vespperhq / vespper

Open-source AI copilot that lets you chat with your observability data and code 🧙‍♂️
https://www.vespper.com/?utm_source=github
Apache License 2.0
291 stars 36 forks source link

feat: Qdrant support for RAG #40

Closed Anush008 closed 2 weeks ago

Anush008 commented 2 weeks ago

Description

This PR adds support for Qdrant - https://qdrant.tech to be used for RAG in Vespper.

To run Qdrant:

docker run -p 6333:6333 qdrant/qdrant

You can find the dashboard to view the data at http://locahost:6333/dashboard/

Set the env:

QDRANT_URL=http://locahost:6333/

Note

I'm in the process of QA testing.


[!IMPORTANT] Adds Qdrant support for RAG in Vespper, including new classes and updates to existing models and utilities.

  • Behavior:
    • Adds Qdrant support for RAG in Vespper.
    • New QdrantVectorStore class in qdrant.ts and qdrant.py for handling Qdrant operations.
    • Updates getVectorStore() in utils.ts and utils.py to include Qdrant.
  • Models:
    • Updates IIndex type in types.ts and db_types.py to include qdrant as a valid type.
    • Updates IndexSchema in db-index.ts to include qdrant in the enum.
  • Dependencies:
    • Adds @qdrant/js-client-rest to package.json.
    • Adds llama-index-vector-stores-qdrant to pyproject.toml.

This description was created by Ellipsis for d1b56133bffb73b16eddac0d2f7289716e7e7968. It will automatically update as commits are pushed.

david1542 commented 2 weeks ago

Hi @Anush008! Thanks a lot for this PR. I'll try my best to review it tomorrow PDT

topaztee commented 2 weeks ago

@ellipsis-dev review this

david1542 commented 2 weeks ago

Thanks for the PR @Anush008. Approved