haive.core.engine.document.loaders.specific.cloud

Cloud Storage Loaders for Document Engine.

This module implements cloud storage loaders for AWS S3, Google Cloud Storage, Azure Blob Storage, and other cloud providers.

Classes

AzureBlobSource	Azure Blob Storage source implementation.
GCSSource	Google Cloud Storage source implementation.
S3Source	AWS S3 storage source implementation.

Module Contents

class haive.core.engine.document.loaders.specific.cloud.AzureBlobSource(account_name, container_name, blob_name=None, prefix=None, **kwargs)

Bases: haive.core.engine.document.loaders.sources.implementation.CloudStorageSource

Azure Blob Storage source implementation.

Init .

Parameters:

• account_name (str) – [TODO: Add description]

• container_name (str) – [TODO: Add description]

• blob_name (str | None) – [TODO: Add description]

• prefix (str | None) – [TODO: Add description]

can_handle(path)

Check if this is an Azure Blob path.

Parameters:

path (str)

Return type:

bool

create_loader()

Create an Azure Blob loader.

Return type:

langchain_core.document_loaders.base.BaseLoader | None

get_confidence_score(path)

Get confidence score for Azure Blob paths.

Parameters:

path (str)

Return type:

float

get_credential_requirements()

Azure Blob needs Azure credentials.

Return type:

list[haive.core.engine.document.loaders.sources.implementation.CredentialType]

requires_authentication()

Azure Blob typically requires authentication.

Return type:

bool

class haive.core.engine.document.loaders.specific.cloud.GCSSource(bucket_name, object_name=None, prefix=None, project_id=None, **kwargs)

Bases: haive.core.engine.document.loaders.sources.implementation.CloudStorageSource

Google Cloud Storage source implementation.

Init .

Parameters:

• bucket_name (str) – [TODO: Add description]

• object_name (str | None) – [TODO: Add description]

• prefix (str | None) – [TODO: Add description]

• project_id (str | None) – [TODO: Add description]

can_handle(path)

Check if this is a GCS path.

Parameters:

path (str)

Return type:

bool

create_loader()

Create a GCS loader.

Return type:

langchain_core.document_loaders.base.BaseLoader | None

get_confidence_score(path)

Get confidence score for GCS paths.

Parameters:

path (str)

Return type:

float

get_credential_requirements()

GCS needs Google Cloud credentials.

Return type:

list[haive.core.engine.document.loaders.sources.implementation.CredentialType]

requires_authentication()

GCS typically requires authentication.

Return type:

bool

class haive.core.engine.document.loaders.specific.cloud.S3Source(bucket_name, object_key=None, prefix=None, region=None, **kwargs)

Bases: haive.core.engine.document.loaders.sources.implementation.CloudStorageSource

AWS S3 storage source implementation.

Init .

Parameters:

• bucket_name (str) – [TODO: Add description]

• object_key (str | None) – [TODO: Add description]

• prefix (str | None) – [TODO: Add description]

• region (str | None) – [TODO: Add description]

can_handle(path)

Check if this is an S3 path.

Parameters:

path (str)

Return type:

bool

create_loader()

Create an S3 loader.

Return type:

langchain_core.document_loaders.base.BaseLoader | None

get_confidence_score(path)

Get confidence score for S3 paths.

Parameters:

path (str)

Return type:

float

get_credential_requirements()

S3 needs AWS credentials.

Return type:

list[haive.core.engine.document.loaders.sources.implementation.CredentialType]

requires_authentication()

S3 typically requires authentication.

Return type:

bool