langchain icon indicating copy to clipboard operation
langchain copied to clipboard

Integrate Rockset as Vectorstore

Open anubhav94N opened this issue 2 years ago • 1 comments

Description

This PR adds Rockset as a vectorstore for langchain. Rockset is a real time OLAP database which provides a fast and efficient vector search functionality. Further since it is entirely schemaless, it can store metadata in separate columns thereby allowing fast metadata filters during vector similarity search (as opposed to storing the entire metadata in a single JSON column). It currently supports three distance functions: COSINE_SIMILARITY, EUCLIDEAN_DISTANCE, and DOT_PRODUCT.

This PR adds rockset client as an optional dependency.

We would love a twitter shoutout, our handle is https://twitter.com/RocksetCloud

Before submitting

  1. Integration test: https://github.com/anubhav94N/langchain/blob/master/tests/integration_tests/vectorstores/test_rocksetdb.py
  2. Example notebook: https://github.com/anubhav94N/langchain/blob/master/docs/modules/indexes/vectorstores/examples/rockset_vector_database.ipynb
  3. Ran make format and make lint locally

Who can review?

@hwchase17, @dev2049 can you help review please?

anubhav94N avatar Jun 15 '23 10:06 anubhav94N

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name Status Preview Comments Updated (UTC)
langchain ✅ Ready (Inspect) Visit Preview 💬 Add feedback Jun 21, 2023 8:20am

vercel[bot] avatar Jun 16 '23 10:06 vercel[bot]

@anubhav94N is attempting to deploy a commit to the LangChain Team on Vercel.

A member of the Team first needs to authorize it.

vercel[bot] avatar Jun 19 '23 12:06 vercel[bot]

thanks @anubhav94N!

dev2049 avatar Jun 21 '23 08:06 dev2049