langchain-mongodb: 0.9.0#

Integrate your operational database and vector search in a single, unified, fully managed platform with full vector database capabilities on MongoDB Atlas.

Store your operational data, metadata, and vector embeddings in oue VectorStore, MongoDBAtlasVectorSearch. Insert into a Chain via a Vector, FullText, or Hybrid Retriever.

agent_toolkit #

Classes

`agent_toolkit.database.MongoDBDatabase`(...)	Wrapper around a MongoDB database.
`agent_toolkit.tool.BaseMongoDBDatabaseTool`	Base tool for interacting with a MongoDB database.
`agent_toolkit.tool.InfoMongoDBDatabaseTool`	Tool for getting metadata about a MongoDB database.
`agent_toolkit.tool.ListMongoDBDatabaseTool`	Tool for getting collection names.
`agent_toolkit.tool.QueryMongoDBCheckerTool`	Use an LLM to check if a query is correct.
`agent_toolkit.tool.QueryMongoDBDatabaseTool`	Tool for querying a MongoDB database.
`agent_toolkit.toolkit.MongoDBDatabaseToolkit`	MongoDBDatabaseToolkit for interacting with MongoDB databases.

cache #

Classes

`cache.MongoDBAtlasSemanticCache`(...[, ...])	MongoDB Atlas Semantic cache.
`cache.MongoDBCache`(connection_string[, ...])	MongoDB Atlas cache

chat_message_histories #

Classes

chat_message_histories.MongoDBChatMessageHistory(...)

Chat message history that stores history in MongoDB.

docstores #

Classes

docstores.MongoDBDocStore(collection[, text_key])

MongoDB Collection providing BaseStore interface.

graphrag #

Classes

graphrag.graph.MongoDBGraphStore(*[, ...])

GraphRAG DataStore

indexes #

Classes

indexes.MongoDBRecordManager(collection)

A MongoDB-based implementation of the record manager.

loaders #

Classes

loaders.MongoDBLoader(collection, *[, ...])

Document Loaders are classes to load Documents.

pipelines #

Functions

pipelines.text_search_stage(query, ...[, ...])

Full-Text search using Lucene's standard (BM25) analyzer

retrievers #

Classes

`retrievers.full_text_search.MongoDBAtlasFullTextSearchRetriever`	Retriever performs full-text searches using Lucene's standard (BM25) analyzer.
`retrievers.graphrag.MongoDBGraphRAGRetriever`	RunnableSerializable API of MongoDB GraphRAG.
`retrievers.hybrid_search.MongoDBAtlasHybridSearchRetriever`	Hybrid Search Retriever combines vector and full-text searches weighting them the via Reciprocal Rank Fusion (RRF) algorithm.
`retrievers.parent_document.MongoDBAtlasParentDocumentRetriever`	MongoDB Atlas's ParentDocumentRetriever
`retrievers.self_querying.MongoDBAtlasSelfQueryRetriever`	Retriever that uses an LLM to deduce filters for Vector Search algorithm.
`retrievers.self_querying.MongoDBStructuredQueryTranslator`()	Translator between MongoDB Query API and LangChain's StructuredQuery.

utils #

Functions

`utils.cosine_similarity`(X, Y)	Row-wise cosine similarity between two equal-width matrices.
`utils.make_serializable`(obj)	Recursively cast values in a dict to a form able to json.dump
`utils.maximal_marginal_relevance`(...[, ...])	Compute Maximal Marginal Relevance (MMR).
`utils.oid_to_str`(oid)	Convert MongoDB's internal BSON ObjectId into a simple str for compatibility.
`utils.str_to_oid`(str_repr)	Attempt to cast string representation of id to MongoDB's internal BSON ObjectId.

vectorstores #

Classes

vectorstores.MongoDBAtlasVectorSearch(...[, ...])

MongoDB Atlas vector store integration.