langchain-mongodb: 0.2.0#
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.
cache#
Classes
|
MongoDB Atlas Semantic cache. |
|
MongoDB Atlas cache |
chat_message_histories#
Classes
Chat message history that stores history in MongoDB. |
langchain_mongodb_index#
Functions
|
Experimental Utility function to create an Atlas Search index |
|
Experimental Utility function to create a vector search index |
|
Drop a created vector search index |
|
Update a search index. |
pipelines#
Functions
|
Combines two aggregations into a single result set in-place. |
|
Sum weighted scores, sort, and apply limit. |
|
Stage adds Reciprocal Rank Fusion weighting. |
|
Full-Text search using Lucene's standard (BM25) analyzer |
|
Vector Search Stage without Scores. |
retrievers#
Classes
|
Hybrid Search Retriever performs full-text searches using Lucene's standard (BM25) analyzer. |
Hybrid Search Retriever combines vector and full-text searches weighting them the via Reciprocal Rank Fusion (RRF) algorithm. |
utils#
Functions
|
Row-wise cosine similarity between two equal-width matrices. |
Recursively cast values in a dict to a form able to json.dump |
|
|
Compute Maximal Marginal Relevance (MMR). |
|
Convert MongoDB's internal BSON ObjectId into a simple str for compatibility. |
|
Attempt to cast string representation of id to MongoDB's internal BSON ObjectId. |
vectorstores#
Classes
|
MongoDB Atlas vector store integration. |