langchain-mnestic 0.1.0

LangChain VectorStore for mnestic — embedded graph + vector + full-text store with one-call hybrid retrieval.

langchain-mnestic

A LangChain VectorStore backed by mnestic — an embedded graph + vector + full-text database (a maintained fork of CozoDB). Retrieval is hybrid by default: dense (HNSW) + keyword (full-text) fused with Reciprocal Rank Fusion, in one call.

pip install langchain-mnestic

from langchain_mnestic import MnesticVectorStore
from langchain_openai import OpenAIEmbeddings

store = MnesticVectorStore.from_texts(
    ["the cat sat on the mat", "a dog ran in the park"],
    embedding=OpenAIEmbeddings(),
    metadatas=[{"src": "a"}, {"src": "b"}],
    engine="sqlite", path="mydocs.db",   # or engine="mem" for ephemeral
)

docs = store.similarity_search("feline", k=2)
retriever = store.as_retriever(search_kwargs={"k": 4})

Scores returned by similarity_search_with_score are RRF fused scores — higher is better (a relevance score, not a distance).

License

Mozilla Public License 2.0.