Langchain VDMS

This package contains the VDMS integration package for LangChain:

• langchain-vdms - An integration between LangChain and VDMS which enables retrievers and vector search for AI applications.

Installation

pip install -U langchain-vdms

VDMS vector database

The VDMS class exposes the VDMS vector store.

from langchain_vdms import VDMS

The VDMS_Client function connects to VDMS server using VDMS client.

from langchain_vdms.vectorstores import VDMS_Client

The VDMS_Utils class exposes a utility with helpful functions related to VDMS.

from langchain_vdms.vectorstores import VDMS_Utils

Example Usage

This example initiates the VDMS vector store and uses the VDMS Client to connect to a VDMS server on localhost using port 55555.

from langchain_vdms.vectorstores import VDMS, VDMS_Client

embeddings = ... # use a LangChain Embeddings class

vectorstore_client = VDMS_Client("localhost", 55555)
vectorstore = VDMS(
    client=vectorstore_client,
    collection_name="foo",
    embedding=embeddings,
    engine="FaissFlat",
    distance_strategy="L2",
)

See additional usage here.

Contributing

Contributions are welcome! Please see CONTRIBUTING.md for guidelines.

License

This project is licensed under the MIT License - see the LICENSE file for details.