lance-format / lance-format/lance

Allow creating an index over a nested vector column

Open
#978 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement rust
Dominant language
Rust
Stars
7.1k
Forks
852
Avg merge
3d 18h
Merged PRs (30d)
272

Description

For large documents, it may be common to have many context windows. Right now we require one embedding per row, but that means for context windows we need to duplicate document metadata quite a bit. It would be nice if we could have multiple embeddings per row.

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

Start by reviewing the issue's requirement for multiple embeddings per row and an index over a nested vector column. Define what nested-column indexing and successful multi-embedding queries should look like, then identify the relevant vector-index entry points and tests before implementation.

Written by the indexing model from the issue text.

Assessment

Tech stack
rust
Domain
databases
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.