tursodatabase / tursodatabase/libsql

Feature request: Index based on embeddings

Open
#2,098 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C
Stars
17.2k
Forks
531
Avg merge
1h 12m
Merged PRs (30d)
1

Description

LibSQL is amazing! I love how easy it is to save and retrieve a vector in the database.

However for semantic search, I don't care about the vector. I just want to see the most similar values.

Also, if we want to do semantic search on multiple columns, we need to add many columns.

My proposition would be to be able to define an embedding function as an index and use it as well for the retrieval.

That way, the embedding, storage, and retrieval of the vectors can be abstracted away from the user.

What do you think?

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No files, tests, or entry points are named. Start by reviewing LibSQL’s existing vector storage and retrieval behavior and its index interfaces; done would mean defining an embedding-based index that abstracts vector storage and retrieval, including semantic search across multiple columns.

Written by the indexing model from the issue text.

Assessment

Domain
databases, machine-learning, search
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.