MongoDBLoader

class langchain_mongodb.loaders.MongoDBLoader(collection: Collection, *, filter_criteria: Dict | None = None, field_names: Sequence[str] | None = None, metadata_names: Sequence[str] | None = None, include_db_collection_in_metadata: bool = True)

Document Loaders are classes to load Documents.

Document Loaders are usually used to load a lot of Documents in a single run.

Methods

__init__(collection, *[, filter_criteria, ...])	Initializes the MongoDB loader with necessary database connection details and configurations.
alazy_load()	A lazy loader for Documents.
aload()	Asynchronously loads data into Document objects.
close()	Close the resources used by the MongoDBLoader.
from_connection_string(connection_string, ...)	Creates a MongoDB loader with necessary database connection details and configurations.
lazy_load()	A lazy loader for Documents.
load()	Load data into Document objects.
load_and_split([text_splitter])	Load Documents and split into chunks.

Parameters:

• collection (Collection)

• filter_criteria (Optional[Dict])

• field_names (Optional[Sequence[str]])

• metadata_names (Optional[Sequence[str]])

• include_db_collection_in_metadata (bool)

__init__(collection: Collection, *, filter_criteria: Dict | None = None, field_names: Sequence[str] | None = None, metadata_names: Sequence[str] | None = None, include_db_collection_in_metadata: bool = True) → None

Initializes the MongoDB loader with necessary database connection details and configurations.

Parameters:

• collection (Collection) – The pymongo collection to fetch documents from.

• filter_criteria (Optional[Dict]) – MongoDB filter criteria for querying

• documents. (extract from)

• field_names (Optional[Sequence[str]]) – List of field names to retrieve

• documents.

• metadata_names (Optional[Sequence[str]]) – Additional metadata fields to

• documents.

• include_db_collection_in_metadata (bool) – Flag to include database and

• metadata. (collection names in)

Return type:

None

async alazy_load() → AsyncIterator[Document]

A lazy loader for Documents.

Return type:

AsyncIterator[Document]

async aload() → List[Document]

Asynchronously loads data into Document objects.

Return type:

List[Document]

close() → None

Close the resources used by the MongoDBLoader.

Return type:

None

classmethod from_connection_string(connection_string: str, db_name: str, collection_name: str, *, filter_criteria: Dict | None = None, field_names: Sequence[str] | None = None, metadata_names: Sequence[str] | None = None, include_db_collection_in_metadata: bool = True) → MongoDBLoader

Creates a MongoDB loader with necessary database connection details and configurations.

Parameters:

• connection_string (str) – MongoDB connection URI.

• db_name (str) – Name of the database to connect to.

• collection_name (str) – Name of the collection to fetch documents from.

• filter_criteria (Optional[Dict]) – MongoDB filter criteria for querying

• documents. (extract from)

• field_names (Optional[Sequence[str]]) – List of field names to retrieve

• documents.

• metadata_names (Optional[Sequence[str]]) – Additional metadata fields to

• documents.

• include_db_collection_in_metadata (bool) – Flag to include database and

• metadata. (collection names in)

Return type:

MongoDBLoader

lazy_load() → Iterator[Document]

A lazy loader for Documents.

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]