AzureAIDocumentIntelligenceLoader#

class langchain_community.document_loaders.doc_intelligence.AzureAIDocumentIntelligenceLoader( api_endpoint: str, api_key: str | None = None, file_path: str | None = None, url_path: str | None = None, bytes_source: bytes | None = None, api_version: str | None = None, api_model: str = 'prebuilt-layout', mode: str = 'markdown', *, analysis_features: List[str] | None = None, azure_credential: 'TokenCredential' | None = None, )[source]#

Load a PDF with Azure Document Intelligence.

Initialize the object for file processing with Azure Document Intelligence (formerly Form Recognizer).

This constructor initializes a AzureAIDocumentIntelligenceParser object to be used for parsing files using the Azure Document Intelligence API. The load method generates Documents whose content representations are determined by the mode parameter.

Parameters:#

api_endpoint: str: The API endpoint to use for DocumentIntelligenceClient construction.
api_key: str: The API key to use for DocumentIntelligenceClient construction.
file_pathOptional[str]: The path to the file that needs to be loaded. Either file_path, url_path or bytes_source must be specified.
url_pathOptional[str]: The URL to the file that needs to be loaded. Either file_path, url_path or bytes_source must be specified.
bytes_sourceOptional[bytes]: The bytes array of the file that needs to be loaded. Either file_path, url_path or bytes_source must be specified.
api_version: Optional[str]: The API version for DocumentIntelligenceClient. Setting None to use the default value from azure-ai-documentintelligence package.
api_model: str: Unique document model name. Default value is “prebuilt-layout”. Note that overriding this default value may result in unsupported behavior.
mode: Optional[str]: The type of content representation of the generated Documents. Use either “single”, “page”, or “markdown”. Default value is “markdown”.
analysis_features: Optional[List[str]]: List of optional analysis features, each feature should be passed as a str that conforms to the enum DocumentAnalysisFeature in azure-ai-documentintelligence package. Default value is None.
azure_credential: Optional[TokenCredential]: The credentials to use for DocumentIntelligenceClient construction, when using credentials other than api_key (like AD).

Examples:#

>>> obj = AzureAIDocumentIntelligenceLoader(
...     file_path="path/to/file",
...     api_endpoint="https://endpoint.azure.com",
...     api_key="APIKEY",
...     api_version="2023-10-31-preview",
...     api_model="prebuilt-layout",
...     mode="markdown"
... )

Methods

`__init__`(api_endpoint[, api_key, file_path, ...])	Initialize the object for file processing with Azure Document Intelligence (formerly Form Recognizer).
`alazy_load`()	A lazy loader for Documents.
`aload`()	Load data into Document objects.
`lazy_load`()	Lazy load the document as pages.
`load`()	Load data into Document objects.
`load_and_split`([text_splitter])	Load Documents and split into chunks.

__init__( api_endpoint: str, api_key: str | None = None, file_path: str | None = None, url_path: str | None = None, bytes_source: bytes | None = None, api_version: str | None = None, api_model: str = 'prebuilt-layout', mode: str = 'markdown', *, analysis_features: List[str] | None = None, azure_credential: 'TokenCredential' | None = None, ) → None[source]#

Initialize the object for file processing with Azure Document Intelligence (formerly Form Recognizer).

This constructor initializes a AzureAIDocumentIntelligenceParser object to be used for parsing files using the Azure Document Intelligence API. The load method generates Documents whose content representations are determined by the mode parameter.

Parameters:#

api_endpoint: str: The API endpoint to use for DocumentIntelligenceClient construction.
api_key: str: The API key to use for DocumentIntelligenceClient construction.
file_pathOptional[str]: The path to the file that needs to be loaded. Either file_path, url_path or bytes_source must be specified.
url_pathOptional[str]: The URL to the file that needs to be loaded. Either file_path, url_path or bytes_source must be specified.
bytes_sourceOptional[bytes]: The bytes array of the file that needs to be loaded. Either file_path, url_path or bytes_source must be specified.
api_version: Optional[str]: The API version for DocumentIntelligenceClient. Setting None to use the default value from azure-ai-documentintelligence package.
api_model: str: Unique document model name. Default value is “prebuilt-layout”. Note that overriding this default value may result in unsupported behavior.
mode: Optional[str]: The type of content representation of the generated Documents. Use either “single”, “page”, or “markdown”. Default value is “markdown”.
analysis_features: Optional[List[str]]: List of optional analysis features, each feature should be passed as a str that conforms to the enum DocumentAnalysisFeature in azure-ai-documentintelligence package. Default value is None.
azure_credential: Optional[TokenCredential]: The credentials to use for DocumentIntelligenceClient construction, when using credentials other than api_key (like AD).

Examples:#

>>> obj = AzureAIDocumentIntelligenceLoader(
...     file_path="path/to/file",
...     api_endpoint="https://endpoint.azure.com",
...     api_key="APIKEY",
...     api_version="2023-10-31-preview",
...     api_model="prebuilt-layout",
...     mode="markdown"
... )

Parameters:

api_endpoint (str)
api_key (Optional[str])
file_path (Optional[str])
url_path (Optional[str])
bytes_source (Optional[bytes])
api_version (Optional[str])
api_model (str)
mode (str)
analysis_features (Optional[List[str]])
azure_credential (Optional['TokenCredential'])

Return type:

None

async alazy_load() → AsyncIterator[Document]#

A lazy loader for Documents.

Return type:: AsyncIterator[Document]

async aload() → list[Document]#

Load data into Document objects.

Return type:: list[Document]

lazy_load() → Iterator[Document][source]#

Lazy load the document as pages.

Return type:: Iterator[Document]

load() → list[Document]#

Load data into Document objects.

Return type:: list[Document]

load_and_split( text_splitter: TextSplitter | None = None, ) → list[Document]#

Load Documents and split into chunks. Chunks are returned as Documents.

Do not override this method. It should be considered to be deprecated!

Parameters:: text_splitter (Optional[TextSplitter]) – TextSplitter instance to use for splitting documents. Defaults to RecursiveCharacterTextSplitter.
Returns:: List of Documents.
Return type:: list[Document]

Parameters:

api_endpoint (str)
api_key (Optional[str])
file_path (Optional[str])
url_path (Optional[str])
bytes_source (Optional[bytes])
api_version (Optional[str])
api_model (str)
mode (str)
analysis_features (Optional[List[str]])
azure_credential (Optional['TokenCredential'])

Examples using AzureAIDocumentIntelligenceLoader