraudulent)

Output

// get_label returns the Label object

name: "fraudulent"
default_variant: "quickstart"
variants: "quickstart"

Input

fraudulent_variant = ff.get_label("fraudulent", "quickstart")

Output

// get_label with variant provided prints out formatted information on label variant

NAME:                          fraudulent
VARIANT:                       quickstart
TYPE:                          bool
ENTITY:                        user
OWNER:                         featureformer
PROVIDER:                      postgres-quickstart
STATUS:                        NO_STATUS
-----------------------------------------------
SOURCE:
NAME                           VARIANT
transactions                   kaggle
-----------------------------------------------
TRAINING SETS:
NAME                           VARIANT
fraud_training                 quickstart
-----------------------------------------------

Input

print(fraudulent_variant)

Output

// get_label returns the LabelVariant object

name: "fraudulent"
variant: "quickstart"
type: "bool"
source {
name: "transactions"
variant: "kaggle"
}
entity: "user"
created {
seconds: 1658168552
nanos: 154924300
}
owner: "featureformer"
provider: "postgres-quickstart"
trainingsets {
name: "fraud_training"
variant: "quickstart"
}
columns {
entity: "customerid"
value: "isfraud"
}

Parameters:

Name	Type	Description	Default
name	str	Name of label to be retrieved	required
variant	str	Name of variant of label	None

Returns:

Name	Type	Description
label	Union[label, LabelVariant]	Label or LabelVariant

Source code in src/featureform/register.py

def print_label(self, name, variant=None, local=False):
    """Get a label. Prints out information on label, and all variants associated with the label. If variant is included, print information on that specific variant and all resources associated with it.

    **Examples:**

    ``` py title="Input"
    fraudulent = rc.get_label("fraudulent")
    ```

    ``` json title="Output"
    // get_label prints out formatted information on label

    NAME:                          fraudulent
    STATUS:                        NO_STATUS
    -----------------------------------------------
    VARIANTS:
    quickstart                     default
    -----------------------------------------------
    ```

    ``` py title="Input"
    print(fraudulent)
    ```

    ``` json title="Output"
    // get_label returns the Label object

    name: "fraudulent"
    default_variant: "quickstart"
    variants: "quickstart"
    ```

    ``` py title="Input"
    fraudulent_variant = ff.get_label("fraudulent", "quickstart")
    ```

    ``` json title="Output"
    // get_label with variant provided prints out formatted information on label variant

    NAME:                          fraudulent
    VARIANT:                       quickstart
    TYPE:                          bool
    ENTITY:                        user
    OWNER:                         featureformer
    PROVIDER:                      postgres-quickstart
    STATUS:                        NO_STATUS
    -----------------------------------------------
    SOURCE:
    NAME                           VARIANT
    transactions                   kaggle
    -----------------------------------------------
    TRAINING SETS:
    NAME                           VARIANT
    fraud_training                 quickstart
    -----------------------------------------------
    ```

    ``` py title="Input"
    print(fraudulent_variant)
    ```

    ``` json title="Output"
    // get_label returns the LabelVariant object

    name: "fraudulent"
    variant: "quickstart"
    type: "bool"
    source {
    name: "transactions"
    variant: "kaggle"
    }
    entity: "user"
    created {
    seconds: 1658168552
    nanos: 154924300
    }
    owner: "featureformer"
    provider: "postgres-quickstart"
    trainingsets {
    name: "fraud_training"
    variant: "quickstart"
    }
    columns {
    entity: "customerid"
    value: "isfraud"
    }
    ```

    Args:
        name (str): Name of label to be retrieved
        variant (str): Name of variant of label

    Returns:
        label (Union[label, LabelVariant]): Label or LabelVariant
    """
    if not variant:
        return get_resource_info(self._stub, "label", name)
    return get_label_variant_info(self._stub, name, variant)

print_source(name, variant=None, local=False)

Get a source. Prints out information on source, and all variants associated with the source. If variant is included, print information on that specific variant and all resources associated with it.

Examples:

Input

transactions = rc.get_transactions("transactions")

Output

// get_source prints out formatted information on source

NAME:                          transactions
STATUS:                        NO_STATUS
-----------------------------------------------
VARIANTS:
kaggle                         default
-----------------------------------------------

Input

print(transactions)

Output

// get_source returns the Source object

name: "transactions"
default_variant: "kaggle"
variants: "kaggle"

Input

transactions_variant = rc.get_source("transactions", "kaggle")

Output

// get_source with variant provided prints out formatted information on source variant

NAME:                          transactions
VARIANT:                       kaggle
OWNER:                         featureformer
DESCRIPTION:                   Fraud Dataset From Kaggle
PROVIDER:                      postgres-quickstart
STATUS:                        NO_STATUS
-----------------------------------------------
DEFINITION:
TRANSFORMATION

-----------------------------------------------
SOURCES
NAME                           VARIANT
-----------------------------------------------
PRIMARY DATA
Transactions
FEATURES:
NAME                           VARIANT
-----------------------------------------------
LABELS:
NAME                           VARIANT
fraudulent                     quickstart
-----------------------------------------------
TRAINING SETS:
NAME                           VARIANT
fraud_training                 quickstart
-----------------------------------------------

Input

print(transactions_variant)

Output

// get_source returns the SourceVariant object

name: "transactions"
variant: "kaggle"
owner: "featureformer"
description: "Fraud Dataset From Kaggle"
provider: "postgres-quickstart"
created {
seconds: 1658168552
nanos: 128768000
}
trainingsets {
name: "fraud_training"
variant: "quickstart"
}
labels {
name: "fraudulent"
variant: "quickstart"
}
primaryData {
table {
    name: "Transactions"
}
}

Parameters:

Name	Type	Description	Default
name	str	Name of source to be retrieved	required
variant	str	Name of variant of source	None

Returns:

Name	Type	Description
source	Union[Source, SourceVariant]	Source or SourceVariant

Source code in src/featureform/register.py

def print_source(self, name, variant=None, local=False):
    """Get a source. Prints out information on source, and all variants associated with the source. If variant is included, print information on that specific variant and all resources associated with it.

    **Examples:**

    ``` py title="Input"
    transactions = rc.get_transactions("transactions")
    ```

    ``` json title="Output"
    // get_source prints out formatted information on source

    NAME:                          transactions
    STATUS:                        NO_STATUS
    -----------------------------------------------
    VARIANTS:
    kaggle                         default
    -----------------------------------------------
    ```

    ``` py title="Input"
    print(transactions)
    ```

    ``` json title="Output"
    // get_source returns the Source object

    name: "transactions"
    default_variant: "kaggle"
    variants: "kaggle"
    ```

    ``` py title="Input"
    transactions_variant = rc.get_source("transactions", "kaggle")
    ```

    ``` json title="Output"
    // get_source with variant provided prints out formatted information on source variant

    NAME:                          transactions
    VARIANT:                       kaggle
    OWNER:                         featureformer
    DESCRIPTION:                   Fraud Dataset From Kaggle
    PROVIDER:                      postgres-quickstart
    STATUS:                        NO_STATUS
    -----------------------------------------------
    DEFINITION:
    TRANSFORMATION

    -----------------------------------------------
    SOURCES
    NAME                           VARIANT
    -----------------------------------------------
    PRIMARY DATA
    Transactions
    FEATURES:
    NAME                           VARIANT
    -----------------------------------------------
    LABELS:
    NAME                           VARIANT
    fraudulent                     quickstart
    -----------------------------------------------
    TRAINING SETS:
    NAME                           VARIANT
    fraud_training                 quickstart
    -----------------------------------------------
    ```

    ``` py title="Input"
    print(transactions_variant)
    ```

    ``` json title="Output"
    // get_source returns the SourceVariant object

    name: "transactions"
    variant: "kaggle"
    owner: "featureformer"
    description: "Fraud Dataset From Kaggle"
    provider: "postgres-quickstart"
    created {
    seconds: 1658168552
    nanos: 128768000
    }
    trainingsets {
    name: "fraud_training"
    variant: "quickstart"
    }
    labels {
    name: "fraudulent"
    variant: "quickstart"
    }
    primaryData {
    table {
        name: "Transactions"
    }
    }
    ```

    Args:
        name (str): Name of source to be retrieved
        variant (str): Name of variant of source

    Returns:
        source (Union[Source, SourceVariant]): Source or SourceVariant
    """
    if not variant:
        return get_resource_info(self._stub, "source", name)
    return get_source_variant_info(self._stub, name, variant)

print_training_set(name, variant=None, local=False)

Get a training set. Prints out information on training set, and all variants associated with the training set. If variant is included, print information on that specific variant and all resources associated with it.

Examples:

Input

fraud_training = rc.get_training_set("fraud_training")

Output

// get_training_set prints out formatted information on training set

NAME:                          fraud_training
STATUS:                        NO_STATUS
-----------------------------------------------
VARIANTS:
quickstart                     default
-----------------------------------------------

Input

print(fraud_training)

Output

// get_training_set returns the TrainingSet object

name: "fraud_training"
default_variant: "quickstart"
variants: "quickstart"

Input

fraudulent_variant = ff.get_training set("fraudulent", "quickstart")

Output

// get_training_set with variant provided prints out formatted information on training set variant

NAME:                          fraud_training
VARIANT:                       quickstart
OWNER:                         featureformer
PROVIDER:                      postgres-quickstart
STATUS:                        NO_STATUS
-----------------------------------------------
LABEL:
NAME                           VARIANT
fraudulent                     quickstart
-----------------------------------------------
FEATURES:
NAME                           VARIANT
avg_transactions               quickstart
-----------------------------------------------

Input

print(fraudulent_variant)

Output

// get_training_set returns the TrainingSetVariant object

name: "fraud_training"
variant: "quickstart"
owner: "featureformer"
created {
seconds: 1658168552
nanos: 157934800
}
provider: "postgres-quickstart"
features {
name: "avg_transactions"
variant: "quickstart"
}
label {
name: "fraudulent"
variant: "quickstart"
}

Parameters:

Name	Type	Description	Default
name	str	Name of training set to be retrieved	required
variant	str	Name of variant of training set	None

Returns:

Name	Type	Description
training_set	Union[TrainingSet, TrainingSetVariant]	TrainingSet or TrainingSetVariant

Source code in src/featureform/register.py

def print_training_set(self, name, variant=None, local=False):
    """Get a training set. Prints out information on training set, and all variants associated with the training set. If variant is included, print information on that specific variant and all resources associated with it.

    **Examples:**

    ``` py title="Input"
    fraud_training = rc.get_training_set("fraud_training")
    ```

    ``` json title="Output"
    // get_training_set prints out formatted information on training set

    NAME:                          fraud_training
    STATUS:                        NO_STATUS
    -----------------------------------------------
    VARIANTS:
    quickstart                     default
    -----------------------------------------------
    ```

    ``` py title="Input"
    print(fraud_training)
    ```

    ``` json title="Output"
    // get_training_set returns the TrainingSet object

    name: "fraud_training"
    default_variant: "quickstart"
    variants: "quickstart"
    ```

    ``` py title="Input"
    fraudulent_variant = ff.get_training set("fraudulent", "quickstart")
    ```

    ``` json title="Output"
    // get_training_set with variant provided prints out formatted information on training set variant

    NAME:                          fraud_training
    VARIANT:                       quickstart
    OWNER:                         featureformer
    PROVIDER:                      postgres-quickstart
    STATUS:                        NO_STATUS
    -----------------------------------------------
    LABEL:
    NAME                           VARIANT
    fraudulent                     quickstart
    -----------------------------------------------
    FEATURES:
    NAME                           VARIANT
    avg_transactions               quickstart
    -----------------------------------------------
    ```

    ``` py title="Input"
    print(fraudulent_variant)
    ```

    ``` json title="Output"
    // get_training_set returns the TrainingSetVariant object

    name: "fraud_training"
    variant: "quickstart"
    owner: "featureformer"
    created {
    seconds: 1658168552
    nanos: 157934800
    }
    provider: "postgres-quickstart"
    features {
    name: "avg_transactions"
    variant: "quickstart"
    }
    label {
    name: "fraudulent"
    variant: "quickstart"
    }
    ```

    Args:
        name (str): Name of training set to be retrieved
        variant (str): Name of variant of training set

    Returns:
        training_set (Union[TrainingSet, TrainingSetVariant]): TrainingSet or TrainingSetVariant
    """
    if not variant:
        return get_resource_info(self._stub, "training-set", name)
    return get_training_set_variant_info(self._stub, name, variant)

search(raw_query, local=False)

Search for registered resources. Prints a list of results.

Examples:

Input

providers_list = rc.search("transact")

Output

// search prints out formatted information on all matches

NAME                           VARIANT            TYPE
avg_transactions               default            Source

Source code in src/featureform/register.py

def search(self, raw_query, local=False):
    """Search for registered resources. Prints a list of results.

    **Examples:**
    ``` py title="Input"
    providers_list = rc.search("transact")
    ```

    ``` json title="Output"
    // search prints out formatted information on all matches

    NAME                           VARIANT            TYPE
    avg_transactions               default            Source
    ```
    """
    if type(raw_query) != str or len(raw_query) == 0:
        raise Exception("query must be string and cannot be empty")
    processed_query = raw_query.translate({ord(i): None for i in ".,-@!*#"})
    return search(processed_query, self._host)

featureform.register.Registrar

These functions are used to register new resources and retrieving existing resources. Retrieved resources can be used to register additional resources.

definitions.py

import featureform as ff

# e.g. registering a new provider
redis = ff.register_redis(
    name="redis-quickstart",
    host="quickstart-redis",  # The internal dns name for redis
    port=6379,
    description="A Redis deployment we created for the Featureform quickstart"
)

Source code in src/featureform/register.py

class Registrar:
    """These functions are used to register new resources and retrieving existing resources.
    Retrieved resources can be used to register additional resources.

    ``` py title="definitions.py"
    import featureform as ff

    # e.g. registering a new provider
    redis = ff.register_redis(
        name="redis-quickstart",
        host="quickstart-redis",  # The internal dns name for redis
        port=6379,
        description="A Redis deployment we created for the Featureform quickstart"
    )
    ```
    """

    def __init__(self):
        self.__state = ResourceState()
        self.__resources = []
        self.__default_owner = ""
        self.__variant_prefix = ""
        if feature_flag.is_enabled("FF_GET_EQUIVALENT_VARIANTS", True):
            self.__run = get_current_timestamp_variant(self.__variant_prefix)
        else:
            self.__run = get_random_name()

        """
        maps client objects (feature object, label object, source decorators) to their resource in the event we want 
        to update the client object after the resource was created

        Introduced for timestamp variants where updates during a resource create ensures that the client object
        has the correct variant when being used as a dependency other resources
        """
        self.__client_obj_to_resource_map = {}

    def add_resource(self, resource):
        self.__resources.append(resource)

    def map_client_object_to_resource(
        self, client_obj, resource_variant: ResourceVariant
    ):
        self.__client_obj_to_resource_map[resource_variant.to_key()] = client_obj

    def get_client_objects_for_resource(self):
        return self.__client_obj_to_resource_map

    def get_resources(self):
        return self.__resources

    def register_user(
        self, name: str, tags: List[str] = [], properties: dict = {}
    ) -> UserRegistrar:
        """Register a user.

        Args:
            name (str): User to be registered.

        Returns:
            UserRegistrar: User
        """
        user = User(name=name, tags=tags, properties=properties)
        self.__resources.append(user)
        return UserRegistrar(self, user)

    def set_default_owner(self, user: str):
        """Set default owner.

        Args:
            user (str): User to be set as default owner of resources.
        """
        self.__default_owner = user

    def default_owner(self) -> str:
        return self.__default_owner

    def must_get_default_owner(self) -> str:
        owner = self.default_owner()
        if owner == "":
            raise ValueError("Owner must be set or a default owner must be specified.")
        return owner

    def set_variant_prefix(self, variant_prefix: str = ""):
        """Set variant prefix.

        Args:
            variant_prefix (str): variant prefix to be set.
        """
        self.__variant_prefix = variant_prefix
        self.set_run()

    def set_run(self, run: str = ""):
        """

        **Example 1**: Using set_run() without arguments will generate a random run name.
        ``` py
        import featureform as ff
        ff.set_run()

        postgres.register_table(
            name="transactions",
            table="transactions_table",
        )

        # Applying will register the source as name=transactions, variant=<randomly-generated>

        ```

        **Example 2**: Using set_run() with arguments will set the variant to the provided name.
        ``` py
        import featureform as ff
        ff.set_run("last_30_days")

        postgres.register_table(
            name="transactions",
            table="transactions_table",
        )

        # Applying will register the source as name=transactions, variant=last_30_days
        ```

        **Example 3**: Generated and set variant names can be used together
        ``` py
        import featureform as ff
        ff.set_run()

        file = spark.register_file(
            name="transactions",
            path="my/transactions.parquet",
            variant="last_30_days"
        )

        @spark.df_transformation(inputs=[file]):
        def customer_count(transactions):
            return transactions.groupBy("CustomerID").count()


        # Applying without a variant for the dataframe transformation will result in
        # the transactions source having a variant of last_30_days and the transformation
        # having a randomly generated variant
        ```

        **Example 4**: This also works within SQL Transformations
        ``` py
        import featureform as ff
        ff.set_run("last_30_days")

        @postgres.sql_transformation():
        def my_transformation():
            return "SELECT CustomerID, Amount FROM {{ transactions }}"

        # The variant will be autofilled so the SQL query is returned as:
        # "SELECT CustomerID, Amount FROM {{ transactions.last_30_days }}"
        ```

        Args:
            run (str): Name of a run to be set.
        """
        if run == "":
            if feature_flag.is_enabled("FF_GET_EQUIVALENT_VARIANTS", True):
                self.__run = get_current_timestamp_variant(self.__variant_prefix)
            else:
                self.__run = get_random_name()
        else:
            self.__run = run

    def get_run(self) -> str:
        """
        Get the current run name.

        **Examples**:
        ``` py
        import featureform as ff

        client = ff.Client()
        f = client.features(("avg_transaction_amount", ff.get_run()), {"user": "123"})

        ```

        Returns:
            run: The name of the current run
        """
        return self.__run

    def get_source(self, name, variant, local=False):
        """
        get_source() can be used to get a reference to an already registered primary source or transformation.
        The returned object can be used to register features and labels or be extended off of to create additional
        transformations.

        **Examples**:

        Registering a transformation from an existing source.
        ``` py
        spark = ff.get_spark("prod-spark")
        transactions = ff.get_source("transactions","kaggle")

        @spark.df_transformation(inputs=[transactions]):
        def customer_count(transactions):
            return transactions.groupBy("CustomerID").count()
        ```

        Registering a feature from an existing source.
        ``` py
        transactions = ff.get_source("transactions","kaggle")

        transactions.register_resources(
            entity=user,
            entity_column="customerid",
            labels=[
                {"name": "fraudulent", "variant": "quickstart", "column": "isfraud", "type": "bool"},
            ],
        )
        ```

        Args:
            name (str): Name of source to be retrieved
            variant (str): Name of variant of source to be retrieved
            local (bool): If localmode is being used

        Returns:
            source (ColumnSourceRegistrar): Source
        """
        if local:
            raise Exception(
                "Localmode is not supported; please try featureform <= 1.12.0"
            )
        else:
            mock_definition = PrimaryData(location=SQLTable(name=""))
            mock_source = SourceVariant(
                created=None,
                name=name,
                variant=variant,
                definition=mock_definition,
                owner="",
                provider="",
                description="",
                tags=[],
                properties={},
            )
            return ColumnSourceRegistrar(self, mock_source)

    def get_redis(self, name):
        """Get a Redis provider. The returned object can be used to register additional resources.

        **Examples**:
        ``` py
        redis = ff.get_redis("redis-quickstart")

        average_user_transaction.register_resources(
            entity=user,
            entity_column="user_id",
            inference_store=redis,
            features=[
                {"name": "avg_transactions", "variant": "quickstart", "column": "avg_transaction_amt", "type": "float32"},
            ],
        )
        ```

        Args:
            name (str): Name of Redis provider to be retrieved

        Returns:
            redis (OnlineProvider): Provider
        """
        mock_config = RedisConfig(host="", port=123, password="", db=123)
        mock_provider = Provider(
            name=name, function="ONLINE", description="", team="", config=mock_config
        )
        return OnlineProvider(self, mock_provider)

    def get_dynamodb(self, name: str):
        """Get a DynamoDB provider. The returned object can be used as an inference store in feature registration.

        **Examples**:
        ``` py
        dynamodb = ff.get_dynamodb("dynamodb-quickstart")

        @ff.entity
        class User:
            avg_transactions = ff.Feature(
                average_user_transaction[["user_id", "avg_transaction_amt"]],
                type=ff.Float32,
                inference_store=dynamodb,
            )
        ```

        Args:
            name (str): Name of DynamoDB provider to be retrieved

        Returns:
            dynamodb (OnlineProvider): Provider
        """
        mock_config = DynamodbConfig(
            region="", access_key="", secret_key="", should_import_from_s3=False
        )
        mock_provider = Provider(
            name=name, function="ONLINE", description="", team="", config=mock_config
        )
        return OnlineProvider(self, mock_provider)

    def get_mongodb(self, name: str):
        """Get a MongoDB provider. The returned object can be used to register additional resources.

        **Examples**:
        ``` py
        mongodb = ff.get_mongodb("mongodb-quickstart")

        average_user_transaction.register_resources(
            entity=user,
            entity_column="user_id",
            inference_store=mongodb,
            features=[
                {"name": "avg_transactions", "variant": "quickstart", "column": "avg_transaction_amt", "type": "float32"},
            ],
        )
        ```

        Args:
            name (str): Name of MongoDB provider to be retrieved

        Returns:
            mongodb (OnlineProvider): Provider
        """
        mock_config = MongoDBConfig(
            username="", password="", host="", port="", database="", throughput=1
        )
        mock_provider = Provider(
            name=name, function="ONLINE", description="", team="", config=mock_config
        )
        return OnlineProvider(self, mock_provider)

    def get_blob_store(self, name):
        """Get an Azure Blob provider. The returned object can be used to register additional resources.

        **Examples**:
        ``` py
        azure_blob = ff.get_blob_store("azure-blob-quickstart")

        average_user_transaction.register_resources(
            entity=user,
            entity_column="user_id",
            inference_store=azure_blob,
            features=[
                {"name": "avg_transactions", "variant": "quickstart", "column": "avg_transaction_amt", "type": "float32"},
            ],
        )
        ```

        Args:
            name (str): Name of Azure blob provider to be retrieved

        Returns:
            azure_blob (FileStoreProvider): Provider
        """
        fake_azure_config = AzureFileStoreConfig(
            account_name="", account_key="", container_name="", root_path=""
        )
        fake_config = OnlineBlobConfig(
            store_type="AZURE", store_config=fake_azure_config.config()
        )
        mock_provider = Provider(
            name=name, function="ONLINE", description="", team="", config=fake_config
        )
        return FileStoreProvider(self, mock_provider, fake_config, "AZURE")

    def get_postgres(self, name):
        """Get a Postgres provider. The returned object can be used to register additional resources.

        **Examples**:
        ``` py
        postgres = ff.get_postgres("postgres-quickstart")
        transactions = postgres.register_table(
            name="transactions",
            variant="kaggle",
            description="Fraud Dataset From Kaggle",
            table="Transactions",  # This is the table's name in Postgres
        )
        ```

        Args:
            name (str): Name of Postgres provider to be retrieved

        Returns:
            postgres (OfflineSQLProvider): Provider
        """
        mock_config = PostgresConfig(
            host="",
            port="",
            database="",
            user="",
            password="",
            sslmode="",
        )
        mock_provider = Provider(
            name=name, function="OFFLINE", description="", team="", config=mock_config
        )
        return OfflineSQLProvider(self, mock_provider)

    def get_clickhouse(self, name):
        """Get a ClickHouse provider. The returned object can be used to register additional resources.

        **Examples**:
        ``` py
        clickhouse = ff.get_clickhouse("clickhouse-quickstart")
        transactions = clickhouse.register_table(
            name="transactions",
            variant="kaggle",
            description="Fraud Dataset From Kaggle",
            table="Transactions",  # This is the table's name in ClickHouse
        )
        ```

        Args:
            name (str): Name of ClickHouse provider to be retrieved

        Returns:
            clickhouse (OfflineSQLProvider): Provider
        """
        mock_config = ClickHouseConfig(
            host="",
            port=9000,
            database="",
            user="",
            password="",
            ssl=False,
        )
        mock_provider = Provider(
            name=name, function="OFFLINE", description="", team="", config=mock_config
        )
        return OfflineSQLProvider(self, mock_provider)

    def get_snowflake(self, name):
        """Get a Snowflake provider. The returned object can be used to register additional resources.

        **Examples**:
        ``` py
        snowflake = ff.get_snowflake("snowflake-quickstart")
        transactions = snowflake.register_table(
            name="transactions",
            variant="kaggle",
            description="Fraud Dataset From Kaggle",
            table="Transactions",  # This is the table's name in Postgres
        )
        ```

        Args:
            name (str): Name of Snowflake provider to be retrieved

        Returns:
            snowflake (OfflineSQLProvider): Provider
        """
        mock_config = SnowflakeConfig(
            account="ff_fake",
            database="ff_fake",
            organization="ff_fake",
            username="ff_fake",
            password="ff_fake",
            schema="ff_fake",
        )
        mock_provider = Provider(
            name=name, function="OFFLINE", description="", team="", config=mock_config
        )
        return OfflineSQLProvider(self, mock_provider)

    def get_snowflake_legacy(self, name: str):
        """Get a Snowflake provider. The returned object can be used to register additional resources.

        **Examples**:
        ``` py
        snowflake = ff.get_snowflake_legacy("snowflake-quickstart")
        transactions = snowflake.register_table(
            name="transactions",
            variant="kaggle",
            description="Fraud Dataset From Kaggle",
            table="Transactions",  # This is the table's name in Postgres
        )
        ```

        Args:
            name (str): Name of Snowflake provider to be retrieved

        Returns:
            snowflake_legacy (OfflineSQLProvider): Provider
        """
        mock_config = SnowflakeConfig(
            account_locator="ff_fake",
            database="ff_fake",
            username="ff_fake",
            password="ff_fake",
            schema="ff_fake",
            warehouse="ff_fake",
            role="ff_fake",
        )
        mock_provider = Provider(
            name=name, function="OFFLINE", description="", team="", config=mock_config
        )
        return OfflineSQLProvider(self, mock_provider)

    def get_redshift(self, name):
        """Get a Redshift provider. The returned object can be used to register additional resources.

        **Examples**:
        ``` py
        redshift = ff.get_redshift("redshift-quickstart")
        transactions = redshift.register_table(
            name="transactions",
            variant="kaggle",
            description="Fraud Dataset From Kaggle",
            table="Transactions",  # This is the table's name in Postgres
        )
        ```

        Args:
            name (str): Name of Redshift provider to be retrieved

        Returns:
            redshift (OfflineSQLProvider): Provider
        """
        mock_config = RedshiftConfig(
            host="", port="5439", database="", user="", password="", sslmode=""
        )
        mock_provider = Provider(
            name=name, function="OFFLINE", description="", team="", config=mock_config
        )
        return OfflineSQLProvider(self, mock_provider)

    def get_bigquery(self, name):
        """Get a BigQuery provider. The returned object can be used to register additional resources.

        **Examples**:
        ``` py
        bigquery = ff.get_bigquery("bigquery-quickstart")
        transactions = bigquery.register_table(
            name="transactions",
            variant="kaggle",
            description="Fraud Dataset From Kaggle",
            table="Transactions",  # This is the table's name in BigQuery
        )
        ```

        Args:
            name (str): Name of BigQuery provider to be retrieved

        Returns:
            bigquery (OfflineSQLProvider): Provider
        """
        mock_config = BigQueryConfig(
            project_id="mock_project",
            dataset_id="mock_dataset",
            credentials=GCPCredentials(
                project_id="mock_project",
                credentials_path="client/tests/test_files/bigquery_dummy_credentials.json",
            ),
        )
        mock_provider = Provider(
            name=name, function="OFFLINE", description="", team="", config=mock_config
        )
        return OfflineSQLProvider(self, mock_provider)

    def get_spark(self, name):
        """Get a Spark provider. The returned object can be used to register additional resources.

        **Examples**:
        ``` py
        spark = ff.get_spark("spark-quickstart")
        transactions = spark.register_file(
            name="transactions",
            variant="kaggle",
            description="Fraud Dataset From Kaggle",
            file_path="s3://bucket/path/to/file/transactions.parquet",  # This is the path to file
        )
        ```

        Args:
            name (str): Name of Spark provider to be retrieved

        Returns:
            spark (OfflineSQLProvider): Provider
        """
        mock_config = SparkConfig(
            executor_type="", executor_config={}, store_type="", store_config={}
        )
        mock_provider = Provider(
            name=name, function="OFFLINE", description="", team="", config=mock_config
        )
        return OfflineSparkProvider(self, mock_provider)

    def get_kubernetes(self, name):
        """
        Get a k8s provider. The returned object can be used to register additional resources.

        **Examples**:
        ``` py

        k8s = ff.get_kubernetes("k8s-azure-quickstart")
        transactions = k8s.register_file(
            name="transactions",
            variant="kaggle",
            description="Fraud Dataset From Kaggle",
            path="path/to/blob",
        )
        ```

        Args:
            name (str): Name of k8s provider to be retrieved

        Returns:
            k8s (OfflineK8sProvider): Provider
        """
        mock_config = K8sConfig(store_type="", store_config={})
        mock_provider = Provider(
            name=name, function="OFFLINE", description="", team="", config=mock_config
        )
        return OfflineK8sProvider(self, mock_provider)

    def get_s3(self, name):
        """
        Get a S3 provider. The returned object can be used with other providers such as Spark and Databricks.

        **Examples**:

        ``` py

        s3 = ff.get_s3("s3-quickstart")
        spark = ff.register_spark(
            name=f"spark-emr-s3",
            description="A Spark deployment we created for the Featureform quickstart",
            team="featureform-team",
            executor=emr,
            filestore=s3,
        )
        ```

        Args:
            name (str): Name of S3 to be retrieved

        Returns:
            s3 (FileStore): Provider
        """
        provider = Provider(
            name=name,
            function="OFFLINE",
            description="description",
            team="team",
            config=s3_config,
        )
        return FileStoreProvider(
            registrar=self,
            provider=provider,
            config=s3_config,
            store_type=s3_config.type(),
        )

    def get_gcs(self, name):
        filePath = "provider/connection/mock_credentials.json"
        fake_creds = GCPCredentials(project_id="id", credentials_path=filePath)
        mock_config = GCSFileStoreConfig(
            bucket_name="", bucket_path="", credentials=fake_creds
        )
        mock_provider = Provider(
            name=name, function="OFFLINE", description="", team="", config=mock_config
        )
        return OfflineK8sProvider(self, mock_provider)

    def _create_mock_creds_file(self, filename, json_data):
        with open(filename, "w") as f:
            json.dumps(json_data, f)

    def get_entity(self, name: str):
        """Get an entity. The returned object can be used to register additional resources.

        **Examples**:

        ``` py
        entity = get_entity("user")
        transactions.register_resources(
            entity=entity,
            entity_column="customerid",
            labels=[
                {"name": "fraudulent", "variant": "quickstart", "column": "isfraud", "type": "bool"},
            ],
        )
        ```

        Args:
            name (str): Name of entity to be retrieved
        Returns:
            entity (EntityRegistrar): Entity
        """
        fakeEntity = Entity(
            name=name, description="", status="", tags=[], properties={}
        )
        return EntityRegistrar(self, fakeEntity)

    def register_redis(
        self,
        name: str,
        host: str,
        port: int = 6379,
        db: int = 0,
        password: str = "",
        description: str = "",
        team: str = "",
        tags: Optional[List[str]] = None,
        properties: Optional[dict] = None,
    ):
        """Register a Redis provider.

        **Examples**:
        ```
        redis = ff.register_redis(
            name="redis-quickstart",
            host="quickstart-redis",
            port=6379,
            password="password",
            description="A Redis deployment we created for the Featureform quickstart"
        )
        ```

        Args:
            name (str): (Immutable) Name of Redis provider to be registered
            host (str): (Immutable) Hostname for Redis
            db (str): (Immutable) Redis database number
            port (int): (Mutable) Redis port
            password (str): (Mutable) Redis password
            description (str): (Mutable) Description of Redis provider to be registered
            team (str): (Mutable) Name of team
            tags (Optional[List[str]]): (Mutable) Optional grouping mechanism for resources
            properties (Optional[dict]): (Mutable) Optional grouping mechanism for resources

        Returns:
            redis (OnlineProvider): Provider
        """
        tags, properties = set_tags_properties(tags, properties)
        config = RedisConfig(host=host, port=port, password=password, db=db)
        provider = Provider(
            name=name,
            function="ONLINE",
            description=description,
            team=team,
            config=config,
            tags=tags,
            properties=properties,
        )
        self.__resources.append(provider)
        return OnlineProvider(self, provider)

    def register_pinecone(
        self,
        name: str,
        project_id: str,
        environment: str,
        api_key: str,
        description: str = "",
        team: str = "",
        tags: List[str] = [],
        properties: dict = {},
    ):
        """Register a Pinecone provider.

        **Examples**:
        ```
        pinecone = ff.register_pinecone(
            name="pinecone-quickstart",
            project_id="2g13ek7",
            environment="us-west4-gcp-free",
            api_key="xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
        )
        ```

        Args:
            name (str): (Immutable) Name of Pinecone provider to be registered
            project_id (str): (Immutable) Pinecone project id
            environment (str): (Immutable) Pinecone environment
            api_key (str): (Mutable) Pinecone api key
            description (str): (Mutable) Description of Pinecone provider to be registered
            team (str): (Mutable) Name of team
            tags (List[str]): (Mutable) Optional grouping mechanism for resources
            properties (dict): (Mutable) Optional grouping mechanism for resources

        Returns:
            pinecone (OnlineProvider): Provider
        """

        tags, properties = set_tags_properties(tags, properties)
        config = PineconeConfig(
            project_id=project_id, environment=environment, api_key=api_key
        )
        provider = Provider(
            name=name,
            function="ONLINE",
            description=description,
            team=team,
            config=config,
            tags=tags,
            properties=properties,
        )
        self.__resources.append(provider)
        return OnlineProvider(self, provider)

    def register_weaviate(
        self,
        name: str,
        url: str,
        api_key: str,
        description: str = "",
        team: str = "",
        tags: List[str] = [],
        properties: dict = {},
    ):
        """Register a Weaviate provider.

        **Examples**:
        ```
        weaviate = ff.register_weaviate(
            name="weaviate-quickstart",
            url="https://<CLUSTER NAME>.weaviate.network",
            api_key="<API KEY>"
            description="A Weaviate project for using embeddings in Featureform"
        )
        ```

        Args:
            name (str): (Immutable) Name of Weaviate provider to be registered
            url (str): (Immutable) Endpoint of Weaviate cluster, either in the cloud or via another deployment operation
            api_key (str): (Mutable) Weaviate api key
            description (str): (Mutable) Description of Weaviate provider to be registered
            team (str): (Mutable) Name of team
            tags (List[str]): (Mutable) Optional grouping mechanism for resources
            properties (dict): (Mutable) Optional grouping mechanism for resources

        Returns:
            weaviate (OnlineProvider): Provider
        """
        config = WeaviateConfig(url=url, api_key=api_key)
        provider = Provider(
            name=name,
            function="ONLINE",
            description=description,
            team=team,
            config=config,
            tags=tags,
            properties=properties,
        )
        self.__resources.append(provider)
        return OnlineProvider(self, provider)

    def register_qdrant(
        self,
        name: str,
        grpc_host: str,
        api_key: str = "",
        use_tls: bool = False,
        description: str = "",
        team: str = "",
        tags: List[str] = [],
        properties: dict = {},
    ):
        """Register a Qdrant provider.

        **Examples**:
        ```
        qdrant = ff.register_qdrant(
            name="qdrant-quickstart",
            grpc_host="xyz-example.eu-central.aws.cloud.qdrant.io:6334",
            api_key="<API KEY>",
            use_tls=True,
            description="A Qdrant project for using embeddings in Featureform"
        )
        ```

        Args:
            name (str): (Immutable) Name of Qdrant provider to be registered
            url (str): (Immutable) gRPC host of the Qdrant cluster, either in the cloud or via local deployment.
            api_key (str): (Mutable) Qdrant API key.
            use_tls (bool): (Immutable) Whether to use TLS for the connection.
            description (str): (Mutable) Description of Qdrant provider to be registered
            team (str): (Mutable) Name of team
            tags (List[str]): (Mutable) Optional grouping mechanism for resources
            properties (dict): (Mutable) Optional grouping mechanism for resources

        Returns:
            qdrant (OnlineProvider): Provider
        """
        config = QdrantConfig(grpc_host=grpc_host, api_key=api_key, use_tls=use_tls)
        provider = Provider(
            name=name,
            function="ONLINE",
            description=description,
            team=team,
            config=config,
            tags=tags,
            properties=properties,
        )
        self.__resources.append(provider)
        return OnlineProvider(self, provider)

    def register_blob_store(
        self,
        name: str,
        account_name: str,
        account_key: str,
        container_name: str,
        root_path: str,
        description: str = "",
        team: str = "",
        tags=None,
        properties=None,
    ):
        """Register an Azure Blob Store provider.

        Azure Blob Storage can be used as the storage component for Spark or the Featureform Pandas Runner.

        **Examples**:
        ```
        blob = ff.register_blob_store(
            name="azure-quickstart",
            container_name="my_company_container"
            root_path="custom/path/in/container"
            account_name=<azure_account_name>
            account_key=<azure_account_key>
            description="An azure blob store provider to store offline and inference data"
        )
        ```

        Args:
            name (str): (Immutable) Name of Azure blob store to be registered
            container_name (str): (Immutable) Azure container name
            root_path (str): (Immutable) A custom path in container to store data
            account_name (str): (Immutable) Azure account name
            account_key (str):  (Mutable) Secret azure account key
            description (str): (Mutable) Description of Azure Blob provider to be registered
            team (str): (Mutable) The name of the team registering the filestore
            tags (List[str]): (Mutable) Optional grouping mechanism for resources
            properties (dict): (Mutable) Optional grouping mechanism for resources

        Returns:
            blob (StorageProvider): Provider
                has all the functionality of OnlineProvider
        """

        tags, properties = set_tags_properties(tags, properties)

        container_name = container_name.replace("abfss://", "")
        if "/" in container_name:
            raise ValueError(
                "container_name cannot contain '/'. container_name should be the name of the Azure Blobstore container only."
            )

        azure_config = AzureFileStoreConfig(
            account_name=account_name,
            account_key=account_key,
            container_name=container_name,
            root_path=root_path,
        )
        config = OnlineBlobConfig(
            store_type="AZURE", store_config=azure_config.config()
        )

        provider = Provider(
            name=name,
            function="ONLINE",
            description=description,
            team=team,
            config=config,
            tags=tags,
            properties=properties,
        )
        self.__resources.append(provider)
        return FileStoreProvider(self, provider, azure_config, "AZURE")

    def register_s3(
        self,
        name: str,
        credentials: AWSCredentials,
        bucket_region: str,
        bucket_name: str,
        path: str = "",
        description: str = "",
        team: str = "",
        tags: List[str] = [],
        properties: dict = {},
    ):
        """Register a S3 store provider.

        This has the functionality of an offline store and can be used as a parameter
        to a k8s or spark provider

        **Examples**:
        ```
        s3 = ff.register_s3(
            name="s3-quickstart",
            credentials=aws_creds,
            bucket_name="bucket_name",
            bucket_region=<bucket_region>,
            path="path/to/store/featureform_files/in/",
            description="An s3 store provider to store offline"
        )
        ```

        Args:
            name (str): (Immutable) Name of S3 store to be registered
            bucket_name (str): (Immutable) AWS Bucket Name
            bucket_region (str): (Immutable) AWS region the bucket is located in
            path (str): (Immutable) The path used to store featureform files in
            credentials (AWSCredentials): (Mutable) AWS credentials to access the bucket
            description (str): (Mutable) Description of S3 provider to be registered
            team (str): (Mutable) The name of the team registering the filestore
            tags (List[str]): (Mutable) Optional grouping mechanism for resources
            properties (dict): (Mutable) Optional grouping mechanism for resources

        Returns:
            s3 (FileStoreProvider): Provider
                has all the functionality of OfflineProvider
        """
        tags, properties = set_tags_properties(tags, properties)

        if bucket_name == "":
            raise ValueError("bucket_name is required and cannot be empty string")

        # TODO: add verification into S3StoreConfig
        bucket_name = bucket_name.replace("s3://", "").replace("s3a://", "")

        if "/" in bucket_name:
            raise ValueError(
                "bucket_name cannot contain '/'. bucket_name should be the name of the AWS S3 bucket only."
            )

        s3_config = S3StoreConfig(
            bucket_path=bucket_name,
            bucket_region=bucket_region,
            credentials=credentials,
            path=path,
        )

        provider = Provider(
            name=name,
            function="OFFLINE",
            description=description,
            team=team,
            config=s3_config,
            tags=tags,
            properties=properties,
        )
        self.__resources.append(provider)
        return FileStoreProvider(self, provider, s3_config, s3_config.type())

    def register_gcs(
        self,
        name: str,
        bucket_name: str,
        root_path: str,
        credentials: GCPCredentials,
        description: str = "",
        team: str = "",
        tags: List[str] = [],
        properties: dict = {},
    ):
        """Register a GCS store provider.

        **Examples**:
        ```
        gcs = ff.register_gcs(
            name="gcs-quickstart",
            credentials=ff.GCPCredentials(...),
            bucket_name="bucket_name",
            root_path="featureform/path/",
            description="An gcs store provider to store offline"
        )
        ```

        Args:
            name (str): (Immutable) Name of GCS store to be registered
            bucket_name (str): (Immutable) The bucket name
            root_path (str): (Immutable) Custom path to be used by featureform
            credentials (GCPCredentials): (Mutable) GCP credentials to access the bucket
            description (str): (Mutable) Description of GCS provider to be registered
            team (str): (Mutable) The name of the team registering the filestore
            tags (List[str]): (Mutable) Optional grouping mechanism for resources
            properties (dict): (Mutable) Optional grouping mechanism for resources

        Returns:
            gcs (FileStoreProvider): Provider
                has all the functionality of OfflineProvider
        """
        tags, properties = set_tags_properties(tags, properties)

        if bucket_name == "":
            raise ValueError("bucket_name is required and cannot be empty string")

        bucket_name = bucket_name.replace("gs://", "")
        if "/" in bucket_name:
            raise ValueError(
                "bucket_name cannot contain '/'. bucket_name should be the name of the GCS bucket only."
            )

        gcs_config = GCSFileStoreConfig(
            bucket_name=bucket_name, bucket_path=root_path, credentials=credentials
        )
        provider = Provider(
            name=name,
            function="OFFLINE",
            description=description,
            team=team,
            config=gcs_config,
            tags=tags,
            properties=properties,
        )
        self.__resources.append(provider)
        return FileStoreProvider(self, provider, gcs_config, gcs_config.type())

    def register_hdfs(
        self,
        name: str,
        host: str,
        port: str,
        username: str = "",
        path: str = "",
        description: str = "",
        team: str = "",
        tags: List[str] = [],
        properties: dict = {},
    ):
        """Register a HDFS store provider.

        This has the functionality of an offline store and can be used as a parameter
        to a k8s or spark provider

        **Examples**:
        ```
        hdfs = ff.register_hdfs(
            name="hdfs-quickstart",
            host="<host>",
            port="<port>",
            path="<path>",
            username="<username>",
            description="An hdfs store provider to store offline"
        )
        ```

        Args:
            name (str): (Immutable) Name of HDFS store to be registered
            host (str): (Immutable) The hostname for HDFS
            path (str): (Immutable) A storage path within HDFS
            port (str): (Mutable) The IPC port for the Namenode for HDFS. (Typically 8020 or 9000)
            username (str): (Mutable) A Username for HDFS
            description (str): (Mutable) Description of HDFS provider to be registered
            team (str): (Mutable) The name of the team registering HDFS

        Returns:
            hdfs (FileStoreProvider): Provider
        """

        hdfs_config = HDFSConfig(host=host, port=port, path=path, username=username)

        provider = Provider(
            name=name,
            function="OFFLINE",
            description=description,
            team=team,
            config=hdfs_config,
            tags=tags,
            properties=properties,
        )
        self.__resources.append(provider)
        return FileStoreProvider(self, provider, hdfs_config, hdfs_config.type())

    # TODO: Set Deprecation Warning For Credentials Path
    def register_firestore(
        self,
        name: str,
        collection: str,
        project_id: str,
        credentials: GCPCredentials,
        credentials_path: str = "",
        description: str = "",
        team: str = "",
        tags: List[str] = [],
        properties: dict = {},
    ):
        """Register a Firestore provider.

        **Examples**:
        ```
        firestore = ff.register_firestore(
            name="firestore-quickstart",
            description="A Firestore deployment we created for the Featureform quickstart",
            project_id="quickstart-project",
            collection="quickstart-collection",
            credentials=ff.GCPCredentials(...)
        )
        ```

        Args:
            name (str): (Immutable) Name of Firestore provider to be registered
            project_id (str): (Immutable) The Project name in GCP
            collection (str): (Immutable) The Collection name in Firestore under the given project ID
            credentials (GCPCredentials): (Mutable) GCP credentials to access Firestore
            description (str): (Mutable) Description of Firestore provider to be registered
            team (str): (Mutable) The name of the team registering the filestore
            tags (List[str]): (Mutable) Optional grouping mechanism for resources
            properties (dict): (Mutable) Optional grouping mechanism for resources

        Returns:
            firestore (OfflineSQLProvider): Provider
        """
        tags, properties = set_tags_properties(tags, properties)
        config = FirestoreConfig(
            collection=collection,
            project_id=project_id,
            credentials=credentials,
        )
        provider = Provider(
            name=name,
            function="ONLINE",
            description=description,
            team=team,
            config=config,
            tags=tags,
            properties=properties,
        )
        self.__resources.append(provider)
        return OnlineProvider(self, provider)

    # TODO: Check these fields
    def register_cassandra(
        self,
        name: str,
        host: str,
        port: int,
        username: str,
        password: str,
        keyspace: str,
        consistency: str = "THREE",
        replication: int = 3,
        description: str = "",
        team: str = "",
        tags: List[str] = [],
        properties: dict = {},
    ):
        """Register a Cassandra provider.

        **Examples**:
        ```
        cassandra = ff.register_cassandra(
                name = "cassandra",
                description = "Example inference store",
                team = "Featureform",
                host = "0.0.0.0",
                port = 9042,
                username = "cassandra",
                password = "cassandra",
                consistency = "THREE",
                replication = 3
            )
        ```

        Args:
            name (str): (Immutable) Name of Cassandra provider to be registered
            host (str): (Immutable) DNS name of Cassandra
            port (str): (Mutable) Port
            username (str): (Mutable) Username
            password (str): (Mutable) Password
            consistency (str): (Mutable) Consistency
            replication (int): (Mutable) Replication
            description (str): (Mutable) Description of Cassandra provider to be registered
            team (str): (Mutable) Name of team
            tags (List[str]): (Mutable) Optional grouping mechanism for resources
            properties (dict): (Mutable) Optional grouping mechanism for resources

        Returns:
            cassandra (OnlineProvider): Provider
        """
        config = CassandraConfig(
            host=host,
            port=port,
            username=username,
            password=password,
            keyspace=keyspace,
            consistency=consistency,
            replication=replication,
        )
        provider = Provider(
            name=name,
            function="ONLINE",
            description=description,
            team=team,
            config=config,
            tags=tags,
            properties=properties,
        )
        self.__resources.append(provider)
        return OnlineProvider(self, provider)

    def register_dynamodb(
        self,
        name: str,
        credentials: AWSCredentials,
        region: str,
        should_import_from_s3: bool = False,
        description: str = "",
        team: str = "",
        tags: List[str] = [],
        properties: dict = {},
    ):
        """Register a DynamoDB provider.

        **Examples**:
        ```
        dynamodb = ff.register_dynamodb(
            name="dynamodb-quickstart",
            description="A Dynamodb deployment we created for the Featureform quickstart",
            credentials=aws_creds,
            region="us-east-1"
        )
        ```

        Args:
            name (str): (Immutable) Name of DynamoDB provider to be registered
            region (str): (Immutable) Region to create dynamo tables
            credentials (AWSCredentials): (Mutable) AWS credentials with permissions to create DynamoDB tables
            should_import_from_s3 (bool): (Mutable) Determines whether feature materialization will occur via a direct import of data from S3 to new table (see [docs](https://docs.aws.amazon.com/amazondynamodb/latest/developerguide/S3DataImport.HowItWorks.html) for details)
            description (str): (Mutable) Description of DynamoDB provider to be registered
            team (str): (Mutable) Name of team
            tags (List[str]): (Mutable) Optional grouping mechanism for resources
            properties (dict): (Mutable) Optional grouping mechanism for resources

        Returns:
            dynamodb (OnlineProvider): Provider
        """
        tags, properties = set_tags_properties(tags, properties)
        config = DynamodbConfig(
            access_key=credentials.access_key,
            secret_key=credentials.secret_key,
            region=region,
            should_import_from_s3=should_import_from_s3,
        )
        provider = Provider(
            name=name,
            function="ONLINE",
            description=description,
            team=team,
            config=config,
            tags=tags,
            properties=properties,
        )
        self.__resources.append(provider)
        return OnlineProvider(self, provider)

    def register_mongodb(
        self,
        name: str,
        username: str,
        password: str,
        database: str,
        host: str,
        port: str,
        throughput: int = 1000,
        description: str = "",
        team: str = "",
        tags: List[str] = [],
        properties: dict = {},
    ):
        """Register a MongoDB provider.

        **Examples**:
        ```
        mongodb = ff.register_mongodb(
            name="mongodb-quickstart",
            description="A MongoDB deployment",
            username="my_username",
            password="myPassword",
            database="featureform_database"
            host="my-mongodb.host.com",
            port="10225",
            throughput=10000
        )
        ```

        Args:
            name (str): (Immutable) Name of MongoDB provider to be registered
            database (str): (Immutable) MongoDB database
            host (str): (Immutable) MongoDB hostname
            port (str): (Immutable) MongoDB port
            username (str): (Mutable) MongoDB username
            password (str): (Mutable) MongoDB password
            throughput (int): (Mutable) The maximum RU limit for autoscaling in CosmosDB
            description (str): (Mutable) Description of MongoDB provider to be registered
            team (str): (Mutable) Name of team
            tags (List[str]): (Mutable) Optional grouping mechanism for resources
            properties (dict): (Mutable) Optional grouping mechanism for resources

        Returns:
            mongodb (OnlineProvider): Provider
        """
        tags, properties = set_tags_properties(tags, properties)
        config = MongoDBConfig(
            username=username,
            password=password,
            host=host,
            port=port,
            database=database,
            throughput=throughput,
        )
        provider = Provider(
            name=name,
            function="ONLINE",
            description=description,
            team=team,
            config=config,
            tags=tags,
            properties=properties,
        )
        self.__resources.append(provider)
        return OnlineProvider(self, provider)

    def register_snowflake_legacy(
        self,
        name: str,
        username: str,
        password: str,
        account_locator: str,
        database: str,
        schema: str = "PUBLIC",
        description: str = "",
        team: str = "",
        warehouse: str = "",
        role: str = "",
        tags: List[str] = [],
        properties: dict = {},
    ):
        """Register a Snowflake provider using legacy credentials.

        **Examples**:
        ```
        snowflake = ff.register_snowflake_legacy(
            name="snowflake-quickstart",
            username="snowflake",
            password="password",
            account_locator="account-locator",
            database="snowflake",
            schema="PUBLIC",
            description="A Snowflake deployment we created for the Featureform quickstart"
        )
        ```

        Args:
            name (str): (Immutable) Name of Snowflake provider to be registered
            account_locator (str): (Immutable) Account Locator
            schema (str): (Immutable) Schema
            database (str): (Immutable) Database
            username (str): (Mutable) Username
            password (str): (Mutable) Password
            warehouse (str): (Mutable) Specifies the virtual warehouse to use by default for queries, loading, etc.
            role (str): (Mutable) Specifies the role to use by default for accessing Snowflake objects in the client session
            description (str): (Mutable) Description of Snowflake provider to be registered
            team (str): (Mutable) Name of team
            tags (List[str]): (Mutable) Optional grouping mechanism for resources
            properties (dict): (Mutable) Optional grouping mechanism for resources

        Returns:
            snowflake (OfflineSQLProvider): Provider
        """
        tags, properties = set_tags_properties(tags, properties)
        config = SnowflakeConfig(
            account_locator=account_locator,
            database=database,
            username=username,
            password=password,
            schema=schema,
            warehouse=warehouse,
            role=role,
        )
        provider = Provider(
            name=name,
            function="OFFLINE",
            description=description,
            team=team,
            config=config,
            tags=tags,
            properties=properties,
        )
        self.__resources.append(provider)
        return OfflineSQLProvider(self, provider)

    # TODO: Recheck mutable fields
    def register_snowflake(
        self,
        name: str,
        username: str,
        password: str,
        account: str,
        organization: str,
        database: str,
        schema: str = "PUBLIC",
        description: str = "",
        team: str = "",
        warehouse: str = "",
        role: str = "",
        tags: List[str] = [],
        properties: dict = {},
    ):
        """Register a Snowflake provider.

        **Examples**:
        ```
        snowflake = ff.register_snowflake(
            name="snowflake-quickstart",
            username="snowflake",
            password="password", #pragma: allowlist secret
            account="account",
            organization="organization",
            database="snowflake",
            schema="PUBLIC",
            description="A Snowflake deployment we created for the Featureform quickstart"
        )
        ```

        Args:
            name (str): (Immutable) Name of Snowflake provider to be registered
            account (str): (Immutable) Account
            organization (str): (Immutable) Organization
            database (str): (Immutable) Database
            schema (str): (Immutable) Schema
            username (str): (Mutable) Username
            password (str): (Mutable) Password
            warehouse (str): (Mutable) Specifies the virtual warehouse to use by default for queries, loading, etc.
            role (str): (Mutable) Specifies the role to use by default for accessing Snowflake objects in the client session
            description (str): (Mutable) Description of Snowflake provider to be registered
            team (str): (Mutable) Name of team
            tags (List[str]): (Mutable) Optional grouping mechanism for resources
            properties (dict): (Mutable) Optional grouping mechanism for resources

        Returns:
            snowflake (OfflineSQLProvider): Provider
        """
        tags, properties = set_tags_properties(tags, properties)
        config = SnowflakeConfig(
            account=account,
            database=database,
            organization=organization,
            username=username,
            password=password,
            schema=schema,
            warehouse=warehouse,
            role=role,
        )
        provider = Provider(
            name=name,
            function="OFFLINE",
            description=description,
            team=team,
            config=config,
            tags=tags,
            properties=properties,
        )
        self.__resources.append(provider)
        return OfflineSQLProvider(self, provider)

    def register_postgres(
        self,
        name: str,
        host: str,
        user: str,
        password: str,
        database: str,
        port: str = "5432",
        description: str = "",
        team: str = "",
        sslmode: str = "disable",
        tags: List[str] = [],
        properties: dict = {},
    ):
        """Register a Postgres provider.

        **Examples**:
        ```
        postgres = ff.register_postgres(
            name="postgres-quickstart",
            description="A Postgres deployment we created for the Featureform quickstart",
            host="quickstart-postgres",  # The internal dns name for postgres
            port="5432",
            user="postgres",
            password="password", #pragma: allowlist secret
            database="postgres"
        )
        ```

        Args:
            name (str): (Immutable) Name of Postgres provider to be registered
            host (str): (Immutable) Hostname for Postgres
            database (str): (Immutable) Database
            port (str): (Mutable) Port
            user (str): (Mutable) User
            password (str): (Mutable) Password
            sslmode (str): (Mutable) SSL mode
            description (str): (Mutable) Description of Postgres provider to be registered
            team (str): (Mutable) Name of team
            tags (List[str]): (Mutable) Optional grouping mechanism for resources
            properties (dict): (Mutable) Optional grouping mechanism for resources

        Returns:
            postgres (OfflineSQLProvider): Provider
        """
        tags, properties = set_tags_properties(tags, properties)
        config = PostgresConfig(
            host=host,
            port=port,
            database=database,
            user=user,
            password=password,
            sslmode=sslmode,
        )
        provider = Provider(
            name=name,
            function="OFFLINE",
            description=description,
            team=team,
            config=config,
            tags=tags or [],
            properties=properties or {},
        )

        self.__resources.append(provider)
        return OfflineSQLProvider(self, provider)

    def register_clickhouse(
        self,
        name: str,
        host: str,
        user: str,
        password: str,
        database: str,
        port: int = 9000,
        description: str = "",
        team: str = "",
        ssl: bool = False,
        tags: List[str] = [],
        properties: dict = {},
    ):
        """Register a ClickHouse provider.

        **Examples**:
        ```
        clickhouse = ff.register_clickhouse(
            name="clickhouse-quickstart",
            description="A ClickHouse deployment we created for the Featureform quickstart",
            host="quickstart-clickhouse",  # The internal dns name for clickhouse
            port=9000,
            user="default",
            password="", #pragma: allowlist secret
            database="default"
        )
        ```

        Args:
            name (str): (Immutable) Name of ClickHouse provider to be registered
            host (str): (Immutable) Hostname for ClickHouse
            database (str): (Immutable) ClickHouse database
            port (int): (Mutable) Port
            ssl (bool): (Mutable) Enable SSL
            user (str): (Mutable) User
            password (str): (Mutable) ClickHouse password
            description (str): (Mutable) Description of ClickHouse provider to be registered
            team (str): (Mutable) Name of team
            tags (List[str]): (Mutable) Optional grouping mechanism for resources
            properties (dict): (Mutable) Optional grouping mechanism for resources

        Returns:
            clickhouse (OfflineSQLProvider): Provider
        """
        tags, properties = set_tags_properties(tags, properties)
        config = ClickHouseConfig(
            host=host,
            port=port,
            database=database,
            user=user,
            password=password,
            ssl=ssl,
        )
        provider = Provider(
            name=name,
            function="OFFLINE",
            description=description,
            team=team,
            config=config,
            tags=tags,
            properties=properties,
        )
        self.__resources.append(provider)
        return OfflineSQLProvider(self, provider)

    def register_redshift(
        self,
        name: str,
        host: str,
        port: str,
        user: str,
        password: str,
        database: str,
        description: str = "",
        team: str = "",
        sslmode: str = "disable",
        tags: List[str] = [],
        properties: dict = {},
    ):
        """Register a Redshift provider.

        **Examples**:
        ```
        redshift = ff.register_redshift(
            name="redshift-quickstart",
            description="A Redshift deployment we created for the Featureform quickstart",
            host="quickstart-redshift",  # The internal dns name for redshift
            port="5432",
            user="redshift",
            password="password", #pragma: allowlist secret
            database="dev"
        )
        ```

        Args:
            name (str): (Immutable) Name of Redshift provider to be registered
            host (str): (Immutable) Hostname for Redshift
            database (str): (Immutable) Redshift database
            port (str): (Mutable) Port
            user (str): (Mutable) User
            password (str): (Mutable) Redshift password
            sslmode (str): (Mutable) SSL mode
            description (str): (Mutable) Description of Redshift provider to be registered
            team (str): (Mutable) Name of team
            tags (List[str]): (Mutable) Optional grouping mechanism for resources
            properties (dict): (Mutable) Optional grouping mechanism for resources

        Returns:
            redshift (OfflineSQLProvider): Provider
        """
        tags, properties = set_tags_properties(tags, properties)
        config = RedshiftConfig(
            host=host,
            port=port,
            database=database,
            user=user,
            password=password,
            sslmode=sslmode,
        )
        provider = Provider(
            name=name,
            function="OFFLINE",
            description=description,
            team=team,
            config=config,
            tags=tags,
            properties=properties,
        )
        self.__resources.append(provider)
        return OfflineSQLProvider(self, provider)

    # TODO: Add deprecated warning for credentials_path
    def register_bigquery(
        self,
        name: str,
        project_id: str,
        dataset_id: str,
        credentials: GCPCredentials,
        credentials_path: str = "",
        description: str = "",
        team: str = "",
        tags: List[str] = [],
        properties: dict = {},
    ):
        """Register a BigQuery provider.

        **Examples**:
        ```
        bigquery = ff.register_bigquery(
            name="bigquery-quickstart",
            description="A BigQuery deployment we created for the Featureform quickstart",
            project_id="quickstart-project",
            dataset_id="quickstart-dataset",
            credentials=GCPCredentials(...)
        )
        ```

        Args:
            name (str): (Immutable) Name of BigQuery provider to be registered
            project_id (str): (Immutable) The Project name in GCP
            dataset_id (str): (Immutable) The Dataset name in GCP under the Project Id
            credentials (GCPCredentials): (Mutable) GCP credentials to access BigQuery
            description (str): (Mutable) Description of BigQuery provider to be registered
            team (str): (Mutable) Name of team
            tags (List[str]): (Mutable) Optional grouping mechanism for resources
            properties (dict): (Mutable) Optional grouping mechanism for resources

        Returns:
            bigquery (OfflineSQLProvider): Provider
        """
        tags, properties = set_tags_properties(tags, properties)

        config = BigQueryConfig(
            project_id=project_id,
            dataset_id=dataset_id,
            credentials=credentials,
        )
        provider = Provider(
            name=name,
            function="OFFLINE",
            description=description,
            team=team,
            config=config,
            tags=tags,
            properties=properties,
        )
        self.__resources.append(provider)
        return OfflineSQLProvider(self, provider)

    def register_spark(
        self,
        name: str,
        executor: ExecutorCredentials,
        filestore: FileStoreProvider,
        description: str = "",
        team: str = "",
        tags: List[str] = [],
        properties: dict = {},
    ):
        """Register a Spark on Executor provider.

        **Examples**:
        ```
        spark = ff.register_spark(
            name="spark-quickstart",
            description="A Spark deployment we created for the Featureform quickstart",
            team="featureform-team",
            executor=databricks,
            filestore=azure_blob_store
        )
        ```

        Args:
            name (str): (Immutable) Name of Spark provider to be registered
            executor (ExecutorCredentials): (Mutable) An Executor Provider used for the compute power
            filestore (FileStoreProvider): (Mutable) A FileStoreProvider used for storage of data
            description (str): (Mutable) Description of Spark provider to be registered
            team (str): (Mutable) Name of team
            tags (List[str]): (Mutable) Optional grouping mechanism for resources
            properties (dict): (Mutable) Optional grouping mechanism for resources

        Returns:
            spark (OfflineSparkProvider): Provider
        """
        tags, properties = set_tags_properties(tags, properties)
        config = SparkConfig(
            executor_type=executor.type(),
            executor_config=executor.config(),
            store_type=filestore.store_type(),
            store_config=filestore.config(),
        )

        provider = Provider(
            name=name,
            function="OFFLINE",
            description=description,
            team=team,
            config=config,
            tags=tags,
            properties=properties,
        )
        self.__resources.append(provider)
        return OfflineSparkProvider(self, provider)

    # TODO: Change things to either filestore or store
    def register_k8s(
        self,
        name: str,
        store: FileStoreProvider,
        description: str = "",
        team: str = "",
        docker_image: str = "",
        tags: List[str] = [],
        properties: dict = {},
    ):
        """
        Register an offline store provider to run on Featureform's own k8s deployment.
        **Examples**:
        ```
        spark = ff.register_k8s(
            name="k8s",
            store=AzureBlobStore(),
            docker_image="my-repo/image:version"
        )
        ```

        Args:
            name (str): (Immutable) Name of provider
            store (FileStoreProvider): (Mutable) Reference to registered file store provider
            docker_image (str): (Mutable) A custom docker image using the base image featureformcom/k8s_runner
            description (str): (Mutable) Description of primary data to be registered
            team (str): (Mutable) A string parameter describing the team that owns the provider
            tags (List[str]): (Mutable) Optional grouping mechanism for resources
            properties (dict): (Mutable) Optional grouping mechanism for resources
        """

        tags, properties = set_tags_properties(tags, properties)
        config = K8sConfig(
            store_type=store.store_type(),
            store_config=store.config(),
            docker_image=docker_image,
        )

        provider = Provider(
            name=name,
            function="OFFLINE",
            description=description,
            team=team,
            config=config,
            tags=tags,
            properties=properties,
        )
        self.__resources.append(provider)
        return OfflineK8sProvider(self, provider)

    def register_primary_data(
        self,
        name: str,
        location: Location,
        provider: Union[str, OfflineProvider],
        tags: List[str],
        properties: dict,
        variant: str = "",
        owner: Union[str, UserRegistrar] = "",
        description: str = "",
    ):
        """Register a primary data source.

        Args:
            name (str): Name of source
            variant (str): Name of variant
            location (Location): Location of primary data
            provider (Union[str, OfflineProvider]): Provider
            owner (Union[str, UserRegistrar]): Owner
            description (str): Description of primary data to be registered

        Returns:
            source (ColumnSourceRegistrar): Source
        """
        if not isinstance(owner, str):
            owner = owner.name()
        if owner == "":
            owner = self.must_get_default_owner()
        if variant == "":
            variant = self.__run
        if not isinstance(provider, str):
            provider = provider.name()
        source = SourceVariant(
            created=None,
            name=name,
            variant=variant,
            definition=PrimaryData(location=location),
            owner=owner,
            provider=provider,
            description=description,
            tags=tags,
            properties=properties,
        )
        self.__resources.append(source)
        column_source_registrar = ColumnSourceRegistrar(self, source)
        self.map_client_object_to_resource(column_source_registrar, source)
        return column_source_registrar

    def register_sql_transformation(
        self,
        name: str,
        query: str,
        provider: Union[str, OfflineProvider],
        variant: str = "",
        owner: Union[str, UserRegistrar] = "",
        description: str = "",
        schedule: str = "",
        args: K8sArgs = None,
        inputs: Union[List[NameVariant], List[str], List[ColumnSourceRegistrar]] = None,
        tags: List[str] = [],
        properties: dict = {},
    ):
        """Register a SQL transformation source.

        Args:
            name (str): Name of source
            variant (str): Name of variant
            query (str): SQL query
            provider (Union[str, OfflineProvider]): Provider
            owner (Union[str, UserRegistrar]): Owner
            description (str): Description of primary data to be registered
            schedule (str): Kubernetes CronJob schedule string ("* * * * *")
            args (K8sArgs): Additional transformation arguments
            tags (List[str]): Optional grouping mechanism for resources
            properties (dict): Optional grouping mechanism for resources

        Returns:
            source (ColumnSourceRegistrar): Source
        """
        if not isinstance(owner, str):
            owner = owner.name()
        if owner == "":
            owner = self.must_get_default_owner()
        if variant == "":
            variant = self.__run
        if not isinstance(provider, str):
            provider = provider.name()
        source = SourceVariant(
            created=None,
            name=name,
            variant=variant,
            definition=SQLTransformation(query, args),
            owner=owner,
            schedule=schedule,
            provider=provider,
            description=description,
            tags=tags,
            properties=properties,
        )
        self.__resources.append(source)
        return ColumnSourceRegistrar(self, source)

    def sql_transformation(
        self,
        provider: Union[str, OfflineProvider],
        variant: str = "",
        name: str = "",
        schedule: str = "",
        owner: Union[str, UserRegistrar] = "",
        inputs: Union[List[NameVariant], List[str], List[ColumnSourceRegistrar]] = None,
        description: str = "",
        args: K8sArgs = None,
        tags: List[str] = [],
        properties: dict = {},
    ):
        """SQL transformation decorator.

        Args:
            variant (str): Name of variant
            provider (Union[str, OfflineProvider]): Provider
            name (str): Name of source
            schedule (str): Kubernetes CronJob schedule string ("* * * * *")
            owner (Union[str, UserRegistrar]): Owner
            inputs (list): Inputs to transformation
            description (str): Description of SQL transformation
            args (K8sArgs): Additional transformation arguments
            tags (List[str]): Optional grouping mechanism for resources
            properties (dict): Optional grouping mechanism for resources

        Returns:
            decorator (SQLTransformationDecorator): decorator
        """
        if not isinstance(owner, str):
            owner = owner.name()
        if owner == "":
            owner = self.must_get_default_owner()
        if variant == "":
            variant = self.__run
        if not isinstance(provider, str):
            provider = provider.name()
        decorator = SQLTransformationDecorator(
            registrar=self,
            name=name,
            run=self.__run,
            variant=variant,
            provider=provider,
            schedule=schedule,
            owner=owner,
            description=description,
            inputs=inputs,
            args=args,
            tags=tags,
            properties=properties,
        )
        return decorator

    def register_df_transformation(
        self,
        name: str,
        query: str,
        provider: Union[str, OfflineProvider],
        variant: str = "",
        owner: Union[str, UserRegistrar] = "",
        description: str = "",
        inputs: list = [],
        schedule: str = "",
        args: K8sArgs = None,
        tags: List[str] = [],
        properties: dict = {},
    ):
        """Register a Dataframe transformation source.

        Args:
            name (str): Name of source
            variant (str): Name of variant
            query (str): SQL query
            provider (Union[str, OfflineProvider]): Provider
            name (str): Name of source
            owner (Union[str, UserRegistrar]): Owner
            description (str): Description of SQL transformation
            inputs (list): Inputs to transformation
            schedule (str): Kubernetes CronJob schedule string ("* * * * *")
            args (K8sArgs): Additional transformation arguments
            tags (List[str]): Optional grouping mechanism for resources
            properties (dict): Optional grouping mechanism for resources

        Returns:
            source (ColumnSourceRegistrar): Source
        """
        if not isinstance(owner, str):
            owner = owner.name()
        if owner == "":
            owner = self.must_get_default_owner()
        if variant == "":
            variant = self.__run
        if not isinstance(provider, str):
            provider = provider.name()
        source = SourceVariant(
            created=None,
            name=name,
            variant=variant,
            definition=DFTransformation(query, inputs, args),
            owner=owner,
            schedule=schedule,
            provider=provider,
            description=description,
            tags=tags,
            properties=properties,
        )
        self.__resources.append(source)
        return ColumnSourceRegistrar(self, source)

    def df_transformation(
        self,
        provider: Union[str, OfflineProvider],
        tags: List[str],
        properties: dict,
        variant: str = "",
        name: str = "",
        owner: Union[str, UserRegistrar] = "",
        description: str = "",
        inputs: Union[List[NameVariant], List[str], List[ColumnSourceRegistrar]] = [],
        args: K8sArgs = None,
    ):
        """Dataframe transformation decorator.

        Args:
            variant (str): Name of variant
            provider (Union[str, OfflineProvider]): Provider
            name (str): Name of source
            owner (Union[str, UserRegistrar]): Owner
            description (str): Description of SQL transformation
            inputs (list): Inputs to transformation
            args (K8sArgs): Additional transformation arguments
            tags (List[str]): Optional grouping mechanism for resources
            properties (dict): Optional grouping mechanism for resources

        Returns:
            decorator (DFTransformationDecorator): decorator
        """

        if not isinstance(owner, str):
            owner = owner.name()
        if owner == "":
            owner = self.must_get_default_owner()
        if variant == "":
            variant = self.__run
        if not isinstance(provider, str):
            provider = provider.name()
        if not isinstance(inputs, list):
            raise ValueError("Dataframe transformation inputs must be a list")
        for i, nv in enumerate(inputs):
            if isinstance(nv, str):  # TODO remove this functionality
                inputs[i] = (nv, self.__run)
            elif isinstance(nv, tuple):
                try:
                    self._verify_tuple(nv)
                except TypeError as e:
                    transformation_message = f"'{name}:{variant}'"
                    if name == "":
                        transformation_message = f"with '{variant}' variant"

                    raise TypeError(
                        f"DF transformation {transformation_message} requires correct inputs "
                        f" '{nv}' is not a valid tuple: {e}"
                    )
                if inputs[i][1] == "":
                    inputs[i] = (inputs[i][0], self.__run)

        decorator = DFTransformationDecorator(
            registrar=self,
            name=name,
            variant=variant,
            provider=provider,
            owner=owner,
            description=description,
            inputs=inputs,
            args=args,
            tags=tags,
            properties=properties,
        )
        return decorator

    def _verify_tuple(self, nv_tuple):
        if not isinstance(nv_tuple, tuple):
            raise TypeError(f"not a tuple; received: '{type(nv_tuple).__name__}' type")

        if len(nv_tuple) != 2:
            raise TypeError(
                "Tuple must be of length 2, got length {}".format(len(nv_tuple))
            )
        if len(nv_tuple) == 2:
            not_string_tuples = not (
                isinstance(nv_tuple[0], str) and isinstance(nv_tuple[1], str)
            )
            if not_string_tuples:
                first_position_type = type(nv_tuple[0]).__name__
                second_position_type = type(nv_tuple[1]).__name__
                raise TypeError(
                    f"Tuple must be of type (str, str); got ({first_position_type}, {second_position_type})"
                )

    def ondemand_feature(
        self,
        fn=None,
        *,
        tags: List[str] = [],
        properties: dict = {},
        variant: str = "",
        name: str = "",
        owner: Union[str, UserRegistrar] = "",
        description: str = "",
    ):
        """On Demand Feature decorator.

        **Examples**
        ```python
        import featureform as ff

        @ff.ondemand_feature()
        def avg_user_transactions(client, params, entities):
            pass
        ```

        Args:
            variant (str): Name of variant
            name (str): Name of source
            owner (Union[str, UserRegistrar]): Owner
            description (str): Description of on demand feature
            tags (List[str]): Optional grouping mechanism for resources
            properties (dict): Optional grouping mechanism for resources

        Returns:
            decorator (OnDemandFeature): decorator

        """

        if not isinstance(owner, str):
            owner = owner.name()
        if owner == "":
            owner = self.must_get_default_owner()
        if variant == "":
            variant = self.__run
        decorator = OnDemandFeatureVariant(
            name=name,
            variant=variant,
            owner=owner,
            description=description,
            tags=tags or [],
            properties=properties or {},
        )

        self.__resources.append(decorator)

        if fn is None:
            return decorator
        else:
            return decorator(fn)

    def state(self):
        for resource in self.__resources:
            try:
                self.__state.add(resource)

            except ResourceRedefinedError:
                raise
            except Exception as e:
                resource_variant = (
                    f" ({resource.variant})" if hasattr(resource, "variant") else ""
                )
                raise Exception(
                    f"Could not add apply {resource.name}{resource_variant}: {e}"
                )
        self.__resources = []
        return self.__state

    def clear_state(self):
        self.__state = ResourceState()
        self.__client_obj_to_resource_map = {}
        self.__resources = []

    def get_state(self):
        """
        Get the state of the resources to be registered.

        Returns:
            resources (List[str]): List of resources to be registered ex. "{type} - {name} ({variant})"
        """
        if len(self.__resources) == 0:
            return "No resources to be registered"

        resources = [["Type", "Name", "Variant"]]
        for resource in self.__resources:
            if hasattr(resource, "variant"):
                resources.append(
                    [resource.__class__.__name__, resource.name, resource.variant]
                )
            else:
                resources.append([resource.__class__.__name__, resource.name, ""])

        print("Resources to be registered:")
        self.__print_state(resources)

    def __print_state(self, data):
        # Calculate the maximum width for each column
        max_widths = [max(len(str(item)) for item in col) for col in zip(*data)]

        # Format the table headers
        headers = " | ".join(
            f"{header:{width}}" for header, width in zip(data[0], max_widths)
        )

        # Generate the separator line
        separator = "-" * len(headers)

        # Format the table rows
        rows = [
            f" | ".join(f"{data[i][j]:{max_widths[j]}}" for j in range(len(data[i])))
            for i in range(1, len(data))
        ]

        # Combine the headers, separator, and rows
        table = headers + "\n" + separator + "\n" + "\n".join(rows)

        print(table)

    def register_entity(
        self,
        name: str,
        description: str = "",
        tags: List[str] = [],
        properties: dict = {},
    ):
        """Register an entity.

        **Examples**:
        ``` py
            user = ff.register_entity("user")
        ```

        Args:
            name (str): Name of entity to be registered
            description (str): Description of entity to be registered
            tags (List[str]): Optional grouping mechanism for resources
            properties (dict): Optional grouping mechanism for resources

        Returns:
            entity (EntityRegistrar): Entity
        """
        entity = Entity(
            name=name,
            description=description,
            status="",
            tags=tags,
            properties=properties,
        )
        self.__resources.append(entity)
        return EntityRegistrar(self, entity)

    def register_column_resources(
        self,
        source: Union[
            NameVariant,
            SourceRegistrar,
            SQLTransformationDecorator,
            DFTransformationDecorator,
        ],
        entity: Union[str, EntityRegistrar],
        entity_column: str,
        owner: Union[str, UserRegistrar] = "",
        inference_store: Union[str, OnlineProvider, FileStoreProvider] = "",
        features: List[ColumnMapping] = None,
        labels: List[ColumnMapping] = None,
        timestamp_column: str = "",
        description: str = "",
        schedule: str = "",
        client_object=None,
    ):
        """Create features and labels from a source. Used in the register_resources function.

        Args:
            source (Union[NameVariant, SourceRegistrar, SQLTransformationDecorator]): Source of features, labels, entity
            entity (Union[str, EntityRegistrar]): Entity
            entity_column (str): Column of entity in source
            owner (Union[str, UserRegistrar]): Owner
            inference_store (Union[str, OnlineProvider]): Online provider
            features (List[ColumnMapping]): List of ColumnMapping objects (dictionaries containing the keys: name, variant, column, resource_type)
            labels (List[ColumnMapping]): List of ColumnMapping objects (dictionaries containing the keys: name, variant, column, resource_type)
            description (str): Description
            schedule (str): Kubernetes CronJob schedule string ("* * * * *")

        Returns:
            resource (ResourceRegistrar): resource
        """

        if (
            type(inference_store) == FileStoreProvider
            and inference_store.store_type() in NON_INFERENCE_STORES
        ):
            raise Exception(
                f"cannot use '{inference_store.store_type()}' as an inference store."
            )

        if features is None:
            features = []
        if labels is None:
            labels = []
        if len(features) == 0 and len(labels) == 0:
            raise ValueError("No features or labels set")
        if isinstance(source, tuple) and source[1] == "":
            source = source[0], self.__run
        if not isinstance(entity, str):
            entity = entity.name()
        if not isinstance(inference_store, str):
            inference_store = inference_store.name()
        if not isinstance(owner, str):
            owner = owner.name()
        if owner == "":
            owner = self.must_get_default_owner()
        feature_resources = []
        label_resources = []
        for feature in features:
            variant = feature.get("variant", "")
            if variant == "":
                variant = self.__run
            if not ScalarType.has_value(feature["type"]) and not isinstance(
                feature["type"], ScalarType
            ):
                raise ValueError(
                    f"Invalid type for feature {feature['name']} ({variant}). Must be a ScalarType or one of {ScalarType.get_values()}"
                )
            if isinstance(feature["type"], ScalarType):
                feature["type"] = feature["type"].value
            desc = feature.get("description", "")
            feature_tags = feature.get("tags", [])
            feature_properties = feature.get("properties", {})
            additional_Parameters = self._get_additional_parameters(ondemand_feature)
            is_embedding = feature.get("is_embedding", False)
            dims = feature.get("dims", 0)
            value_type = ScalarType(feature["type"])
            if dims > 0:
                value_type = VectorType(value_type, dims, is_embedding)
            resource = FeatureVariant(
                created=None,
                name=feature["name"],
                variant=variant,
                source=source,
                value_type=value_type,
                entity=entity,
                owner=owner,
                provider=inference_store,
                description=desc,
                schedule=schedule,
                location=ResourceColumnMapping(
                    entity=entity_column,
                    value=feature["column"],
                    timestamp=timestamp_column,
                ),
                tags=feature_tags,
                properties=feature_properties,
                additional_parameters=additional_Parameters,
            )
            self.__resources.append(resource)
            self.map_client_object_to_resource(client_object, resource)
            feature_resources.append(resource)

        for label in labels:
            variant = label.get("variant", "")
            if variant == "":
                variant = self.__run
            if not ScalarType.has_value(label["type"]) and not isinstance(
                label["type"], ScalarType
            ):
                raise ValueError(
                    f"Invalid type for label {label['name']} ({variant}). Must be a ScalarType or one of {ScalarType.get_values()}"
                )
            if isinstance(label["type"], ScalarType):
                label["type"] = label["type"].value
            desc = label.get("description", "")
            label_tags = label.get("tags", [])
            label_properties = label.get("properties", {})
            resource = LabelVariant(
                name=label["name"],
                variant=variant,
                source=source,
                value_type=label["type"],
                entity=entity,
                owner=owner,
                provider=inference_store,
                description=desc,
                location=ResourceColumnMapping(
                    entity=entity_column,
                    value=label["column"],
                    timestamp=timestamp_column,
                ),
                tags=label_tags,
                properties=label_properties,
            )
            self.__resources.append(resource)
            self.map_client_object_to_resource(client_object, resource)
            label_resources.append(resource)
        return ResourceRegistrar(self, features, labels)

    def _get_additional_parameters(self, feature):
        return OndemandFeatureParameters(definition="() => REGISTER")

    def __get_feature_nv(self, features, run):
        feature_nv_list = []
        feature_lags = []
        for feature in features:
            if isinstance(feature, str):
                feature_nv_list.append((feature, run))
            elif isinstance(feature, dict):
                lag = feature.get("lag")
                if "variant" not in feature:
                    feature["variant"] = run
                if lag:
                    required_lag_keys = set(["lag", "feature", "variant"])
                    received_lag_keys = set(feature.keys())
                    if (
                        required_lag_keys.intersection(received_lag_keys)
                        != required_lag_keys
                    ):
                        raise ValueError(
                            f"feature lags require 'lag', 'feature', 'variant' fields. Received: {feature.keys()}"
                        )

                    if not isinstance(lag, timedelta):
                        raise ValueError(
                            f"the lag, '{lag}', needs to be of type 'datetime.timedelta'. Received: {type(lag)}."
                        )

                    feature_name_variant = (feature["feature"], feature["variant"])
                    if feature_name_variant not in feature_nv_list:
                        feature_nv_list.append(feature_name_variant)

                    lag_name = f"{feature['feature']}_{feature['variant']}_lag_{lag}"
                    sanitized_lag_name = (
                        lag_name.replace(" ", "").replace(",", "_").replace(":", "_")
                    )
                    feature["name"] = feature.get("name", sanitized_lag_name)

                    feature_lags.append(feature)
                else:
                    feature_nv = (feature["name"], feature["variant"])
                    feature_nv_list.append(feature_nv)
            elif isinstance(feature, list):
                feature_nv, feature_lags_list = self.__get_feature_nv(feature, run)
                if len(feature_nv) != 0:
                    feature_nv_list.extend(feature_nv)

                if len(feature_lags_list) != 0:
                    feature_lags.extend(feature_lags_list)
            else:
                feature_nv_list.append(feature)

        return feature_nv_list, feature_lags

    def register_training_set(
        self,
        name: str,
        variant: str = "",
        features: Union[
            list, List[FeatureColumnResource], MultiFeatureColumnResource
        ] = [],
        label: Union[NameVariant, LabelColumnResource] = ("", ""),
        resources: list = [],
        owner: Union[str, UserRegistrar] = "",
        description: str = "",
        schedule: str = "",
        tags: List[str] = [],
        properties: dict = {},
    ):
        """Register a training set.

        **Example**:
        ```
        ff.register_training_set(
            name="my_training_set",
            label=("label", "v1"),
            features=[("feature1", "v1"), ("feature2", "v1")],
        )
        ```

        Args:
            name (str): Name of training set to be registered
            variant (str): Name of variant to be registered
            label (NameVariant): Label of training set
            features (List[NameVariant]): Features of training set
            resources (List[Resource]): A list of previously registered resources
            owner (Union[str, UserRegistrar]): Owner
            description (str): Description of training set to be registered
            schedule (str): Kubernetes CronJob schedule string ("* * * * *")
            tags (List[str]): Optional grouping mechanism for resources
            properties (dict): Optional grouping mechanism for resources

        Returns:
            resource (ResourceRegistrar): resource
        """
        if not isinstance(owner, str):
            owner = owner.name()
        if owner == "":
            owner = self.must_get_default_owner()
        if variant == "":
            variant = self.__run

        if not isinstance(features, (list, MultiFeatureColumnResource)):
            raise ValueError(
                f"Invalid features type: {type(features)} "
                "Features must be entered as a list of name-variant tuples (e.g. [('feature1', 'quickstart'), ('feature2', 'quickstart')]) or a list of FeatureColumnResource instances."
            )
        if not isinstance(label, (tuple, str, LabelColumnResource)):
            raise ValueError(
                f"Invalid label type: {type(label)} "
                "Label must be entered as a name-variant tuple (e.g. ('fraudulent', 'quickstart')), a resource name, or an instance of LabelColumnResource."
            )

        for resource in resources:
            features += resource.features()
            resource_label = resource.label()
            # label == () if it is NOT manually entered
            if label == ("", ""):
                label = resource_label
            # Elif: If label was updated to store resource_label it will not check the following elif
            elif resource_label != ():
                raise ValueError("A training set can only have one label")

        features, feature_lags = self.__get_feature_nv(features, self.__run)
        if label == ():
            raise ValueError("Label must be set")
        if features == []:
            raise ValueError("A training-set must have atleast one feature")
        if isinstance(label, str):
            label = (label, self.__run)
        if not isinstance(label, LabelColumnResource) and label[1] == "":
            label = (label[0], self.__run)

        processed_features = []
        for feature in features:
            if isinstance(feature, tuple) and feature[1] == "":
                feature = (feature[0], self.__run)
            processed_features.append(feature)
        resource = TrainingSetVariant(
            created=None,
            name=name,
            variant=variant,
            description=description,
            owner=owner,
            schedule=schedule,
            label=label,
            features=processed_features,
            feature_lags=feature_lags,
            tags=tags,
            properties=properties,
        )
        self.__resources.append(resource)
        return resource

    def register_model(
        self, name: str, tags: List[str] = [], properties: dict = {}
    ) -> Model:
        """Register a model.

        Args:
            name (str): Model to be registered
            tags (List[str]): Optional grouping mechanism for resources
            properties (dict): Optional grouping mechanism for resources

        Returns:
            ModelRegistrar: Model
        """
        model = Model(name, description="", tags=tags, properties=properties)
        self.__resources.append(model)
        return model

df_transformation(provider, tags, properties, variant='', name='', owner='', description='', inputs=[], args=None)

Dataframe transformation decorator.

Parameters:

Name	Type	Description	Default
variant	str	Name of variant	''
provider	Union[str, OfflineProvider]	Provider	required
name	str	Name of source	''
owner	Union[str, UserRegistrar]	Owner	''
description	str	Description of SQL transformation	''
inputs	list	Inputs to transformation	[]
args	K8sArgs	Additional transformation arguments	None
tags	List[str]	Optional grouping mechanism for resources	required
properties	dict	Optional grouping mechanism for resources	required

Returns:

Name	Type	Description
decorator	DFTransformationDecorator	decorator

Source code in src/featureform/register.py

def df_transformation(
    self,
    provider: Union[str, OfflineProvider],
    tags: List[str],
    properties: dict,
    variant: str = "",
    name: str = "",
    owner: Union[str, UserRegistrar] = "",
    description: str = "",
    inputs: Union[List[NameVariant], List[str], List[ColumnSourceRegistrar]] = [],
    args: K8sArgs = None,
):
    """Dataframe transformation decorator.

    Args:
        variant (str): Name of variant
        provider (Union[str, OfflineProvider]): Provider
        name (str): Name of source
        owner (Union[str, UserRegistrar]): Owner
        description (str): Description of SQL transformation
        inputs (list): Inputs to transformation
        args (K8sArgs): Additional transformation arguments
        tags (List[str]): Optional grouping mechanism for resources
        properties (dict): Optional grouping mechanism for resources

    Returns:
        decorator (DFTransformationDecorator): decorator
    """

    if not isinstance(owner, str):
        owner = owner.name()
    if owner == "":
        owner = self.must_get_default_owner()
    if variant == "":
        variant = self.__run
    if not isinstance(provider, str):
        provider = provider.name()
    if not isinstance(inputs, list):
        raise ValueError("Dataframe transformation inputs must be a list")
    for i, nv in enumerate(inputs):
        if isinstance(nv, str):  # TODO remove this functionality
            inputs[i] = (nv, self.__run)
        elif isinstance(nv, tuple):
            try:
                self._verify_tuple(nv)
            except TypeError as e:
                transformation_message = f"'{name}:{variant}'"
                if name == "":
                    transformation_message = f"with '{variant}' variant"

                raise TypeError(
                    f"DF transformation {transformation_message} requires correct inputs "
                    f" '{nv}' is not a valid tuple: {e}"
                )
            if inputs[i][1] == "":
                inputs[i] = (inputs[i][0], self.__run)

    decorator = DFTransformationDecorator(
        registrar=self,
        name=name,
        variant=variant,
        provider=provider,
        owner=owner,
        description=description,
        inputs=inputs,
        args=args,
        tags=tags,
        properties=properties,
    )
    return decorator

get_bigquery(name)

Get a BigQuery provider. The returned object can be used to register additional resources.

Examples:

bigquery = ff.get_bigquery("bigquery-quickstart")
transactions = bigquery.register_table(
    name="transactions",
    variant="kaggle",
    description="Fraud Dataset From Kaggle",
    table="Transactions",  # This is the table's name in BigQuery
)

Parameters:

Name	Type	Description	Default
name	str	Name of BigQuery provider to be retrieved	required

Returns:

Name	Type	Description
bigquery	OfflineSQLProvider	Provider

Source code in src/featureform/register.py

def get_bigquery(self, name):
    """Get a BigQuery provider. The returned object can be used to register additional resources.

    **Examples**:
    ``` py
    bigquery = ff.get_bigquery("bigquery-quickstart")
    transactions = bigquery.register_table(
        name="transactions",
        variant="kaggle",
        description="Fraud Dataset From Kaggle",
        table="Transactions",  # This is the table's name in BigQuery
    )
    ```

    Args:
        name (str): Name of BigQuery provider to be retrieved

    Returns:
        bigquery (OfflineSQLProvider): Provider
    """
    mock_config = BigQueryConfig(
        project_id="mock_project",
        dataset_id="mock_dataset",
        credentials=GCPCredentials(
            project_id="mock_project",
            credentials_path="client/tests/test_files/bigquery_dummy_credentials.json",
        ),
    )
    mock_provider = Provider(
        name=name, function="OFFLINE", description="", team="", config=mock_config
    )
    return OfflineSQLProvider(self, mock_provider)

get_blob_store(name)

Get an Azure Blob provider. The returned object can be used to register additional resources.

Examples:

azure_blob = ff.get_blob_store("azure-blob-quickstart")

average_user_transaction.register_resources(
    entity=user,
    entity_column="user_id",
    inference_store=azure_blob,
    features=[
        {"name": "avg_transactions", "variant": "quickstart", "column": "avg_transaction_amt", "type": "float32"},
    ],
)

Parameters:

Name	Type	Description	Default
name	str	Name of Azure blob provider to be retrieved	required

Returns:

Name	Type	Description
azure_blob	FileStoreProvider	Provider

Source code in src/featureform/register.py

def get_blob_store(self, name):
    """Get an Azure Blob provider. The returned object can be used to register additional resources.

    **Examples**:
    ``` py
    azure_blob = ff.get_blob_store("azure-blob-quickstart")

    average_user_transaction.register_resources(
        entity=user,
        entity_column="user_id",
        inference_store=azure_blob,
        features=[
            {"name": "avg_transactions", "variant": "quickstart", "column": "avg_transaction_amt", "type": "float32"},
        ],
    )
    ```

    Args:
        name (str): Name of Azure blob provider to be retrieved

    Returns:
        azure_blob (FileStoreProvider): Provider
    """
    fake_azure_config = AzureFileStoreConfig(
        account_name="", account_key="", container_name="", root_path=""
    )
    fake_config = OnlineBlobConfig(
        store_type="AZURE", store_config=fake_azure_config.config()
    )
    mock_provider = Provider(
        name=name, function="ONLINE", description="", team="", config=fake_config
    )
    return FileStoreProvider(self, mock_provider, fake_config, "AZURE")

get_clickhouse(name)

Get a ClickHouse provider. The returned object can be used to register additional resources.

Examples:

clickhouse = ff.get_clickhouse("clickhouse-quickstart")
transactions = clickhouse.register_table(
    name="transactions",
    variant="kaggle",
    description="Fraud Dataset From Kaggle",
    table="Transactions",  # This is the table's name in ClickHouse
)

Parameters:

Name	Type	Description	Default
name	str	Name of ClickHouse provider to be retrieved	required

Returns:

Name	Type	Description
clickhouse	OfflineSQLProvider	Provider

Source code in src/featureform/register.py

def get_clickhouse(self, name):
    """Get a ClickHouse provider. The returned object can be used to register additional resources.

    **Examples**:
    ``` py
    clickhouse = ff.get_clickhouse("clickhouse-quickstart")
    transactions = clickhouse.register_table(
        name="transactions",
        variant="kaggle",
        description="Fraud Dataset From Kaggle",
        table="Transactions",  # This is the table's name in ClickHouse
    )
    ```

    Args:
        name (str): Name of ClickHouse provider to be retrieved

    Returns:
        clickhouse (OfflineSQLProvider): Provider
    """
    mock_config = ClickHouseConfig(
        host="",
        port=9000,
        database="",
        user="",
        password="",
        ssl=False,
    )
    mock_provider = Provider(
        name=name, function="OFFLINE", description="", team="", config=mock_config
    )
    return OfflineSQLProvider(self, mock_provider)

get_dynamodb(name)

Get a DynamoDB provider. The returned object can be used as an inference store in feature registration.

Examples:

dynamodb = ff.get_dynamodb("dynamodb-quickstart")

@ff.entity
class User:
    avg_transactions = ff.Feature(
        average_user_transaction[["user_id", "avg_transaction_amt"]],
        type=ff.Float32,
        inference_store=dynamodb,
    )

Parameters:

Name	Type	Description	Default
name	str	Name of DynamoDB provider to be retrieved	required

Returns:

Name	Type	Description
dynamodb	OnlineProvider	Provider

Source code in src/featureform/register.py

def get_dynamodb(self, name: str):
    """Get a DynamoDB provider. The returned object can be used as an inference store in feature registration.

    **Examples**:
    ``` py
    dynamodb = ff.get_dynamodb("dynamodb-quickstart")

    @ff.entity
    class User:
        avg_transactions = ff.Feature(
            average_user_transaction[["user_id", "avg_transaction_amt"]],
            type=ff.Float32,
            inference_store=dynamodb,
        )
    ```

    Args:
        name (str): Name of DynamoDB provider to be retrieved

    Returns:
        dynamodb (OnlineProvider): Provider
    """
    mock_config = DynamodbConfig(
        region="", access_key="", secret_key="", should_import_from_s3=False
    )
    mock_provider = Provider(
        name=name, function="ONLINE", description="", team="", config=mock_config
    )
    return OnlineProvider(self, mock_provider)

get_entity(name)

Get an entity. The returned object can be used to register additional resources.

Examples:

entity = get_entity("user")
transactions.register_resources(
    entity=entity,
    entity_column="customerid",
    labels=[
        {"name": "fraudulent", "variant": "quickstart", "column": "isfraud", "type": "bool"},
    ],
)

Parameters:

Name	Type	Description	Default
name	str	Name of entity to be retrieved	required

Returns: entity (EntityRegistrar): Entity

Source code in src/featureform/register.py

def get_entity(self, name: str):
    """Get an entity. The returned object can be used to register additional resources.

    **Examples**:

    ``` py
    entity = get_entity("user")
    transactions.register_resources(
        entity=entity,
        entity_column="customerid",
        labels=[
            {"name": "fraudulent", "variant": "quickstart", "column": "isfraud", "type": "bool"},
        ],
    )
    ```

    Args:
        name (str): Name of entity to be retrieved
    Returns:
        entity (EntityRegistrar): Entity
    """
    fakeEntity = Entity(
        name=name, description="", status="", tags=[], properties={}
    )
    return EntityRegistrar(self, fakeEntity)

get_kubernetes(name)

Get a k8s provider. The returned object can be used to register additional resources.

Examples:

k8s = ff.get_kubernetes("k8s-azure-quickstart")
transactions = k8s.register_file(
    name="transactions",
    variant="kaggle",
    description="Fraud Dataset From Kaggle",
    path="path/to/blob",
)

Parameters:

Name	Type	Description	Default
name	str	Name of k8s provider to be retrieved	required

Returns:

Name	Type	Description
k8s	OfflineK8sProvider	Provider

Source code in src/featureform/register.py

def get_kubernetes(self, name):
    """
    Get a k8s provider. The returned object can be used to register additional resources.

    **Examples**:
    ``` py

    k8s = ff.get_kubernetes("k8s-azure-quickstart")
    transactions = k8s.register_file(
        name="transactions",
        variant="kaggle",
        description="Fraud Dataset From Kaggle",
        path="path/to/blob",
    )
    ```

    Args:
        name (str): Name of k8s provider to be retrieved

    Returns:
        k8s (OfflineK8sProvider): Provider
    """
    mock_config = K8sConfig(store_type="", store_config={})
    mock_provider = Provider(
        name=name, function="OFFLINE", description="", team="", config=mock_config
    )
    return OfflineK8sProvider(self, mock_provider)

get_mongodb(name)

Get a MongoDB provider. The returned object can be used to register additional resources.

Examples:

mongodb = ff.get_mongodb("mongodb-quickstart")

average_user_transaction.register_resources(
    entity=user,
    entity_column="user_id",
    inference_store=mongodb,
    features=[
        {"name": "avg_transactions", "variant": "quickstart", "column": "avg_transaction_amt", "type": "float32"},
    ],
)

Parameters:

Name	Type	Description	Default
name	str	Name of MongoDB provider to be retrieved	required

Returns:

Name	Type	Description
mongodb	OnlineProvider	Provider

Source code in src/featureform/register.py

def get_mongodb(self, name: str):
    """Get a MongoDB provider. The returned object can be used to register additional resources.

    **Examples**:
    ``` py
    mongodb = ff.get_mongodb("mongodb-quickstart")

    average_user_transaction.register_resources(
        entity=user,
        entity_column="user_id",
        inference_store=mongodb,
        features=[
            {"name": "avg_transactions", "variant": "quickstart", "column": "avg_transaction_amt", "type": "float32"},
        ],
    )
    ```

    Args:
        name (str): Name of MongoDB provider to be retrieved

    Returns:
        mongodb (OnlineProvider): Provider
    """
    mock_config = MongoDBConfig(
        username="", password="", host="", port="", database="", throughput=1
    )
    mock_provider = Provider(
        name=name, function="ONLINE", description="", team="", config=mock_config
    )
    return OnlineProvider(self, mock_provider)

get_postgres(name)

Get a Postgres provider. The returned object can be used to register additional resources.

Examples:

postgres = ff.get_postgres("postgres-quickstart")
transactions = postgres.register_table(
    name="transactions",
    variant="kaggle",
    description="Fraud Dataset From Kaggle",
    table="Transactions",  # This is the table's name in Postgres
)

Parameters:

Name	Type	Description	Default
name	str	Name of Postgres provider to be retrieved	required

Returns:

Name	Type	Description
postgres	OfflineSQLProvider	Provider

Source code in src/featureform/register.py

def get_postgres(self, name):
    """Get a Postgres provider. The returned object can be used to register additional resources.

    **Examples**:
    ``` py
    postgres = ff.get_postgres("postgres-quickstart")
    transactions = postgres.register_table(
        name="transactions",
        variant="kaggle",
        description="Fraud Dataset From Kaggle",
        table="Transactions",  # This is the table's name in Postgres
    )
    ```

    Args:
        name (str): Name of Postgres provider to be retrieved

    Returns:
        postgres (OfflineSQLProvider): Provider
    """
    mock_config = PostgresConfig(
        host="",
        port="",
        database="",
        user="",
        password="",
        sslmode="",
    )
    mock_provider = Provider(
        name=name, function="OFFLINE", description="", team="", config=mock_config
    )
    return OfflineSQLProvider(self, mock_provider)

get_redis(name)

Get a Redis provider. The returned object can be used to register additional resources.

Examples:

redis = ff.get_redis("redis-quickstart")

average_user_transaction.register_resources(
    entity=user,
    entity_column="user_id",
    inference_store=redis,
    features=[
        {"name": "avg_transactions", "variant": "quickstart", "column": "avg_transaction_amt", "type": "float32"},
    ],
)

Parameters:

Name	Type	Description	Default
name	str	Name of Redis provider to be retrieved	required

Returns:

Name	Type	Description
redis	OnlineProvider	Provider

Source code in src/featureform/register.py

def get_redis(self, name):
    """Get a Redis provider. The returned object can be used to register additional resources.

    **Examples**:
    ``` py
    redis = ff.get_redis("redis-quickstart")

    average_user_transaction.register_resources(
        entity=user,
        entity_column="user_id",
        inference_store=redis,
        features=[
            {"name": "avg_transactions", "variant": "quickstart", "column": "avg_transaction_amt", "type": "float32"},
        ],
    )
    ```

    Args:
        name (str): Name of Redis provider to be retrieved

    Returns:
        redis (OnlineProvider): Provider
    """
    mock_config = RedisConfig(host="", port=123, password="", db=123)
    mock_provider = Provider(
        name=name, function="ONLINE", description="", team="", config=mock_config
    )
    return OnlineProvider(self, mock_provider)

get_redshift(name)

Get a Redshift provider. The returned object can be used to register additional resources.

Examples:

redshift = ff.get_redshift("redshift-quickstart")
transactions = redshift.register_table(
    name="transactions",
    variant="kaggle",
    description="Fraud Dataset From Kaggle",
    table="Transactions",  # This is the table's name in Postgres
)

Parameters:

Name	Type	Description	Default
name	str	Name of Redshift provider to be retrieved	required

Returns:

Name	Type	Description
redshift	OfflineSQLProvider	Provider

Source code in src/featureform/register.py

def get_redshift(self, name):
    """Get a Redshift provider. The returned object can be used to register additional resources.

    **Examples**:
    ``` py
    redshift = ff.get_redshift("redshift-quickstart")
    transactions = redshift.register_table(
        name="transactions",
        variant="kaggle",
        description="Fraud Dataset From Kaggle",
        table="Transactions",  # This is the table's name in Postgres
    )
    ```

    Args:
        name (str): Name of Redshift provider to be retrieved

    Returns:
        redshift (OfflineSQLProvider): Provider
    """
    mock_config = RedshiftConfig(
        host="", port="5439", database="", user="", password="", sslmode=""
    )
    mock_provider = Provider(
        name=name, function="OFFLINE", description="", team="", config=mock_config
    )
    return OfflineSQLProvider(self, mock_provider)

get_run()

Get the current run name.

Examples:

import featureform as ff

client = ff.Client()
f = client.features(("avg_transaction_amount", ff.get_run()), {"user": "123"})

Returns:

Name	Type	Description
run	str	The name of the current run

Source code in src/featureform/register.py

def get_run(self) -> str:
    """
    Get the current run name.

    **Examples**:
    ``` py
    import featureform as ff

    client = ff.Client()
    f = client.features(("avg_transaction_amount", ff.get_run()), {"user": "123"})

    ```

    Returns:
        run: The name of the current run
    """
    return self.__run

get_s3(name)

Get a S3 provider. The returned object can be used with other providers such as Spark and Databricks.

Examples:

s3 = ff.get_s3("s3-quickstart")
spark = ff.register_spark(
    name=f"spark-emr-s3",
    description="A Spark deployment we created for the Featureform quickstart",
    team="featureform-team",
    executor=emr,
    filestore=s3,
)

Parameters:

Name	Type	Description	Default
name	str	Name of S3 to be retrieved	required

Returns:

Name	Type	Description
s3	FileStore	Provider

Source code in src/featureform/register.py

def get_s3(self, name):
    """
    Get a S3 provider. The returned object can be used with other providers such as Spark and Databricks.

    **Examples**:

    ``` py

    s3 = ff.get_s3("s3-quickstart")
    spark = ff.register_spark(
        name=f"spark-emr-s3",
        description="A Spark deployment we created for the Featureform quickstart",
        team="featureform-team",
        executor=emr,
        filestore=s3,
    )
    ```

    Args:
        name (str): Name of S3 to be retrieved

    Returns:
        s3 (FileStore): Provider
    """
    provider = Provider(
        name=name,
        function="OFFLINE",
        description="description",
        team="team",
        config=s3_config,
    )
    return FileStoreProvider(
        registrar=self,
        provider=provider,
        config=s3_config,
        store_type=s3_config.type(),
    )

get_snowflake(name)

Get a Snowflake provider. The returned object can be used to register additional resources.

Examples:

snowflake = ff.get_snowflake("snowflake-quickstart")
transactions = snowflake.register_table(
    name="transactions",
    variant="kaggle",
    description="Fraud Dataset From Kaggle",
    table="Transactions",  # This is the table's name in Postgres
)

Parameters:

Name	Type	Description	Default
name	str	Name of Snowflake provider to be retrieved	required

Returns:

Name	Type	Description
snowflake	OfflineSQLProvider	Provider

Source code in src/featureform/register.py

def get_snowflake(self, name):
    """Get a Snowflake provider. The returned object can be used to register additional resources.

    **Examples**:
    ``` py
    snowflake = ff.get_snowflake("snowflake-quickstart")
    transactions = snowflake.register_table(
        name="transactions",
        variant="kaggle",
        description="Fraud Dataset From Kaggle",
        table="Transactions",  # This is the table's name in Postgres
    )
    ```

    Args:
        name (str): Name of Snowflake provider to be retrieved

    Returns:
        snowflake (OfflineSQLProvider): Provider
    """
    mock_config = SnowflakeConfig(
        account="ff_fake",
        database="ff_fake",
        organization="ff_fake",
        username="ff_fake",
        password="ff_fake",
        schema="ff_fake",
    )
    mock_provider = Provider(
        name=name, function="OFFLINE", description="", team="", config=mock_config
    )
    return OfflineSQLProvider(self, mock_provider)

get_snowflake_legacy(name)

Get a Snowflake provider. The returned object can be used to register additional resources.

Examples:

snowflake = ff.get_snowflake_legacy("snowflake-quickstart")
transactions = snowflake.register_table(
    name="transactions",
    variant="kaggle",
    description="Fraud Dataset From Kaggle",
    table="Transactions",  # This is the table's name in Postgres
)

Parameters:

Name	Type	Description	Default
name	str	Name of Snowflake provider to be retrieved	required

Returns:

Name	Type	Description
snowflake_legacy	OfflineSQLProvider	Provider

Source code in src/featureform/register.py

def get_snowflake_legacy(self, name: str):
    """Get a Snowflake provider. The returned object can be used to register additional resources.

    **Examples**:
    ``` py
    snowflake = ff.get_snowflake_legacy("snowflake-quickstart")
    transactions = snowflake.register_table(
        name="transactions",
        variant="kaggle",
        description="Fraud Dataset From Kaggle",
        table="Transactions",  # This is the table's name in Postgres
    )
    ```

    Args:
        name (str): Name of Snowflake provider to be retrieved

    Returns:
        snowflake_legacy (OfflineSQLProvider): Provider
    """
    mock_config = SnowflakeConfig(
        account_locator="ff_fake",
        database="ff_fake",
        username="ff_fake",
        password="ff_fake",
        schema="ff_fake",
        warehouse="ff_fake",
        role="ff_fake",
    )
    mock_provider = Provider(
        name=name, function="OFFLINE", description="", team="", config=mock_config
    )
    return OfflineSQLProvider(self, mock_provider)

get_source(name, variant, local=False)

get_source() can be used to get a reference to an already registered primary source or transformation. The returned object can be used to register features and labels or be extended off of to create additional transformations.

Examples:

Registering a transformation from an existing source.

spark = ff.get_spark("prod-spark")
transactions = ff.get_source("transactions","kaggle")

@spark.df_transformation(inputs=[transactions]):
def customer_count(transactions):
    return transactions.groupBy("CustomerID").count()

Registering a feature from an existing source.

transactions = ff.get_source("transactions","kaggle")

transactions.register_resources(
    entity=user,
    entity_column="customerid",
    labels=[
        {"name": "fraudulent", "variant": "quickstart", "column": "isfraud", "type": "bool"},
    ],
)

Parameters:

Name	Type	Description	Default
name	str	Name of source to be retrieved	required
variant	str	Name of variant of source to be retrieved	required
local	bool	If localmode is being used	False

Returns:

Name	Type	Description
source	ColumnSourceRegistrar	Source

Source code in src/featureform/register.py

def get_source(self, name, variant, local=False):
    """
    get_source() can be used to get a reference to an already registered primary source or transformation.
    The returned object can be used to register features and labels or be extended off of to create additional
    transformations.

    **Examples**:

    Registering a transformation from an existing source.
    ``` py
    spark = ff.get_spark("prod-spark")
    transactions = ff.get_source("transactions","kaggle")

    @spark.df_transformation(inputs=[transactions]):
    def customer_count(transactions):
        return transactions.groupBy("CustomerID").count()
    ```

    Registering a feature from an existing source.
    ``` py
    transactions = ff.get_source("transactions","kaggle")

    transactions.register_resources(
        entity=user,
        entity_column="customerid",
        labels=[
            {"name": "fraudulent", "variant": "quickstart", "column": "isfraud", "type": "bool"},
        ],
    )
    ```

    Args:
        name (str): Name of source to be retrieved
        variant (str): Name of variant of source to be retrieved
        local (bool): If localmode is being used

    Returns:
        source (ColumnSourceRegistrar): Source
    """
    if local:
        raise Exception(
            "Localmode is not supported; please try featureform <= 1.12.0"
        )
    else:
        mock_definition = PrimaryData(location=SQLTable(name=""))
        mock_source = SourceVariant(
            created=None,
            name=name,
            variant=variant,
            definition=mock_definition,
            owner="",
            provider="",
            description="",
            tags=[],
            properties={},
        )
        return ColumnSourceRegistrar(self, mock_source)

get_spark(name)

Get a Spark provider. The returned object can be used to register additional resources.

Examples:

spark = ff.get_spark("spark-quickstart")
transactions = spark.register_file(
    name="transactions",
    variant="kaggle",
    description="Fraud Dataset From Kaggle",
    file_path="s3://bucket/path/to/file/transactions.parquet",  # This is the path to file
)

Parameters:

Name	Type	Description	Default
name	str	Name of Spark provider to be retrieved	required

Returns:

Name	Type	Description
spark	OfflineSQLProvider	Provider

Source code in src/featureform/register.py

def get_spark(self, name):
    """Get a Spark provider. The returned object can be used to register additional resources.

    **Examples**:
    ``` py
    spark = ff.get_spark("spark-quickstart")
    transactions = spark.register_file(
        name="transactions",
        variant="kaggle",
        description="Fraud Dataset From Kaggle",
        file_path="s3://bucket/path/to/file/transactions.parquet",  # This is the path to file
    )
    ```

    Args:
        name (str): Name of Spark provider to be retrieved

    Returns:
        spark (OfflineSQLProvider): Provider
    """
    mock_config = SparkConfig(
        executor_type="", executor_config={}, store_type="", store_config={}
    )
    mock_provider = Provider(
        name=name, function="OFFLINE", description="", team="", config=mock_config
    )
    return OfflineSparkProvider(self, mock_provider)

get_state()

Get the state of the resources to be registered.

Returns:

Name	Type	Description
resources	List[str]	List of resources to be registered ex. "{type} - {name} ({variant})"

Source code in src/featureform/register.py

def get_state(self):
    """
    Get the state of the resources to be registered.

    Returns:
        resources (List[str]): List of resources to be registered ex. "{type} - {name} ({variant})"
    """
    if len(self.__resources) == 0:
        return "No resources to be registered"

    resources = [["Type", "Name", "Variant"]]
    for resource in self.__resources:
        if hasattr(resource, "variant"):
            resources.append(
                [resource.__class__.__name__, resource.name, resource.variant]
            )
        else:
            resources.append([resource.__class__.__name__, resource.name, ""])

    print("Resources to be registered:")
    self.__print_state(resources)

ondemand_feature(fn=None, *, tags=[], properties={}, variant='', name='', owner='', description='')

On Demand Feature decorator.

Examples

import featureform as ff

@ff.ondemand_feature()
def avg_user_transactions(client, params, entities):
    pass

Parameters:

Name	Type	Description	Default
variant	str	Name of variant	''
name	str	Name of source	''
owner	Union[str, UserRegistrar]	Owner	''
description	str	Description of on demand feature	''
tags	List[str]	Optional grouping mechanism for resources	[]
properties	dict	Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
decorator	OnDemandFeature	decorator

Source code in src/featureform/register.py

def ondemand_feature(
    self,
    fn=None,
    *,
    tags: List[str] = [],
    properties: dict = {},
    variant: str = "",
    name: str = "",
    owner: Union[str, UserRegistrar] = "",
    description: str = "",
):
    """On Demand Feature decorator.

    **Examples**
    ```python
    import featureform as ff

    @ff.ondemand_feature()
    def avg_user_transactions(client, params, entities):
        pass
    ```

    Args:
        variant (str): Name of variant
        name (str): Name of source
        owner (Union[str, UserRegistrar]): Owner
        description (str): Description of on demand feature
        tags (List[str]): Optional grouping mechanism for resources
        properties (dict): Optional grouping mechanism for resources

    Returns:
        decorator (OnDemandFeature): decorator

    """

    if not isinstance(owner, str):
        owner = owner.name()
    if owner == "":
        owner = self.must_get_default_owner()
    if variant == "":
        variant = self.__run
    decorator = OnDemandFeatureVariant(
        name=name,
        variant=variant,
        owner=owner,
        description=description,
        tags=tags or [],
        properties=properties or {},
    )

    self.__resources.append(decorator)

    if fn is None:
        return decorator
    else:
        return decorator(fn)

register_bigquery(name, project_id, dataset_id, credentials, credentials_path='', description='', team='', tags=[], properties={})

Register a BigQuery provider.

Examples:

bigquery = ff.register_bigquery(
    name="bigquery-quickstart",
    description="A BigQuery deployment we created for the Featureform quickstart",
    project_id="quickstart-project",
    dataset_id="quickstart-dataset",
    credentials=GCPCredentials(...)
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of BigQuery provider to be registered	required
project_id	str	(Immutable) The Project name in GCP	required
dataset_id	str	(Immutable) The Dataset name in GCP under the Project Id	required
credentials	GCPCredentials	(Mutable) GCP credentials to access BigQuery	required
description	str	(Mutable) Description of BigQuery provider to be registered	''
team	str	(Mutable) Name of team	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	[]
properties	dict	(Mutable) Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
bigquery	OfflineSQLProvider	Provider

Source code in src/featureform/register.py

def register_bigquery(
    self,
    name: str,
    project_id: str,
    dataset_id: str,
    credentials: GCPCredentials,
    credentials_path: str = "",
    description: str = "",
    team: str = "",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a BigQuery provider.

    **Examples**:
    ```
    bigquery = ff.register_bigquery(
        name="bigquery-quickstart",
        description="A BigQuery deployment we created for the Featureform quickstart",
        project_id="quickstart-project",
        dataset_id="quickstart-dataset",
        credentials=GCPCredentials(...)
    )
    ```

    Args:
        name (str): (Immutable) Name of BigQuery provider to be registered
        project_id (str): (Immutable) The Project name in GCP
        dataset_id (str): (Immutable) The Dataset name in GCP under the Project Id
        credentials (GCPCredentials): (Mutable) GCP credentials to access BigQuery
        description (str): (Mutable) Description of BigQuery provider to be registered
        team (str): (Mutable) Name of team
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources

    Returns:
        bigquery (OfflineSQLProvider): Provider
    """
    tags, properties = set_tags_properties(tags, properties)

    config = BigQueryConfig(
        project_id=project_id,
        dataset_id=dataset_id,
        credentials=credentials,
    )
    provider = Provider(
        name=name,
        function="OFFLINE",
        description=description,
        team=team,
        config=config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return OfflineSQLProvider(self, provider)

register_blob_store(name, account_name, account_key, container_name, root_path, description='', team='', tags=None, properties=None)

Register an Azure Blob Store provider.

Azure Blob Storage can be used as the storage component for Spark or the Featureform Pandas Runner.

Examples:

blob = ff.register_blob_store(
    name="azure-quickstart",
    container_name="my_company_container"
    root_path="custom/path/in/container"
    account_name=<azure_account_name>
    account_key=<azure_account_key>
    description="An azure blob store provider to store offline and inference data"
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of Azure blob store to be registered	required
container_name	str	(Immutable) Azure container name	required
root_path	str	(Immutable) A custom path in container to store data	required
account_name	str	(Immutable) Azure account name	required
account_key	str	(Mutable) Secret azure account key	required
description	str	(Mutable) Description of Azure Blob provider to be registered	''
team	str	(Mutable) The name of the team registering the filestore	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	None
properties	dict	(Mutable) Optional grouping mechanism for resources	None

Returns:

Name	Type	Description
blob	StorageProvider	Provider has all the functionality of OnlineProvider

Source code in src/featureform/register.py

def register_blob_store(
    self,
    name: str,
    account_name: str,
    account_key: str,
    container_name: str,
    root_path: str,
    description: str = "",
    team: str = "",
    tags=None,
    properties=None,
):
    """Register an Azure Blob Store provider.

    Azure Blob Storage can be used as the storage component for Spark or the Featureform Pandas Runner.

    **Examples**:
    ```
    blob = ff.register_blob_store(
        name="azure-quickstart",
        container_name="my_company_container"
        root_path="custom/path/in/container"
        account_name=<azure_account_name>
        account_key=<azure_account_key>
        description="An azure blob store provider to store offline and inference data"
    )
    ```

    Args:
        name (str): (Immutable) Name of Azure blob store to be registered
        container_name (str): (Immutable) Azure container name
        root_path (str): (Immutable) A custom path in container to store data
        account_name (str): (Immutable) Azure account name
        account_key (str):  (Mutable) Secret azure account key
        description (str): (Mutable) Description of Azure Blob provider to be registered
        team (str): (Mutable) The name of the team registering the filestore
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources

    Returns:
        blob (StorageProvider): Provider
            has all the functionality of OnlineProvider
    """

    tags, properties = set_tags_properties(tags, properties)

    container_name = container_name.replace("abfss://", "")
    if "/" in container_name:
        raise ValueError(
            "container_name cannot contain '/'. container_name should be the name of the Azure Blobstore container only."
        )

    azure_config = AzureFileStoreConfig(
        account_name=account_name,
        account_key=account_key,
        container_name=container_name,
        root_path=root_path,
    )
    config = OnlineBlobConfig(
        store_type="AZURE", store_config=azure_config.config()
    )

    provider = Provider(
        name=name,
        function="ONLINE",
        description=description,
        team=team,
        config=config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return FileStoreProvider(self, provider, azure_config, "AZURE")

register_cassandra(name, host, port, username, password, keyspace, consistency='THREE', replication=3, description='', team='', tags=[], properties={})

Register a Cassandra provider.

Examples:

cassandra = ff.register_cassandra(
        name = "cassandra",
        description = "Example inference store",
        team = "Featureform",
        host = "0.0.0.0",
        port = 9042,
        username = "cassandra",
        password = "cassandra",
        consistency = "THREE",
        replication = 3
    )

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of Cassandra provider to be registered	required
host	str	(Immutable) DNS name of Cassandra	required
port	str	(Mutable) Port	required
username	str	(Mutable) Username	required
password	str	(Mutable) Password	required
consistency	str	(Mutable) Consistency	'THREE'
replication	int	(Mutable) Replication	3
description	str	(Mutable) Description of Cassandra provider to be registered	''
team	str	(Mutable) Name of team	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	[]
properties	dict	(Mutable) Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
cassandra	OnlineProvider	Provider

Source code in src/featureform/register.py

def register_cassandra(
    self,
    name: str,
    host: str,
    port: int,
    username: str,
    password: str,
    keyspace: str,
    consistency: str = "THREE",
    replication: int = 3,
    description: str = "",
    team: str = "",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a Cassandra provider.

    **Examples**:
    ```
    cassandra = ff.register_cassandra(
            name = "cassandra",
            description = "Example inference store",
            team = "Featureform",
            host = "0.0.0.0",
            port = 9042,
            username = "cassandra",
            password = "cassandra",
            consistency = "THREE",
            replication = 3
        )
    ```

    Args:
        name (str): (Immutable) Name of Cassandra provider to be registered
        host (str): (Immutable) DNS name of Cassandra
        port (str): (Mutable) Port
        username (str): (Mutable) Username
        password (str): (Mutable) Password
        consistency (str): (Mutable) Consistency
        replication (int): (Mutable) Replication
        description (str): (Mutable) Description of Cassandra provider to be registered
        team (str): (Mutable) Name of team
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources

    Returns:
        cassandra (OnlineProvider): Provider
    """
    config = CassandraConfig(
        host=host,
        port=port,
        username=username,
        password=password,
        keyspace=keyspace,
        consistency=consistency,
        replication=replication,
    )
    provider = Provider(
        name=name,
        function="ONLINE",
        description=description,
        team=team,
        config=config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return OnlineProvider(self, provider)

register_clickhouse(name, host, user, password, database, port=9000, description='', team='', ssl=False, tags=[], properties={})

Register a ClickHouse provider.

Examples:

clickhouse = ff.register_clickhouse(
    name="clickhouse-quickstart",
    description="A ClickHouse deployment we created for the Featureform quickstart",
    host="quickstart-clickhouse",  # The internal dns name for clickhouse
    port=9000,
    user="default",
    password="", #pragma: allowlist secret
    database="default"
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of ClickHouse provider to be registered	required
host	str	(Immutable) Hostname for ClickHouse	required
database	str	(Immutable) ClickHouse database	required
port	int	(Mutable) Port	9000
ssl	bool	(Mutable) Enable SSL	False
user	str	(Mutable) User	required
password	str	(Mutable) ClickHouse password	required
description	str	(Mutable) Description of ClickHouse provider to be registered	''
team	str	(Mutable) Name of team	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	[]
properties	dict	(Mutable) Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
clickhouse	OfflineSQLProvider	Provider

Source code in src/featureform/register.py

def register_clickhouse(
    self,
    name: str,
    host: str,
    user: str,
    password: str,
    database: str,
    port: int = 9000,
    description: str = "",
    team: str = "",
    ssl: bool = False,
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a ClickHouse provider.

    **Examples**:
    ```
    clickhouse = ff.register_clickhouse(
        name="clickhouse-quickstart",
        description="A ClickHouse deployment we created for the Featureform quickstart",
        host="quickstart-clickhouse",  # The internal dns name for clickhouse
        port=9000,
        user="default",
        password="", #pragma: allowlist secret
        database="default"
    )
    ```

    Args:
        name (str): (Immutable) Name of ClickHouse provider to be registered
        host (str): (Immutable) Hostname for ClickHouse
        database (str): (Immutable) ClickHouse database
        port (int): (Mutable) Port
        ssl (bool): (Mutable) Enable SSL
        user (str): (Mutable) User
        password (str): (Mutable) ClickHouse password
        description (str): (Mutable) Description of ClickHouse provider to be registered
        team (str): (Mutable) Name of team
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources

    Returns:
        clickhouse (OfflineSQLProvider): Provider
    """
    tags, properties = set_tags_properties(tags, properties)
    config = ClickHouseConfig(
        host=host,
        port=port,
        database=database,
        user=user,
        password=password,
        ssl=ssl,
    )
    provider = Provider(
        name=name,
        function="OFFLINE",
        description=description,
        team=team,
        config=config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return OfflineSQLProvider(self, provider)

register_column_resources(source, entity, entity_column, owner='', inference_store='', features=None, labels=None, timestamp_column='', description='', schedule='', client_object=None)

Create features and labels from a source. Used in the register_resources function.

Parameters:

Name	Type	Description	Default
source	Union[NameVariant, SourceRegistrar, SQLTransformationDecorator]	Source of features, labels, entity	required
entity	Union[str, EntityRegistrar]	Entity	required
entity_column	str	Column of entity in source	required
owner	Union[str, UserRegistrar]	Owner	''
inference_store	Union[str, OnlineProvider]	Online provider	''
features	List[ColumnMapping]	List of ColumnMapping objects (dictionaries containing the keys: name, variant, column, resource_type)	None
labels	List[ColumnMapping]	List of ColumnMapping objects (dictionaries containing the keys: name, variant, column, resource_type)	None
description	str	Description	''
schedule	str	Kubernetes CronJob schedule string (" * * * ")	''

Returns:

Name	Type	Description
resource	ResourceRegistrar	resource

Source code in src/featureform/register.py

def register_column_resources(
    self,
    source: Union[
        NameVariant,
        SourceRegistrar,
        SQLTransformationDecorator,
        DFTransformationDecorator,
    ],
    entity: Union[str, EntityRegistrar],
    entity_column: str,
    owner: Union[str, UserRegistrar] = "",
    inference_store: Union[str, OnlineProvider, FileStoreProvider] = "",
    features: List[ColumnMapping] = None,
    labels: List[ColumnMapping] = None,
    timestamp_column: str = "",
    description: str = "",
    schedule: str = "",
    client_object=None,
):
    """Create features and labels from a source. Used in the register_resources function.

    Args:
        source (Union[NameVariant, SourceRegistrar, SQLTransformationDecorator]): Source of features, labels, entity
        entity (Union[str, EntityRegistrar]): Entity
        entity_column (str): Column of entity in source
        owner (Union[str, UserRegistrar]): Owner
        inference_store (Union[str, OnlineProvider]): Online provider
        features (List[ColumnMapping]): List of ColumnMapping objects (dictionaries containing the keys: name, variant, column, resource_type)
        labels (List[ColumnMapping]): List of ColumnMapping objects (dictionaries containing the keys: name, variant, column, resource_type)
        description (str): Description
        schedule (str): Kubernetes CronJob schedule string ("* * * * *")

    Returns:
        resource (ResourceRegistrar): resource
    """

    if (
        type(inference_store) == FileStoreProvider
        and inference_store.store_type() in NON_INFERENCE_STORES
    ):
        raise Exception(
            f"cannot use '{inference_store.store_type()}' as an inference store."
        )

    if features is None:
        features = []
    if labels is None:
        labels = []
    if len(features) == 0 and len(labels) == 0:
        raise ValueError("No features or labels set")
    if isinstance(source, tuple) and source[1] == "":
        source = source[0], self.__run
    if not isinstance(entity, str):
        entity = entity.name()
    if not isinstance(inference_store, str):
        inference_store = inference_store.name()
    if not isinstance(owner, str):
        owner = owner.name()
    if owner == "":
        owner = self.must_get_default_owner()
    feature_resources = []
    label_resources = []
    for feature in features:
        variant = feature.get("variant", "")
        if variant == "":
            variant = self.__run
        if not ScalarType.has_value(feature["type"]) and not isinstance(
            feature["type"], ScalarType
        ):
            raise ValueError(
                f"Invalid type for feature {feature['name']} ({variant}). Must be a ScalarType or one of {ScalarType.get_values()}"
            )
        if isinstance(feature["type"], ScalarType):
            feature["type"] = feature["type"].value
        desc = feature.get("description", "")
        feature_tags = feature.get("tags", [])
        feature_properties = feature.get("properties", {})
        additional_Parameters = self._get_additional_parameters(ondemand_feature)
        is_embedding = feature.get("is_embedding", False)
        dims = feature.get("dims", 0)
        value_type = ScalarType(feature["type"])
        if dims > 0:
            value_type = VectorType(value_type, dims, is_embedding)
        resource = FeatureVariant(
            created=None,
            name=feature["name"],
            variant=variant,
            source=source,
            value_type=value_type,
            entity=entity,
            owner=owner,
            provider=inference_store,
            description=desc,
            schedule=schedule,
            location=ResourceColumnMapping(
                entity=entity_column,
                value=feature["column"],
                timestamp=timestamp_column,
            ),
            tags=feature_tags,
            properties=feature_properties,
            additional_parameters=additional_Parameters,
        )
        self.__resources.append(resource)
        self.map_client_object_to_resource(client_object, resource)
        feature_resources.append(resource)

    for label in labels:
        variant = label.get("variant", "")
        if variant == "":
            variant = self.__run
        if not ScalarType.has_value(label["type"]) and not isinstance(
            label["type"], ScalarType
        ):
            raise ValueError(
                f"Invalid type for label {label['name']} ({variant}). Must be a ScalarType or one of {ScalarType.get_values()}"
            )
        if isinstance(label["type"], ScalarType):
            label["type"] = label["type"].value
        desc = label.get("description", "")
        label_tags = label.get("tags", [])
        label_properties = label.get("properties", {})
        resource = LabelVariant(
            name=label["name"],
            variant=variant,
            source=source,
            value_type=label["type"],
            entity=entity,
            owner=owner,
            provider=inference_store,
            description=desc,
            location=ResourceColumnMapping(
                entity=entity_column,
                value=label["column"],
                timestamp=timestamp_column,
            ),
            tags=label_tags,
            properties=label_properties,
        )
        self.__resources.append(resource)
        self.map_client_object_to_resource(client_object, resource)
        label_resources.append(resource)
    return ResourceRegistrar(self, features, labels)

register_df_transformation(name, query, provider, variant='', owner='', description='', inputs=[], schedule='', args=None, tags=[], properties={})

Register a Dataframe transformation source.

Parameters:

Name	Type	Description	Default
name	str	Name of source	required
variant	str	Name of variant	''
query	str	SQL query	required
provider	Union[str, OfflineProvider]	Provider	required
name	str	Name of source	required
owner	Union[str, UserRegistrar]	Owner	''
description	str	Description of SQL transformation	''
inputs	list	Inputs to transformation	[]
schedule	str	Kubernetes CronJob schedule string (" * * * ")	''
args	K8sArgs	Additional transformation arguments	None
tags	List[str]	Optional grouping mechanism for resources	[]
properties	dict	Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
source	ColumnSourceRegistrar	Source

Source code in src/featureform/register.py

def register_df_transformation(
    self,
    name: str,
    query: str,
    provider: Union[str, OfflineProvider],
    variant: str = "",
    owner: Union[str, UserRegistrar] = "",
    description: str = "",
    inputs: list = [],
    schedule: str = "",
    args: K8sArgs = None,
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a Dataframe transformation source.

    Args:
        name (str): Name of source
        variant (str): Name of variant
        query (str): SQL query
        provider (Union[str, OfflineProvider]): Provider
        name (str): Name of source
        owner (Union[str, UserRegistrar]): Owner
        description (str): Description of SQL transformation
        inputs (list): Inputs to transformation
        schedule (str): Kubernetes CronJob schedule string ("* * * * *")
        args (K8sArgs): Additional transformation arguments
        tags (List[str]): Optional grouping mechanism for resources
        properties (dict): Optional grouping mechanism for resources

    Returns:
        source (ColumnSourceRegistrar): Source
    """
    if not isinstance(owner, str):
        owner = owner.name()
    if owner == "":
        owner = self.must_get_default_owner()
    if variant == "":
        variant = self.__run
    if not isinstance(provider, str):
        provider = provider.name()
    source = SourceVariant(
        created=None,
        name=name,
        variant=variant,
        definition=DFTransformation(query, inputs, args),
        owner=owner,
        schedule=schedule,
        provider=provider,
        description=description,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(source)
    return ColumnSourceRegistrar(self, source)

register_dynamodb(name, credentials, region, should_import_from_s3=False, description='', team='', tags=[], properties={})

Register a DynamoDB provider.

Examples:

dynamodb = ff.register_dynamodb(
    name="dynamodb-quickstart",
    description="A Dynamodb deployment we created for the Featureform quickstart",
    credentials=aws_creds,
    region="us-east-1"
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of DynamoDB provider to be registered	required
region	str	(Immutable) Region to create dynamo tables	required
credentials	AWSCredentials	(Mutable) AWS credentials with permissions to create DynamoDB tables	required
should_import_from_s3	bool	(Mutable) Determines whether feature materialization will occur via a direct import of data from S3 to new table (see docs for details)	False
description	str	(Mutable) Description of DynamoDB provider to be registered	''
team	str	(Mutable) Name of team	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	[]
properties	dict	(Mutable) Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
dynamodb	OnlineProvider	Provider

Source code in src/featureform/register.py

def register_dynamodb(
    self,
    name: str,
    credentials: AWSCredentials,
    region: str,
    should_import_from_s3: bool = False,
    description: str = "",
    team: str = "",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a DynamoDB provider.

    **Examples**:
    ```
    dynamodb = ff.register_dynamodb(
        name="dynamodb-quickstart",
        description="A Dynamodb deployment we created for the Featureform quickstart",
        credentials=aws_creds,
        region="us-east-1"
    )
    ```

    Args:
        name (str): (Immutable) Name of DynamoDB provider to be registered
        region (str): (Immutable) Region to create dynamo tables
        credentials (AWSCredentials): (Mutable) AWS credentials with permissions to create DynamoDB tables
        should_import_from_s3 (bool): (Mutable) Determines whether feature materialization will occur via a direct import of data from S3 to new table (see [docs](https://docs.aws.amazon.com/amazondynamodb/latest/developerguide/S3DataImport.HowItWorks.html) for details)
        description (str): (Mutable) Description of DynamoDB provider to be registered
        team (str): (Mutable) Name of team
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources

    Returns:
        dynamodb (OnlineProvider): Provider
    """
    tags, properties = set_tags_properties(tags, properties)
    config = DynamodbConfig(
        access_key=credentials.access_key,
        secret_key=credentials.secret_key,
        region=region,
        should_import_from_s3=should_import_from_s3,
    )
    provider = Provider(
        name=name,
        function="ONLINE",
        description=description,
        team=team,
        config=config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return OnlineProvider(self, provider)

register_entity(name, description='', tags=[], properties={})

Register an entity.

Examples:

    user = ff.register_entity("user")

Parameters:

Name	Type	Description	Default
name	str	Name of entity to be registered	required
description	str	Description of entity to be registered	''
tags	List[str]	Optional grouping mechanism for resources	[]
properties	dict	Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
entity	EntityRegistrar	Entity

Source code in src/featureform/register.py

def register_entity(
    self,
    name: str,
    description: str = "",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register an entity.

    **Examples**:
    ``` py
        user = ff.register_entity("user")
    ```

    Args:
        name (str): Name of entity to be registered
        description (str): Description of entity to be registered
        tags (List[str]): Optional grouping mechanism for resources
        properties (dict): Optional grouping mechanism for resources

    Returns:
        entity (EntityRegistrar): Entity
    """
    entity = Entity(
        name=name,
        description=description,
        status="",
        tags=tags,
        properties=properties,
    )
    self.__resources.append(entity)
    return EntityRegistrar(self, entity)

register_firestore(name, collection, project_id, credentials, credentials_path='', description='', team='', tags=[], properties={})

Register a Firestore provider.

Examples:

firestore = ff.register_firestore(
    name="firestore-quickstart",
    description="A Firestore deployment we created for the Featureform quickstart",
    project_id="quickstart-project",
    collection="quickstart-collection",
    credentials=ff.GCPCredentials(...)
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of Firestore provider to be registered	required
project_id	str	(Immutable) The Project name in GCP	required
collection	str	(Immutable) The Collection name in Firestore under the given project ID	required
credentials	GCPCredentials	(Mutable) GCP credentials to access Firestore	required
description	str	(Mutable) Description of Firestore provider to be registered	''
team	str	(Mutable) The name of the team registering the filestore	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	[]
properties	dict	(Mutable) Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
firestore	OfflineSQLProvider	Provider

Source code in src/featureform/register.py

def register_firestore(
    self,
    name: str,
    collection: str,
    project_id: str,
    credentials: GCPCredentials,
    credentials_path: str = "",
    description: str = "",
    team: str = "",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a Firestore provider.

    **Examples**:
    ```
    firestore = ff.register_firestore(
        name="firestore-quickstart",
        description="A Firestore deployment we created for the Featureform quickstart",
        project_id="quickstart-project",
        collection="quickstart-collection",
        credentials=ff.GCPCredentials(...)
    )
    ```

    Args:
        name (str): (Immutable) Name of Firestore provider to be registered
        project_id (str): (Immutable) The Project name in GCP
        collection (str): (Immutable) The Collection name in Firestore under the given project ID
        credentials (GCPCredentials): (Mutable) GCP credentials to access Firestore
        description (str): (Mutable) Description of Firestore provider to be registered
        team (str): (Mutable) The name of the team registering the filestore
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources

    Returns:
        firestore (OfflineSQLProvider): Provider
    """
    tags, properties = set_tags_properties(tags, properties)
    config = FirestoreConfig(
        collection=collection,
        project_id=project_id,
        credentials=credentials,
    )
    provider = Provider(
        name=name,
        function="ONLINE",
        description=description,
        team=team,
        config=config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return OnlineProvider(self, provider)

register_gcs(name, bucket_name, root_path, credentials, description='', team='', tags=[], properties={})

Register a GCS store provider.

Examples:

gcs = ff.register_gcs(
    name="gcs-quickstart",
    credentials=ff.GCPCredentials(...),
    bucket_name="bucket_name",
    root_path="featureform/path/",
    description="An gcs store provider to store offline"
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of GCS store to be registered	required
bucket_name	str	(Immutable) The bucket name	required
root_path	str	(Immutable) Custom path to be used by featureform	required
credentials	GCPCredentials	(Mutable) GCP credentials to access the bucket	required
description	str	(Mutable) Description of GCS provider to be registered	''
team	str	(Mutable) The name of the team registering the filestore	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	[]
properties	dict	(Mutable) Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
gcs	FileStoreProvider	Provider has all the functionality of OfflineProvider

Source code in src/featureform/register.py

def register_gcs(
    self,
    name: str,
    bucket_name: str,
    root_path: str,
    credentials: GCPCredentials,
    description: str = "",
    team: str = "",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a GCS store provider.

    **Examples**:
    ```
    gcs = ff.register_gcs(
        name="gcs-quickstart",
        credentials=ff.GCPCredentials(...),
        bucket_name="bucket_name",
        root_path="featureform/path/",
        description="An gcs store provider to store offline"
    )
    ```

    Args:
        name (str): (Immutable) Name of GCS store to be registered
        bucket_name (str): (Immutable) The bucket name
        root_path (str): (Immutable) Custom path to be used by featureform
        credentials (GCPCredentials): (Mutable) GCP credentials to access the bucket
        description (str): (Mutable) Description of GCS provider to be registered
        team (str): (Mutable) The name of the team registering the filestore
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources

    Returns:
        gcs (FileStoreProvider): Provider
            has all the functionality of OfflineProvider
    """
    tags, properties = set_tags_properties(tags, properties)

    if bucket_name == "":
        raise ValueError("bucket_name is required and cannot be empty string")

    bucket_name = bucket_name.replace("gs://", "")
    if "/" in bucket_name:
        raise ValueError(
            "bucket_name cannot contain '/'. bucket_name should be the name of the GCS bucket only."
        )

    gcs_config = GCSFileStoreConfig(
        bucket_name=bucket_name, bucket_path=root_path, credentials=credentials
    )
    provider = Provider(
        name=name,
        function="OFFLINE",
        description=description,
        team=team,
        config=gcs_config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return FileStoreProvider(self, provider, gcs_config, gcs_config.type())

register_hdfs(name, host, port, username='', path='', description='', team='', tags=[], properties={})

Register a HDFS store provider.

This has the functionality of an offline store and can be used as a parameter to a k8s or spark provider

Examples:

hdfs = ff.register_hdfs(
    name="hdfs-quickstart",
    host="<host>",
    port="<port>",
    path="<path>",
    username="<username>",
    description="An hdfs store provider to store offline"
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of HDFS store to be registered	required
host	str	(Immutable) The hostname for HDFS	required
path	str	(Immutable) A storage path within HDFS	''
port	str	(Mutable) The IPC port for the Namenode for HDFS. (Typically 8020 or 9000)	required
username	str	(Mutable) A Username for HDFS	''
description	str	(Mutable) Description of HDFS provider to be registered	''
team	str	(Mutable) The name of the team registering HDFS	''

Returns:

Name	Type	Description
hdfs	FileStoreProvider	Provider

Source code in src/featureform/register.py

def register_hdfs(
    self,
    name: str,
    host: str,
    port: str,
    username: str = "",
    path: str = "",
    description: str = "",
    team: str = "",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a HDFS store provider.

    This has the functionality of an offline store and can be used as a parameter
    to a k8s or spark provider

    **Examples**:
    ```
    hdfs = ff.register_hdfs(
        name="hdfs-quickstart",
        host="<host>",
        port="<port>",
        path="<path>",
        username="<username>",
        description="An hdfs store provider to store offline"
    )
    ```

    Args:
        name (str): (Immutable) Name of HDFS store to be registered
        host (str): (Immutable) The hostname for HDFS
        path (str): (Immutable) A storage path within HDFS
        port (str): (Mutable) The IPC port for the Namenode for HDFS. (Typically 8020 or 9000)
        username (str): (Mutable) A Username for HDFS
        description (str): (Mutable) Description of HDFS provider to be registered
        team (str): (Mutable) The name of the team registering HDFS

    Returns:
        hdfs (FileStoreProvider): Provider
    """

    hdfs_config = HDFSConfig(host=host, port=port, path=path, username=username)

    provider = Provider(
        name=name,
        function="OFFLINE",
        description=description,
        team=team,
        config=hdfs_config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return FileStoreProvider(self, provider, hdfs_config, hdfs_config.type())

register_k8s(name, store, description='', team='', docker_image='', tags=[], properties={})

Register an offline store provider to run on Featureform's own k8s deployment. Examples:

spark = ff.register_k8s(
    name="k8s",
    store=AzureBlobStore(),
    docker_image="my-repo/image:version"
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of provider	required
store	FileStoreProvider	(Mutable) Reference to registered file store provider	required
docker_image	str	(Mutable) A custom docker image using the base image featureformcom/k8s_runner	''
description	str	(Mutable) Description of primary data to be registered	''
team	str	(Mutable) A string parameter describing the team that owns the provider	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	[]
properties	dict	(Mutable) Optional grouping mechanism for resources	{}

Source code in src/featureform/register.py

def register_k8s(
    self,
    name: str,
    store: FileStoreProvider,
    description: str = "",
    team: str = "",
    docker_image: str = "",
    tags: List[str] = [],
    properties: dict = {},
):
    """
    Register an offline store provider to run on Featureform's own k8s deployment.
    **Examples**:
    ```
    spark = ff.register_k8s(
        name="k8s",
        store=AzureBlobStore(),
        docker_image="my-repo/image:version"
    )
    ```

    Args:
        name (str): (Immutable) Name of provider
        store (FileStoreProvider): (Mutable) Reference to registered file store provider
        docker_image (str): (Mutable) A custom docker image using the base image featureformcom/k8s_runner
        description (str): (Mutable) Description of primary data to be registered
        team (str): (Mutable) A string parameter describing the team that owns the provider
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources
    """

    tags, properties = set_tags_properties(tags, properties)
    config = K8sConfig(
        store_type=store.store_type(),
        store_config=store.config(),
        docker_image=docker_image,
    )

    provider = Provider(
        name=name,
        function="OFFLINE",
        description=description,
        team=team,
        config=config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return OfflineK8sProvider(self, provider)

register_model(name, tags=[], properties={})

Register a model.

Parameters:

Name	Type	Description	Default
name	str	Model to be registered	required
tags	List[str]	Optional grouping mechanism for resources	[]
properties	dict	Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
ModelRegistrar	Model	Model

Source code in src/featureform/register.py

def register_model(
    self, name: str, tags: List[str] = [], properties: dict = {}
) -> Model:
    """Register a model.

    Args:
        name (str): Model to be registered
        tags (List[str]): Optional grouping mechanism for resources
        properties (dict): Optional grouping mechanism for resources

    Returns:
        ModelRegistrar: Model
    """
    model = Model(name, description="", tags=tags, properties=properties)
    self.__resources.append(model)
    return model

register_mongodb(name, username, password, database, host, port, throughput=1000, description='', team='', tags=[], properties={})

Register a MongoDB provider.

Examples:

mongodb = ff.register_mongodb(
    name="mongodb-quickstart",
    description="A MongoDB deployment",
    username="my_username",
    password="myPassword",
    database="featureform_database"
    host="my-mongodb.host.com",
    port="10225",
    throughput=10000
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of MongoDB provider to be registered	required
database	str	(Immutable) MongoDB database	required
host	str	(Immutable) MongoDB hostname	required
port	str	(Immutable) MongoDB port	required
username	str	(Mutable) MongoDB username	required
password	str	(Mutable) MongoDB password	required
throughput	int	(Mutable) The maximum RU limit for autoscaling in CosmosDB	1000
description	str	(Mutable) Description of MongoDB provider to be registered	''
team	str	(Mutable) Name of team	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	[]
properties	dict	(Mutable) Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
mongodb	OnlineProvider	Provider

Source code in src/featureform/register.py

def register_mongodb(
    self,
    name: str,
    username: str,
    password: str,
    database: str,
    host: str,
    port: str,
    throughput: int = 1000,
    description: str = "",
    team: str = "",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a MongoDB provider.

    **Examples**:
    ```
    mongodb = ff.register_mongodb(
        name="mongodb-quickstart",
        description="A MongoDB deployment",
        username="my_username",
        password="myPassword",
        database="featureform_database"
        host="my-mongodb.host.com",
        port="10225",
        throughput=10000
    )
    ```

    Args:
        name (str): (Immutable) Name of MongoDB provider to be registered
        database (str): (Immutable) MongoDB database
        host (str): (Immutable) MongoDB hostname
        port (str): (Immutable) MongoDB port
        username (str): (Mutable) MongoDB username
        password (str): (Mutable) MongoDB password
        throughput (int): (Mutable) The maximum RU limit for autoscaling in CosmosDB
        description (str): (Mutable) Description of MongoDB provider to be registered
        team (str): (Mutable) Name of team
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources

    Returns:
        mongodb (OnlineProvider): Provider
    """
    tags, properties = set_tags_properties(tags, properties)
    config = MongoDBConfig(
        username=username,
        password=password,
        host=host,
        port=port,
        database=database,
        throughput=throughput,
    )
    provider = Provider(
        name=name,
        function="ONLINE",
        description=description,
        team=team,
        config=config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return OnlineProvider(self, provider)

register_pinecone(name, project_id, environment, api_key, description='', team='', tags=[], properties={})

Register a Pinecone provider.

Examples:

pinecone = ff.register_pinecone(
    name="pinecone-quickstart",
    project_id="2g13ek7",
    environment="us-west4-gcp-free",
    api_key="xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of Pinecone provider to be registered	required
project_id	str	(Immutable) Pinecone project id	required
environment	str	(Immutable) Pinecone environment	required
api_key	str	(Mutable) Pinecone api key	required
description	str	(Mutable) Description of Pinecone provider to be registered	''
team	str	(Mutable) Name of team	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	[]
properties	dict	(Mutable) Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
pinecone	OnlineProvider	Provider

Source code in src/featureform/register.py

def register_pinecone(
    self,
    name: str,
    project_id: str,
    environment: str,
    api_key: str,
    description: str = "",
    team: str = "",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a Pinecone provider.

    **Examples**:
    ```
    pinecone = ff.register_pinecone(
        name="pinecone-quickstart",
        project_id="2g13ek7",
        environment="us-west4-gcp-free",
        api_key="xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
    )
    ```

    Args:
        name (str): (Immutable) Name of Pinecone provider to be registered
        project_id (str): (Immutable) Pinecone project id
        environment (str): (Immutable) Pinecone environment
        api_key (str): (Mutable) Pinecone api key
        description (str): (Mutable) Description of Pinecone provider to be registered
        team (str): (Mutable) Name of team
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources

    Returns:
        pinecone (OnlineProvider): Provider
    """

    tags, properties = set_tags_properties(tags, properties)
    config = PineconeConfig(
        project_id=project_id, environment=environment, api_key=api_key
    )
    provider = Provider(
        name=name,
        function="ONLINE",
        description=description,
        team=team,
        config=config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return OnlineProvider(self, provider)

register_postgres(name, host, user, password, database, port='5432', description='', team='', sslmode='disable', tags=[], properties={})

Register a Postgres provider.

Examples:

postgres = ff.register_postgres(
    name="postgres-quickstart",
    description="A Postgres deployment we created for the Featureform quickstart",
    host="quickstart-postgres",  # The internal dns name for postgres
    port="5432",
    user="postgres",
    password="password", #pragma: allowlist secret
    database="postgres"
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of Postgres provider to be registered	required
host	str	(Immutable) Hostname for Postgres	required
database	str	(Immutable) Database	required
port	str	(Mutable) Port	'5432'
user	str	(Mutable) User	required
password	str	(Mutable) Password	required
sslmode	str	(Mutable) SSL mode	'disable'
description	str	(Mutable) Description of Postgres provider to be registered	''
team	str	(Mutable) Name of team	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	[]
properties	dict	(Mutable) Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
postgres	OfflineSQLProvider	Provider

Source code in src/featureform/register.py

def register_postgres(
    self,
    name: str,
    host: str,
    user: str,
    password: str,
    database: str,
    port: str = "5432",
    description: str = "",
    team: str = "",
    sslmode: str = "disable",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a Postgres provider.

    **Examples**:
    ```
    postgres = ff.register_postgres(
        name="postgres-quickstart",
        description="A Postgres deployment we created for the Featureform quickstart",
        host="quickstart-postgres",  # The internal dns name for postgres
        port="5432",
        user="postgres",
        password="password", #pragma: allowlist secret
        database="postgres"
    )
    ```

    Args:
        name (str): (Immutable) Name of Postgres provider to be registered
        host (str): (Immutable) Hostname for Postgres
        database (str): (Immutable) Database
        port (str): (Mutable) Port
        user (str): (Mutable) User
        password (str): (Mutable) Password
        sslmode (str): (Mutable) SSL mode
        description (str): (Mutable) Description of Postgres provider to be registered
        team (str): (Mutable) Name of team
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources

    Returns:
        postgres (OfflineSQLProvider): Provider
    """
    tags, properties = set_tags_properties(tags, properties)
    config = PostgresConfig(
        host=host,
        port=port,
        database=database,
        user=user,
        password=password,
        sslmode=sslmode,
    )
    provider = Provider(
        name=name,
        function="OFFLINE",
        description=description,
        team=team,
        config=config,
        tags=tags or [],
        properties=properties or {},
    )

    self.__resources.append(provider)
    return OfflineSQLProvider(self, provider)

register_primary_data(name, location, provider, tags, properties, variant='', owner='', description='')

Register a primary data source.

Parameters:

Name	Type	Description	Default
name	str	Name of source	required
variant	str	Name of variant	''
location	Location	Location of primary data	required
provider	Union[str, OfflineProvider]	Provider	required
owner	Union[str, UserRegistrar]	Owner	''
description	str	Description of primary data to be registered	''

Returns:

Name	Type	Description
source	ColumnSourceRegistrar	Source

Source code in src/featureform/register.py

def register_primary_data(
    self,
    name: str,
    location: Location,
    provider: Union[str, OfflineProvider],
    tags: List[str],
    properties: dict,
    variant: str = "",
    owner: Union[str, UserRegistrar] = "",
    description: str = "",
):
    """Register a primary data source.

    Args:
        name (str): Name of source
        variant (str): Name of variant
        location (Location): Location of primary data
        provider (Union[str, OfflineProvider]): Provider
        owner (Union[str, UserRegistrar]): Owner
        description (str): Description of primary data to be registered

    Returns:
        source (ColumnSourceRegistrar): Source
    """
    if not isinstance(owner, str):
        owner = owner.name()
    if owner == "":
        owner = self.must_get_default_owner()
    if variant == "":
        variant = self.__run
    if not isinstance(provider, str):
        provider = provider.name()
    source = SourceVariant(
        created=None,
        name=name,
        variant=variant,
        definition=PrimaryData(location=location),
        owner=owner,
        provider=provider,
        description=description,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(source)
    column_source_registrar = ColumnSourceRegistrar(self, source)
    self.map_client_object_to_resource(column_source_registrar, source)
    return column_source_registrar

register_qdrant(name, grpc_host, api_key='', use_tls=False, description='', team='', tags=[], properties={})

Register a Qdrant provider.

Examples:

qdrant = ff.register_qdrant(
    name="qdrant-quickstart",
    grpc_host="xyz-example.eu-central.aws.cloud.qdrant.io:6334",
    api_key="<API KEY>",
    use_tls=True,
    description="A Qdrant project for using embeddings in Featureform"
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of Qdrant provider to be registered	required
url	str	(Immutable) gRPC host of the Qdrant cluster, either in the cloud or via local deployment.	required
api_key	str	(Mutable) Qdrant API key.	''
use_tls	bool	(Immutable) Whether to use TLS for the connection.	False
description	str	(Mutable) Description of Qdrant provider to be registered	''
team	str	(Mutable) Name of team	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	[]
properties	dict	(Mutable) Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
qdrant	OnlineProvider	Provider

Source code in src/featureform/register.py

def register_qdrant(
    self,
    name: str,
    grpc_host: str,
    api_key: str = "",
    use_tls: bool = False,
    description: str = "",
    team: str = "",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a Qdrant provider.

    **Examples**:
    ```
    qdrant = ff.register_qdrant(
        name="qdrant-quickstart",
        grpc_host="xyz-example.eu-central.aws.cloud.qdrant.io:6334",
        api_key="<API KEY>",
        use_tls=True,
        description="A Qdrant project for using embeddings in Featureform"
    )
    ```

    Args:
        name (str): (Immutable) Name of Qdrant provider to be registered
        url (str): (Immutable) gRPC host of the Qdrant cluster, either in the cloud or via local deployment.
        api_key (str): (Mutable) Qdrant API key.
        use_tls (bool): (Immutable) Whether to use TLS for the connection.
        description (str): (Mutable) Description of Qdrant provider to be registered
        team (str): (Mutable) Name of team
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources

    Returns:
        qdrant (OnlineProvider): Provider
    """
    config = QdrantConfig(grpc_host=grpc_host, api_key=api_key, use_tls=use_tls)
    provider = Provider(
        name=name,
        function="ONLINE",
        description=description,
        team=team,
        config=config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return OnlineProvider(self, provider)

register_redis(name, host, port=6379, db=0, password='', description='', team='', tags=None, properties=None)

Register a Redis provider.

Examples:

redis = ff.register_redis(
    name="redis-quickstart",
    host="quickstart-redis",
    port=6379,
    password="password",
    description="A Redis deployment we created for the Featureform quickstart"
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of Redis provider to be registered	required
host	str	(Immutable) Hostname for Redis	required
db	str	(Immutable) Redis database number	0
port	int	(Mutable) Redis port	6379
password	str	(Mutable) Redis password	''
description	str	(Mutable) Description of Redis provider to be registered	''
team	str	(Mutable) Name of team	''
tags	Optional[List[str]]	(Mutable) Optional grouping mechanism for resources	None
properties	Optional[dict]	(Mutable) Optional grouping mechanism for resources	None

Returns:

Name	Type	Description
redis	OnlineProvider	Provider

Source code in src/featureform/register.py

def register_redis(
    self,
    name: str,
    host: str,
    port: int = 6379,
    db: int = 0,
    password: str = "",
    description: str = "",
    team: str = "",
    tags: Optional[List[str]] = None,
    properties: Optional[dict] = None,
):
    """Register a Redis provider.

    **Examples**:
    ```
    redis = ff.register_redis(
        name="redis-quickstart",
        host="quickstart-redis",
        port=6379,
        password="password",
        description="A Redis deployment we created for the Featureform quickstart"
    )
    ```

    Args:
        name (str): (Immutable) Name of Redis provider to be registered
        host (str): (Immutable) Hostname for Redis
        db (str): (Immutable) Redis database number
        port (int): (Mutable) Redis port
        password (str): (Mutable) Redis password
        description (str): (Mutable) Description of Redis provider to be registered
        team (str): (Mutable) Name of team
        tags (Optional[List[str]]): (Mutable) Optional grouping mechanism for resources
        properties (Optional[dict]): (Mutable) Optional grouping mechanism for resources

    Returns:
        redis (OnlineProvider): Provider
    """
    tags, properties = set_tags_properties(tags, properties)
    config = RedisConfig(host=host, port=port, password=password, db=db)
    provider = Provider(
        name=name,
        function="ONLINE",
        description=description,
        team=team,
        config=config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return OnlineProvider(self, provider)

register_redshift(name, host, port, user, password, database, description='', team='', sslmode='disable', tags=[], properties={})

Register a Redshift provider.

Examples:

redshift = ff.register_redshift(
    name="redshift-quickstart",
    description="A Redshift deployment we created for the Featureform quickstart",
    host="quickstart-redshift",  # The internal dns name for redshift
    port="5432",
    user="redshift",
    password="password", #pragma: allowlist secret
    database="dev"
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of Redshift provider to be registered	required
host	str	(Immutable) Hostname for Redshift	required
database	str	(Immutable) Redshift database	required
port	str	(Mutable) Port	required
user	str	(Mutable) User	required
password	str	(Mutable) Redshift password	required
sslmode	str	(Mutable) SSL mode	'disable'
description	str	(Mutable) Description of Redshift provider to be registered	''
team	str	(Mutable) Name of team	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	[]
properties	dict	(Mutable) Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
redshift	OfflineSQLProvider	Provider

Source code in src/featureform/register.py

def register_redshift(
    self,
    name: str,
    host: str,
    port: str,
    user: str,
    password: str,
    database: str,
    description: str = "",
    team: str = "",
    sslmode: str = "disable",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a Redshift provider.

    **Examples**:
    ```
    redshift = ff.register_redshift(
        name="redshift-quickstart",
        description="A Redshift deployment we created for the Featureform quickstart",
        host="quickstart-redshift",  # The internal dns name for redshift
        port="5432",
        user="redshift",
        password="password", #pragma: allowlist secret
        database="dev"
    )
    ```

    Args:
        name (str): (Immutable) Name of Redshift provider to be registered
        host (str): (Immutable) Hostname for Redshift
        database (str): (Immutable) Redshift database
        port (str): (Mutable) Port
        user (str): (Mutable) User
        password (str): (Mutable) Redshift password
        sslmode (str): (Mutable) SSL mode
        description (str): (Mutable) Description of Redshift provider to be registered
        team (str): (Mutable) Name of team
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources

    Returns:
        redshift (OfflineSQLProvider): Provider
    """
    tags, properties = set_tags_properties(tags, properties)
    config = RedshiftConfig(
        host=host,
        port=port,
        database=database,
        user=user,
        password=password,
        sslmode=sslmode,
    )
    provider = Provider(
        name=name,
        function="OFFLINE",
        description=description,
        team=team,
        config=config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return OfflineSQLProvider(self, provider)

register_s3(name, credentials, bucket_region, bucket_name, path='', description='', team='', tags=[], properties={})

Register a S3 store provider.

This has the functionality of an offline store and can be used as a parameter to a k8s or spark provider

Examples:

s3 = ff.register_s3(
    name="s3-quickstart",
    credentials=aws_creds,
    bucket_name="bucket_name",
    bucket_region=<bucket_region>,
    path="path/to/store/featureform_files/in/",
    description="An s3 store provider to store offline"
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of S3 store to be registered	required
bucket_name	str	(Immutable) AWS Bucket Name	required
bucket_region	str	(Immutable) AWS region the bucket is located in	required
path	str	(Immutable) The path used to store featureform files in	''
credentials	AWSCredentials	(Mutable) AWS credentials to access the bucket	required
description	str	(Mutable) Description of S3 provider to be registered	''
team	str	(Mutable) The name of the team registering the filestore	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	[]
properties	dict	(Mutable) Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
s3	FileStoreProvider	Provider has all the functionality of OfflineProvider

Source code in src/featureform/register.py

def register_s3(
    self,
    name: str,
    credentials: AWSCredentials,
    bucket_region: str,
    bucket_name: str,
    path: str = "",
    description: str = "",
    team: str = "",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a S3 store provider.

    This has the functionality of an offline store and can be used as a parameter
    to a k8s or spark provider

    **Examples**:
    ```
    s3 = ff.register_s3(
        name="s3-quickstart",
        credentials=aws_creds,
        bucket_name="bucket_name",
        bucket_region=<bucket_region>,
        path="path/to/store/featureform_files/in/",
        description="An s3 store provider to store offline"
    )
    ```

    Args:
        name (str): (Immutable) Name of S3 store to be registered
        bucket_name (str): (Immutable) AWS Bucket Name
        bucket_region (str): (Immutable) AWS region the bucket is located in
        path (str): (Immutable) The path used to store featureform files in
        credentials (AWSCredentials): (Mutable) AWS credentials to access the bucket
        description (str): (Mutable) Description of S3 provider to be registered
        team (str): (Mutable) The name of the team registering the filestore
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources

    Returns:
        s3 (FileStoreProvider): Provider
            has all the functionality of OfflineProvider
    """
    tags, properties = set_tags_properties(tags, properties)

    if bucket_name == "":
        raise ValueError("bucket_name is required and cannot be empty string")

    # TODO: add verification into S3StoreConfig
    bucket_name = bucket_name.replace("s3://", "").replace("s3a://", "")

    if "/" in bucket_name:
        raise ValueError(
            "bucket_name cannot contain '/'. bucket_name should be the name of the AWS S3 bucket only."
        )

    s3_config = S3StoreConfig(
        bucket_path=bucket_name,
        bucket_region=bucket_region,
        credentials=credentials,
        path=path,
    )

    provider = Provider(
        name=name,
        function="OFFLINE",
        description=description,
        team=team,
        config=s3_config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return FileStoreProvider(self, provider, s3_config, s3_config.type())

register_snowflake(name, username, password, account, organization, database, schema='PUBLIC', description='', team='', warehouse='', role='', tags=[], properties={})

Register a Snowflake provider.

Examples:

snowflake = ff.register_snowflake(
    name="snowflake-quickstart",
    username="snowflake",
    password="password", #pragma: allowlist secret
    account="account",
    organization="organization",
    database="snowflake",
    schema="PUBLIC",
    description="A Snowflake deployment we created for the Featureform quickstart"
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of Snowflake provider to be registered	required
account	str	(Immutable) Account	required
organization	str	(Immutable) Organization	required
database	str	(Immutable) Database	required
schema	str	(Immutable) Schema	'PUBLIC'
username	str	(Mutable) Username	required
password	str	(Mutable) Password	required
warehouse	str	(Mutable) Specifies the virtual warehouse to use by default for queries, loading, etc.	''
role	str	(Mutable) Specifies the role to use by default for accessing Snowflake objects in the client session	''
description	str	(Mutable) Description of Snowflake provider to be registered	''
team	str	(Mutable) Name of team	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	[]
properties	dict	(Mutable) Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
snowflake	OfflineSQLProvider	Provider

Source code in src/featureform/register.py

def register_snowflake(
    self,
    name: str,
    username: str,
    password: str,
    account: str,
    organization: str,
    database: str,
    schema: str = "PUBLIC",
    description: str = "",
    team: str = "",
    warehouse: str = "",
    role: str = "",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a Snowflake provider.

    **Examples**:
    ```
    snowflake = ff.register_snowflake(
        name="snowflake-quickstart",
        username="snowflake",
        password="password", #pragma: allowlist secret
        account="account",
        organization="organization",
        database="snowflake",
        schema="PUBLIC",
        description="A Snowflake deployment we created for the Featureform quickstart"
    )
    ```

    Args:
        name (str): (Immutable) Name of Snowflake provider to be registered
        account (str): (Immutable) Account
        organization (str): (Immutable) Organization
        database (str): (Immutable) Database
        schema (str): (Immutable) Schema
        username (str): (Mutable) Username
        password (str): (Mutable) Password
        warehouse (str): (Mutable) Specifies the virtual warehouse to use by default for queries, loading, etc.
        role (str): (Mutable) Specifies the role to use by default for accessing Snowflake objects in the client session
        description (str): (Mutable) Description of Snowflake provider to be registered
        team (str): (Mutable) Name of team
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources

    Returns:
        snowflake (OfflineSQLProvider): Provider
    """
    tags, properties = set_tags_properties(tags, properties)
    config = SnowflakeConfig(
        account=account,
        database=database,
        organization=organization,
        username=username,
        password=password,
        schema=schema,
        warehouse=warehouse,
        role=role,
    )
    provider = Provider(
        name=name,
        function="OFFLINE",
        description=description,
        team=team,
        config=config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return OfflineSQLProvider(self, provider)

register_snowflake_legacy(name, username, password, account_locator, database, schema='PUBLIC', description='', team='', warehouse='', role='', tags=[], properties={})

Register a Snowflake provider using legacy credentials.

Examples:

snowflake = ff.register_snowflake_legacy(
    name="snowflake-quickstart",
    username="snowflake",
    password="password",
    account_locator="account-locator",
    database="snowflake",
    schema="PUBLIC",
    description="A Snowflake deployment we created for the Featureform quickstart"
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of Snowflake provider to be registered	required
account_locator	str	(Immutable) Account Locator	required
schema	str	(Immutable) Schema	'PUBLIC'
database	str	(Immutable) Database	required
username	str	(Mutable) Username	required
password	str	(Mutable) Password	required
warehouse	str	(Mutable) Specifies the virtual warehouse to use by default for queries, loading, etc.	''
role	str	(Mutable) Specifies the role to use by default for accessing Snowflake objects in the client session	''
description	str	(Mutable) Description of Snowflake provider to be registered	''
team	str	(Mutable) Name of team	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	[]
properties	dict	(Mutable) Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
snowflake	OfflineSQLProvider	Provider

Source code in src/featureform/register.py

def register_snowflake_legacy(
    self,
    name: str,
    username: str,
    password: str,
    account_locator: str,
    database: str,
    schema: str = "PUBLIC",
    description: str = "",
    team: str = "",
    warehouse: str = "",
    role: str = "",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a Snowflake provider using legacy credentials.

    **Examples**:
    ```
    snowflake = ff.register_snowflake_legacy(
        name="snowflake-quickstart",
        username="snowflake",
        password="password",
        account_locator="account-locator",
        database="snowflake",
        schema="PUBLIC",
        description="A Snowflake deployment we created for the Featureform quickstart"
    )
    ```

    Args:
        name (str): (Immutable) Name of Snowflake provider to be registered
        account_locator (str): (Immutable) Account Locator
        schema (str): (Immutable) Schema
        database (str): (Immutable) Database
        username (str): (Mutable) Username
        password (str): (Mutable) Password
        warehouse (str): (Mutable) Specifies the virtual warehouse to use by default for queries, loading, etc.
        role (str): (Mutable) Specifies the role to use by default for accessing Snowflake objects in the client session
        description (str): (Mutable) Description of Snowflake provider to be registered
        team (str): (Mutable) Name of team
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources

    Returns:
        snowflake (OfflineSQLProvider): Provider
    """
    tags, properties = set_tags_properties(tags, properties)
    config = SnowflakeConfig(
        account_locator=account_locator,
        database=database,
        username=username,
        password=password,
        schema=schema,
        warehouse=warehouse,
        role=role,
    )
    provider = Provider(
        name=name,
        function="OFFLINE",
        description=description,
        team=team,
        config=config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return OfflineSQLProvider(self, provider)

register_spark(name, executor, filestore, description='', team='', tags=[], properties={})

Register a Spark on Executor provider.

Examples:

spark = ff.register_spark(
    name="spark-quickstart",
    description="A Spark deployment we created for the Featureform quickstart",
    team="featureform-team",
    executor=databricks,
    filestore=azure_blob_store
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of Spark provider to be registered	required
executor	ExecutorCredentials	(Mutable) An Executor Provider used for the compute power	required
filestore	FileStoreProvider	(Mutable) A FileStoreProvider used for storage of data	required
description	str	(Mutable) Description of Spark provider to be registered	''
team	str	(Mutable) Name of team	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	[]
properties	dict	(Mutable) Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
spark	OfflineSparkProvider	Provider

Source code in src/featureform/register.py

def register_spark(
    self,
    name: str,
    executor: ExecutorCredentials,
    filestore: FileStoreProvider,
    description: str = "",
    team: str = "",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a Spark on Executor provider.

    **Examples**:
    ```
    spark = ff.register_spark(
        name="spark-quickstart",
        description="A Spark deployment we created for the Featureform quickstart",
        team="featureform-team",
        executor=databricks,
        filestore=azure_blob_store
    )
    ```

    Args:
        name (str): (Immutable) Name of Spark provider to be registered
        executor (ExecutorCredentials): (Mutable) An Executor Provider used for the compute power
        filestore (FileStoreProvider): (Mutable) A FileStoreProvider used for storage of data
        description (str): (Mutable) Description of Spark provider to be registered
        team (str): (Mutable) Name of team
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources

    Returns:
        spark (OfflineSparkProvider): Provider
    """
    tags, properties = set_tags_properties(tags, properties)
    config = SparkConfig(
        executor_type=executor.type(),
        executor_config=executor.config(),
        store_type=filestore.store_type(),
        store_config=filestore.config(),
    )

    provider = Provider(
        name=name,
        function="OFFLINE",
        description=description,
        team=team,
        config=config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return OfflineSparkProvider(self, provider)

register_sql_transformation(name, query, provider, variant='', owner='', description='', schedule='', args=None, inputs=None, tags=[], properties={})

Register a SQL transformation source.

Parameters:

Name	Type	Description	Default
name	str	Name of source	required
variant	str	Name of variant	''
query	str	SQL query	required
provider	Union[str, OfflineProvider]	Provider	required
owner	Union[str, UserRegistrar]	Owner	''
description	str	Description of primary data to be registered	''
schedule	str	Kubernetes CronJob schedule string (" * * * ")	''
args	K8sArgs	Additional transformation arguments	None
tags	List[str]	Optional grouping mechanism for resources	[]
properties	dict	Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
source	ColumnSourceRegistrar	Source

Source code in src/featureform/register.py

def register_sql_transformation(
    self,
    name: str,
    query: str,
    provider: Union[str, OfflineProvider],
    variant: str = "",
    owner: Union[str, UserRegistrar] = "",
    description: str = "",
    schedule: str = "",
    args: K8sArgs = None,
    inputs: Union[List[NameVariant], List[str], List[ColumnSourceRegistrar]] = None,
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a SQL transformation source.

    Args:
        name (str): Name of source
        variant (str): Name of variant
        query (str): SQL query
        provider (Union[str, OfflineProvider]): Provider
        owner (Union[str, UserRegistrar]): Owner
        description (str): Description of primary data to be registered
        schedule (str): Kubernetes CronJob schedule string ("* * * * *")
        args (K8sArgs): Additional transformation arguments
        tags (List[str]): Optional grouping mechanism for resources
        properties (dict): Optional grouping mechanism for resources

    Returns:
        source (ColumnSourceRegistrar): Source
    """
    if not isinstance(owner, str):
        owner = owner.name()
    if owner == "":
        owner = self.must_get_default_owner()
    if variant == "":
        variant = self.__run
    if not isinstance(provider, str):
        provider = provider.name()
    source = SourceVariant(
        created=None,
        name=name,
        variant=variant,
        definition=SQLTransformation(query, args),
        owner=owner,
        schedule=schedule,
        provider=provider,
        description=description,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(source)
    return ColumnSourceRegistrar(self, source)

register_training_set(name, variant='', features=[], label=('', ''), resources=[], owner='', description='', schedule='', tags=[], properties={})

Register a training set.

Example:

ff.register_training_set(
    name="my_training_set",
    label=("label", "v1"),
    features=[("feature1", "v1"), ("feature2", "v1")],
)

Parameters:

Name	Type	Description	Default
name	str	Name of training set to be registered	required
variant	str	Name of variant to be registered	''
label	NameVariant	Label of training set	('', '')
features	List[NameVariant]	Features of training set	[]
resources	List[Resource]	A list of previously registered resources	[]
owner	Union[str, UserRegistrar]	Owner	''
description	str	Description of training set to be registered	''
schedule	str	Kubernetes CronJob schedule string (" * * * ")	''
tags	List[str]	Optional grouping mechanism for resources	[]
properties	dict	Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
resource	ResourceRegistrar	resource

Source code in src/featureform/register.py

def register_training_set(
    self,
    name: str,
    variant: str = "",
    features: Union[
        list, List[FeatureColumnResource], MultiFeatureColumnResource
    ] = [],
    label: Union[NameVariant, LabelColumnResource] = ("", ""),
    resources: list = [],
    owner: Union[str, UserRegistrar] = "",
    description: str = "",
    schedule: str = "",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a training set.

    **Example**:
    ```
    ff.register_training_set(
        name="my_training_set",
        label=("label", "v1"),
        features=[("feature1", "v1"), ("feature2", "v1")],
    )
    ```

    Args:
        name (str): Name of training set to be registered
        variant (str): Name of variant to be registered
        label (NameVariant): Label of training set
        features (List[NameVariant]): Features of training set
        resources (List[Resource]): A list of previously registered resources
        owner (Union[str, UserRegistrar]): Owner
        description (str): Description of training set to be registered
        schedule (str): Kubernetes CronJob schedule string ("* * * * *")
        tags (List[str]): Optional grouping mechanism for resources
        properties (dict): Optional grouping mechanism for resources

    Returns:
        resource (ResourceRegistrar): resource
    """
    if not isinstance(owner, str):
        owner = owner.name()
    if owner == "":
        owner = self.must_get_default_owner()
    if variant == "":
        variant = self.__run

    if not isinstance(features, (list, MultiFeatureColumnResource)):
        raise ValueError(
            f"Invalid features type: {type(features)} "
            "Features must be entered as a list of name-variant tuples (e.g. [('feature1', 'quickstart'), ('feature2', 'quickstart')]) or a list of FeatureColumnResource instances."
        )
    if not isinstance(label, (tuple, str, LabelColumnResource)):
        raise ValueError(
            f"Invalid label type: {type(label)} "
            "Label must be entered as a name-variant tuple (e.g. ('fraudulent', 'quickstart')), a resource name, or an instance of LabelColumnResource."
        )

    for resource in resources:
        features += resource.features()
        resource_label = resource.label()
        # label == () if it is NOT manually entered
        if label == ("", ""):
            label = resource_label
        # Elif: If label was updated to store resource_label it will not check the following elif
        elif resource_label != ():
            raise ValueError("A training set can only have one label")

    features, feature_lags = self.__get_feature_nv(features, self.__run)
    if label == ():
        raise ValueError("Label must be set")
    if features == []:
        raise ValueError("A training-set must have atleast one feature")
    if isinstance(label, str):
        label = (label, self.__run)
    if not isinstance(label, LabelColumnResource) and label[1] == "":
        label = (label[0], self.__run)

    processed_features = []
    for feature in features:
        if isinstance(feature, tuple) and feature[1] == "":
            feature = (feature[0], self.__run)
        processed_features.append(feature)
    resource = TrainingSetVariant(
        created=None,
        name=name,
        variant=variant,
        description=description,
        owner=owner,
        schedule=schedule,
        label=label,
        features=processed_features,
        feature_lags=feature_lags,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(resource)
    return resource

register_user(name, tags=[], properties={})

Register a user.

Parameters:

Name	Type	Description	Default
name	str	User to be registered.	required

Returns:

Name	Type	Description
UserRegistrar	UserRegistrar	User

Source code in src/featureform/register.py

def register_user(
    self, name: str, tags: List[str] = [], properties: dict = {}
) -> UserRegistrar:
    """Register a user.

    Args:
        name (str): User to be registered.

    Returns:
        UserRegistrar: User
    """
    user = User(name=name, tags=tags, properties=properties)
    self.__resources.append(user)
    return UserRegistrar(self, user)

register_weaviate(name, url, api_key, description='', team='', tags=[], properties={})

Register a Weaviate provider.

Examples:

weaviate = ff.register_weaviate(
    name="weaviate-quickstart",
    url="https://<CLUSTER NAME>.weaviate.network",
    api_key="<API KEY>"
    description="A Weaviate project for using embeddings in Featureform"
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of Weaviate provider to be registered	required
url	str	(Immutable) Endpoint of Weaviate cluster, either in the cloud or via another deployment operation	required
api_key	str	(Mutable) Weaviate api key	required
description	str	(Mutable) Description of Weaviate provider to be registered	''
team	str	(Mutable) Name of team	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	[]
properties	dict	(Mutable) Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
weaviate	OnlineProvider	Provider

Source code in src/featureform/register.py

def register_weaviate(
    self,
    name: str,
    url: str,
    api_key: str,
    description: str = "",
    team: str = "",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a Weaviate provider.

    **Examples**:
    ```
    weaviate = ff.register_weaviate(
        name="weaviate-quickstart",
        url="https://<CLUSTER NAME>.weaviate.network",
        api_key="<API KEY>"
        description="A Weaviate project for using embeddings in Featureform"
    )
    ```

    Args:
        name (str): (Immutable) Name of Weaviate provider to be registered
        url (str): (Immutable) Endpoint of Weaviate cluster, either in the cloud or via another deployment operation
        api_key (str): (Mutable) Weaviate api key
        description (str): (Mutable) Description of Weaviate provider to be registered
        team (str): (Mutable) Name of team
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources

    Returns:
        weaviate (OnlineProvider): Provider
    """
    config = WeaviateConfig(url=url, api_key=api_key)
    provider = Provider(
        name=name,
        function="ONLINE",
        description=description,
        team=team,
        config=config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return OnlineProvider(self, provider)

set_default_owner(user)

Set default owner.

Parameters:

Name	Type	Description	Default
user	str	User to be set as default owner of resources.	required

Source code in src/featureform/register.py

def set_default_owner(self, user: str):
    """Set default owner.

    Args:
        user (str): User to be set as default owner of resources.
    """
    self.__default_owner = user

set_run(run='')

Example 1: Using set_run() without arguments will generate a random run name.

import featureform as ff
ff.set_run()

postgres.register_table(
    name="transactions",
    table="transactions_table",
)

# Applying will register the source as name=transactions, variant=<randomly-generated>

Example 2: Using set_run() with arguments will set the variant to the provided name.

import featureform as ff
ff.set_run("last_30_days")

postgres.register_table(
    name="transactions",
    table="transactions_table",
)

# Applying will register the source as name=transactions, variant=last_30_days

Example 3: Generated and set variant names can be used together

import featureform as ff
ff.set_run()

file = spark.register_file(
    name="transactions",
    path="my/transactions.parquet",
    variant="last_30_days"
)

@spark.df_transformation(inputs=[file]):
def customer_count(transactions):
    return transactions.groupBy("CustomerID").count()


# Applying without a variant for the dataframe transformation will result in
# the transactions source having a variant of last_30_days and the transformation
# having a randomly generated variant

Example 4: This also works within SQL Transformations

import featureform as ff
ff.set_run("last_30_days")

@postgres.sql_transformation():
def my_transformation():
    return "SELECT CustomerID, Amount FROM {{ transactions }}"

# The variant will be autofilled so the SQL query is returned as:
# "SELECT CustomerID, Amount FROM {{ transactions.last_30_days }}"

Parameters:

Name	Type	Description	Default
run	str	Name of a run to be set.	''

Source code in src/featureform/register.py

def set_run(self, run: str = ""):
    """

    **Example 1**: Using set_run() without arguments will generate a random run name.
    ``` py
    import featureform as ff
    ff.set_run()

    postgres.register_table(
        name="transactions",
        table="transactions_table",
    )

    # Applying will register the source as name=transactions, variant=<randomly-generated>

    ```

    **Example 2**: Using set_run() with arguments will set the variant to the provided name.
    ``` py
    import featureform as ff
    ff.set_run("last_30_days")

    postgres.register_table(
        name="transactions",
        table="transactions_table",
    )

    # Applying will register the source as name=transactions, variant=last_30_days
    ```

    **Example 3**: Generated and set variant names can be used together
    ``` py
    import featureform as ff
    ff.set_run()

    file = spark.register_file(
        name="transactions",
        path="my/transactions.parquet",
        variant="last_30_days"
    )

    @spark.df_transformation(inputs=[file]):
    def customer_count(transactions):
        return transactions.groupBy("CustomerID").count()


    # Applying without a variant for the dataframe transformation will result in
    # the transactions source having a variant of last_30_days and the transformation
    # having a randomly generated variant
    ```

    **Example 4**: This also works within SQL Transformations
    ``` py
    import featureform as ff
    ff.set_run("last_30_days")

    @postgres.sql_transformation():
    def my_transformation():
        return "SELECT CustomerID, Amount FROM {{ transactions }}"

    # The variant will be autofilled so the SQL query is returned as:
    # "SELECT CustomerID, Amount FROM {{ transactions.last_30_days }}"
    ```

    Args:
        run (str): Name of a run to be set.
    """
    if run == "":
        if feature_flag.is_enabled("FF_GET_EQUIVALENT_VARIANTS", True):
            self.__run = get_current_timestamp_variant(self.__variant_prefix)
        else:
            self.__run = get_random_name()
    else:
        self.__run = run

set_variant_prefix(variant_prefix='')

Set variant prefix.

Parameters:

Name	Type	Description	Default
variant_prefix	str	variant prefix to be set.	''

Source code in src/featureform/register.py

def set_variant_prefix(self, variant_prefix: str = ""):
    """Set variant prefix.

    Args:
        variant_prefix (str): variant prefix to be set.
    """
    self.__variant_prefix = variant_prefix
    self.set_run()

sql_transformation(provider, variant='', name='', schedule='', owner='', inputs=None, description='', args=None, tags=[], properties={})

SQL transformation decorator.

Parameters:

Name	Type	Description	Default
variant	str	Name of variant	''
provider	Union[str, OfflineProvider]	Provider	required
name	str	Name of source	''
schedule	str	Kubernetes CronJob schedule string (" * * * ")	''
owner	Union[str, UserRegistrar]	Owner	''
inputs	list	Inputs to transformation	None
description	str	Description of SQL transformation	''
args	K8sArgs	Additional transformation arguments	None
tags	List[str]	Optional grouping mechanism for resources	[]
properties	dict	Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
decorator	SQLTransformationDecorator	decorator

Source code in src/featureform/register.py

def sql_transformation(
    self,
    provider: Union[str, OfflineProvider],
    variant: str = "",
    name: str = "",
    schedule: str = "",
    owner: Union[str, UserRegistrar] = "",
    inputs: Union[List[NameVariant], List[str], List[ColumnSourceRegistrar]] = None,
    description: str = "",
    args: K8sArgs = None,
    tags: List[str] = [],
    properties: dict = {},
):
    """SQL transformation decorator.

    Args:
        variant (str): Name of variant
        provider (Union[str, OfflineProvider]): Provider
        name (str): Name of source
        schedule (str): Kubernetes CronJob schedule string ("* * * * *")
        owner (Union[str, UserRegistrar]): Owner
        inputs (list): Inputs to transformation
        description (str): Description of SQL transformation
        args (K8sArgs): Additional transformation arguments
        tags (List[str]): Optional grouping mechanism for resources
        properties (dict): Optional grouping mechanism for resources

    Returns:
        decorator (SQLTransformationDecorator): decorator
    """
    if not isinstance(owner, str):
        owner = owner.name()
    if owner == "":
        owner = self.must_get_default_owner()
    if variant == "":
        variant = self.__run
    if not isinstance(provider, str):
        provider = provider.name()
    decorator = SQLTransformationDecorator(
        registrar=self,
        name=name,
        run=self.__run,
        variant=variant,
        provider=provider,
        schedule=schedule,
        owner=owner,
        description=description,
        inputs=inputs,
        args=args,
        tags=tags,
        properties=properties,
    )
    return decorator

featureform.register.OfflineSQLProvider

Bases: OfflineProvider

Source code in src/featureform/register.py

class OfflineSQLProvider(OfflineProvider):
    def __init__(self, registrar, provider):
        super().__init__(registrar, provider)
        self.__registrar = registrar
        self.__provider = provider

    def register_table(
        self,
        name: str,
        table: str,
        variant: str = "",
        owner: Union[str, UserRegistrar] = "",
        description: str = "",
        tags: List[str] = [],
        properties: dict = {},
    ):
        """Register a SQL table as a primary data source.

        **Example**

        ```
        postgres = client.get_provider("my_postgres")
        table =  postgres.register_table(
            name="transactions",
            variant="july_2023",
            table="transactions_table",
        ):
        ```

        Args:
            name (str): Name of table to be registered
            variant (str): Name of variant to be registered
            table (str): Name of SQL table
            owner (Union[str, UserRegistrar]): Owner
            description (str): Description of table to be registered

        Returns:
            source (ColumnSourceRegistrar): source
        """
        return self.__registrar.register_primary_data(
            name=name,
            variant=variant,
            location=SQLTable(table),
            owner=owner,
            provider=self.name(),
            description=description,
            tags=tags,
            properties=properties,
        )

    def sql_transformation(
        self,
        owner: Union[str, UserRegistrar] = "",
        variant: str = "",
        name: str = "",
        schedule: str = "",
        description: str = "",
        inputs: list = None,
        tags: List[str] = [],
        properties: dict = {},
    ):
        """
        Register a SQL transformation source.

        The name of the function is the name of the resulting source.

        Sources for the transformation can be specified by adding the Name and Variant in brackets '{{ name.variant }}'.
        The correct source is substituted when the query is run.

        **Examples**:

        ``` py
        postgres = client.get_provider("my_postgres")
        @postgres.sql_transformation(variant="quickstart")
        def average_user_transaction():
            return "SELECT CustomerID as user_id, avg(TransactionAmount) as avg_transaction_amt from {{transactions.v1}} GROUP BY user_id"
        ```

        Args:
            name (str): Name of source
            variant (str): Name of variant
            schedule (str): The frequency at which the transformation is run as a cron expression
            owner (Union[str, UserRegistrar]): Owner
            description (str): Description of primary data to be registered
            inputs (list): A list of Source NameVariant Tuples to input into the transformation


        Returns:
            source (ColumnSourceRegistrar): Source
        """
        return self.__registrar.sql_transformation(
            name=name,
            variant=variant,
            owner=owner,
            schedule=schedule,
            provider=self.name(),
            description=description,
            inputs=inputs,
            tags=tags,
            properties=properties,
        )

register_table(name, table, variant='', owner='', description='', tags=[], properties={})

Register a SQL table as a primary data source.

Example

postgres = client.get_provider("my_postgres")
table =  postgres.register_table(
    name="transactions",
    variant="july_2023",
    table="transactions_table",
):

Parameters:

Name	Type	Description	Default
name	str	Name of table to be registered	required
variant	str	Name of variant to be registered	''
table	str	Name of SQL table	required
owner	Union[str, UserRegistrar]	Owner	''
description	str	Description of table to be registered	''

Returns:

Name	Type	Description
source	ColumnSourceRegistrar	source

Source code in src/featureform/register.py

def register_table(
    self,
    name: str,
    table: str,
    variant: str = "",
    owner: Union[str, UserRegistrar] = "",
    description: str = "",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a SQL table as a primary data source.

    **Example**

    ```
    postgres = client.get_provider("my_postgres")
    table =  postgres.register_table(
        name="transactions",
        variant="july_2023",
        table="transactions_table",
    ):
    ```

    Args:
        name (str): Name of table to be registered
        variant (str): Name of variant to be registered
        table (str): Name of SQL table
        owner (Union[str, UserRegistrar]): Owner
        description (str): Description of table to be registered

    Returns:
        source (ColumnSourceRegistrar): source
    """
    return self.__registrar.register_primary_data(
        name=name,
        variant=variant,
        location=SQLTable(table),
        owner=owner,
        provider=self.name(),
        description=description,
        tags=tags,
        properties=properties,
    )

sql_transformation(owner='', variant='', name='', schedule='', description='', inputs=None, tags=[], properties={})

Register a SQL transformation source.

The name of the function is the name of the resulting source.

Sources for the transformation can be specified by adding the Name and Variant in brackets '{{ name.variant }}'. The correct source is substituted when the query is run.

Examples:

postgres = client.get_provider("my_postgres")
@postgres.sql_transformation(variant="quickstart")
def average_user_transaction():
    return "SELECT CustomerID as user_id, avg(TransactionAmount) as avg_transaction_amt from {{transactions.v1}} GROUP BY user_id"

Parameters:

Name	Type	Description	Default
name	str	Name of source	''
variant	str	Name of variant	''
schedule	str	The frequency at which the transformation is run as a cron expression	''
owner	Union[str, UserRegistrar]	Owner	''
description	str	Description of primary data to be registered	''
inputs	list	A list of Source NameVariant Tuples to input into the transformation	None

Returns:

Name	Type	Description
source	ColumnSourceRegistrar	Source

Source code in src/featureform/register.py

def sql_transformation(
    self,
    owner: Union[str, UserRegistrar] = "",
    variant: str = "",
    name: str = "",
    schedule: str = "",
    description: str = "",
    inputs: list = None,
    tags: List[str] = [],
    properties: dict = {},
):
    """
    Register a SQL transformation source.

    The name of the function is the name of the resulting source.

    Sources for the transformation can be specified by adding the Name and Variant in brackets '{{ name.variant }}'.
    The correct source is substituted when the query is run.

    **Examples**:

    ``` py
    postgres = client.get_provider("my_postgres")
    @postgres.sql_transformation(variant="quickstart")
    def average_user_transaction():
        return "SELECT CustomerID as user_id, avg(TransactionAmount) as avg_transaction_amt from {{transactions.v1}} GROUP BY user_id"
    ```

    Args:
        name (str): Name of source
        variant (str): Name of variant
        schedule (str): The frequency at which the transformation is run as a cron expression
        owner (Union[str, UserRegistrar]): Owner
        description (str): Description of primary data to be registered
        inputs (list): A list of Source NameVariant Tuples to input into the transformation


    Returns:
        source (ColumnSourceRegistrar): Source
    """
    return self.__registrar.sql_transformation(
        name=name,
        variant=variant,
        owner=owner,
        schedule=schedule,
        provider=self.name(),
        description=description,
        inputs=inputs,
        tags=tags,
        properties=properties,
    )

featureform.register.ColumnSourceRegistrar

Bases: SourceRegistrar

Source code in src/featureform/register.py

class ColumnSourceRegistrar(SourceRegistrar):
    def __getitem__(self, columns: List[str]):
        col_len = len(columns)
        if col_len < 2:
            raise Exception(
                f"Expected 2 columns, but found {col_len}. Missing entity and/or source columns"
            )
        elif col_len > 3:
            raise Exception(
                f"Found unrecognized columns {', '.join(columns[3:])}. Expected 2 required columns and an optional 3rd timestamp column"
            )
        return (self.registrar(), self, columns)

    def register_resources(
        self,
        entity: Union[str, EntityRegistrar],
        entity_column: str,
        owner: Union[str, UserRegistrar] = "",
        inference_store: Union[str, OnlineProvider, FileStoreProvider] = "",
        features: List[ColumnMapping] = None,
        labels: List[ColumnMapping] = None,
        timestamp_column: str = "",
        description: str = "",
        schedule: str = "",
    ):
        """
        Registers a features and/or labels that can be used in training sets or served.

        **Examples**:
        ``` py
        average_user_transaction.register_resources(
            entity=user,
            entity_column="CustomerID",
            inference_store=local,
            features=[
                {"name": "avg_transactions", "variant": "quickstart", "column": "TransactionAmount", "type": "float32"},
            ],
        )
        ```

        Args:
            entity (Union[str, EntityRegistrar]): The name to reference the entity by when serving features
            entity_column (str): The name of the column in the source to be used as the entity
            owner (Union[str, UserRegistrar]): The owner of the resource(s)
            inference_store (Union[str, OnlineProvider, FileStoreProvider]): Where to store the materialized feature for serving. (Use the local provider in Localmode)
            features (List[ColumnMapping]): A list of column mappings to define the features
            labels (List[ColumnMapping]): A list of column mappings to define the labels
            timestamp_column: (str): The name of an optional timestamp column in the dataset. Will be used to match the features and labels with point-in-time correctness

        Returns:
            registrar (ResourceRegister): Registrar
        """
        return self.registrar().register_column_resources(
            source=self,
            entity=entity,
            entity_column=entity_column,
            owner=owner,
            inference_store=inference_store,
            features=features,
            labels=labels,
            timestamp_column=timestamp_column,
            description=description,
            schedule=schedule,
            client_object=self,
        )

register_resources(entity, entity_column, owner='', inference_store='', features=None, labels=None, timestamp_column='', description='', schedule='')

Registers a features and/or labels that can be used in training sets or served.

Examples:

average_user_transaction.register_resources(
    entity=user,
    entity_column="CustomerID",
    inference_store=local,
    features=[
        {"name": "avg_transactions", "variant": "quickstart", "column": "TransactionAmount", "type": "float32"},
    ],
)

Parameters:

Name	Type	Description	Default
entity	Union[str, EntityRegistrar]	The name to reference the entity by when serving features	required
entity_column	str	The name of the column in the source to be used as the entity	required
owner	Union[str, UserRegistrar]	The owner of the resource(s)	''
inference_store	Union[str, OnlineProvider, FileStoreProvider]	Where to store the materialized feature for serving. (Use the local provider in Localmode)	''
features	List[ColumnMapping]	A list of column mappings to define the features	None
labels	List[ColumnMapping]	A list of column mappings to define the labels	None
timestamp_column	str	(str): The name of an optional timestamp column in the dataset. Will be used to match the features and labels with point-in-time correctness	''

Returns:

Name	Type	Description
registrar	ResourceRegister	Registrar

Source code in src/featureform/register.py

def register_resources(
    self,
    entity: Union[str, EntityRegistrar],
    entity_column: str,
    owner: Union[str, UserRegistrar] = "",
    inference_store: Union[str, OnlineProvider, FileStoreProvider] = "",
    features: List[ColumnMapping] = None,
    labels: List[ColumnMapping] = None,
    timestamp_column: str = "",
    description: str = "",
    schedule: str = "",
):
    """
    Registers a features and/or labels that can be used in training sets or served.

    **Examples**:
    ``` py
    average_user_transaction.register_resources(
        entity=user,
        entity_column="CustomerID",
        inference_store=local,
        features=[
            {"name": "avg_transactions", "variant": "quickstart", "column": "TransactionAmount", "type": "float32"},
        ],
    )
    ```

    Args:
        entity (Union[str, EntityRegistrar]): The name to reference the entity by when serving features
        entity_column (str): The name of the column in the source to be used as the entity
        owner (Union[str, UserRegistrar]): The owner of the resource(s)
        inference_store (Union[str, OnlineProvider, FileStoreProvider]): Where to store the materialized feature for serving. (Use the local provider in Localmode)
        features (List[ColumnMapping]): A list of column mappings to define the features
        labels (List[ColumnMapping]): A list of column mappings to define the labels
        timestamp_column: (str): The name of an optional timestamp column in the dataset. Will be used to match the features and labels with point-in-time correctness

    Returns:
        registrar (ResourceRegister): Registrar
    """
    return self.registrar().register_column_resources(
        source=self,
        entity=entity,
        entity_column=entity_column,
        owner=owner,
        inference_store=inference_store,
        features=features,
        labels=labels,
        timestamp_column=timestamp_column,
        description=description,
        schedule=schedule,
        client_object=self,
    )

Qdrant

Register a Qdrant provider.

Examples:

qdrant = ff.register_qdrant(
    name="qdrant-quickstart",
    grpc_host="xyz-example.eu-central.aws.cloud.qdrant.io:6334",
    api_key="<API KEY>",
    use_tls=True,
    description="A Qdrant project for using embeddings in Featureform"
)

Parameters:

Name	Type	Description	Default
name	str	(Immutable) Name of Qdrant provider to be registered	required
url	str	(Immutable) gRPC host of the Qdrant cluster, either in the cloud or via local deployment.	required
api_key	str	(Mutable) Qdrant API key.	''
use_tls	bool	(Immutable) Whether to use TLS for the connection.	False
description	str	(Mutable) Description of Qdrant provider to be registered	''
team	str	(Mutable) Name of team	''
tags	List[str]	(Mutable) Optional grouping mechanism for resources	[]
properties	dict	(Mutable) Optional grouping mechanism for resources	{}

Returns:

Name	Type	Description
qdrant	OnlineProvider	Provider

Source code in src/featureform/register.py

def register_qdrant(
    self,
    name: str,
    grpc_host: str,
    api_key: str = "",
    use_tls: bool = False,
    description: str = "",
    team: str = "",
    tags: List[str] = [],
    properties: dict = {},
):
    """Register a Qdrant provider.

    **Examples**:
    ```
    qdrant = ff.register_qdrant(
        name="qdrant-quickstart",
        grpc_host="xyz-example.eu-central.aws.cloud.qdrant.io:6334",
        api_key="<API KEY>",
        use_tls=True,
        description="A Qdrant project for using embeddings in Featureform"
    )
    ```

    Args:
        name (str): (Immutable) Name of Qdrant provider to be registered
        url (str): (Immutable) gRPC host of the Qdrant cluster, either in the cloud or via local deployment.
        api_key (str): (Mutable) Qdrant API key.
        use_tls (bool): (Immutable) Whether to use TLS for the connection.
        description (str): (Mutable) Description of Qdrant provider to be registered
        team (str): (Mutable) Name of team
        tags (List[str]): (Mutable) Optional grouping mechanism for resources
        properties (dict): (Mutable) Optional grouping mechanism for resources

    Returns:
        qdrant (OnlineProvider): Provider
    """
    config = QdrantConfig(grpc_host=grpc_host, api_key=api_key, use_tls=use_tls)
    provider = Provider(
        name=name,
        function="ONLINE",
        description=description,
        team=team,
        config=config,
        tags=tags,
        properties=properties,
    )
    self.__resources.append(provider)
    return OnlineProvider(self, provider)