GenericLoader#

class langchain_community.document_loaders.generic.GenericLoader(blob_loader: BlobLoader, blob_parser: BaseBlobParser)[source]#

Generic Document Loader.

A generic document loader that allows combining an arbitrary blob loader with a blob parser.

Examples

Parse a specific PDF file:

 from langchain_community.document_loaders import GenericLoader
 from langchain_community.document_loaders.parsers.pdf import PyPDFParser

 # Recursively load all text files in a directory.
 loader = GenericLoader.from_filesystem(
     "my_lovely_pdf.pdf",
     parser=PyPDFParser()
 )

.. code-block:: python

     from langchain_community.document_loaders import GenericLoader
     from langchain_community.document_loaders.blob_loaders import FileSystemBlobLoader


     loader = GenericLoader.from_filesystem(
         path="path/to/directory",
         glob="**/[!.]*",
         suffixes=[".pdf"],
         show_progress=True,
     )

     docs = loader.lazy_load()
     next(docs)

Example instantiations to change which files are loaded:

# Recursively load all text files in a directory.
loader = GenericLoader.from_filesystem("/path/to/dir", glob="**/*.txt")

# Recursively load all non-hidden files in a directory.
loader = GenericLoader.from_filesystem("/path/to/dir", glob="**/[!.]*")

# Load all files in a directory without recursion.
loader = GenericLoader.from_filesystem("/path/to/dir", glob="*")

Example instantiations to change which parser is used:

from langchain_community.document_loaders.parsers.pdf import PyPDFParser

# Recursively load all text files in a directory.
loader = GenericLoader.from_filesystem(
    "/path/to/dir",
    glob="**/*.pdf",
    parser=PyPDFParser()
)

A generic document loader.

Parameters:

  • blob_loader (BlobLoader) – A blob loader which knows how to yield blobs

  • blob_parser (BaseBlobParser) – A blob parser which knows how to parse blobs into documents

Methods

__init__(blob_loader, blob_parser)

A generic document loader.

alazy_load()

A lazy loader for Documents.

aload()

Load data into Document objects.

from_filesystem(path, *[, glob, exclude, ...])

Create a generic document loader using a filesystem blob loader.

get_parser(**kwargs)

Override this method to associate a default parser with the class.

lazy_load()

Load documents lazily.

load()

Load data into Document objects.

load_and_split([text_splitter])

Load all documents and split them into sentences.
__init__(blob_loader: BlobLoader, blob_parser: BaseBlobParser) → None[source]#

A generic document loader.

Parameters:

  • blob_loader (BlobLoader) – A blob loader which knows how to yield blobs

  • blob_parser (BaseBlobParser) – A blob parser which knows how to parse blobs into documents

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]

classmethod from_filesystem(path: str | Path, *, glob: str = '**/[!.]*', exclude: Sequence[str] = (), suffixes: Sequence[str] | None = None, show_progress: bool = False, parser: Literal['default'] | BaseBlobParser = 'default', parser_kwargs: dict | None = None) → GenericLoader[source]#

Create a generic document loader using a filesystem blob loader.

Parameters:

  • path (str | Path) –

    The path to the directory to load documents from OR the path to a single file to load. If this is a file, glob, exclude, suffixes

    will be ignored.

  • glob (str) – The glob pattern to use to find documents.

  • suffixes (Sequence[str] | None) – The suffixes to use to filter documents. If None, all files matching the glob will be loaded.

  • exclude (Sequence[str]) – A list of patterns to exclude from the loader.

  • show_progress (bool) – Whether to show a progress bar or not (requires tqdm). Proxies to the file system loader.

  • parser (Literal['default'] | ~langchain_core.document_loaders.base.BaseBlobParser) – A blob parser which knows how to parse blobs into documents, will instantiate a default parser if not provided. The default can be overridden by either passing a parser or setting the class attribute blob_parser (the latter should be used with inheritance).

  • parser_kwargs (dict | None) – Keyword arguments to pass to the parser.

Returns:

A generic document loader.

Return type:

GenericLoader

static get_parser(**kwargs: Any) → BaseBlobParser[source]#

Override this method to associate a default parser with the class.

Parameters:

kwargs (Any) –

Return type:

BaseBlobParser

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

Load documents lazily. Use this when working at a large scale.

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][source]#

Load all documents and split them into sentences.

Parameters:

text_splitter (Optional[TextSplitter]) –

Return type:

List[Document]

Examples using GenericLoader

On this page