lance-format / lance-format/lance
Implement CacheCode for HNSW indices
Open
Nobody has claimed this yet.
A-index
enhancement
- Dominant language
- Rust
- Stars
- 7.1k
- Forks
- 852
- Avg merge
- 3d 18h
- Merged PRs (30d)
- 272
Description
Follow up to https://github.com/lance-format/lance/pull/6223, which implements it for IVF_PQ indexes.
Cache codec serializes and deserializes index cache entries.
Key requirements:
- Add a unit test that validates that after prewarm a serializing backend will not require IO to serve HNSW queries.
- Use zero copy Arrow IPC utilities to do serde
lance-arrow/src/ipc.rs
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reviewing PR #6223, which implements CacheCode for IVF_PQ indices, and inspect lance-arrow/src/ipc.rs for the zero-copy Arrow IPC utilities. Then trace the HNSW cache and prewarm path. Done means a unit test confirms that a serializing backend serves prewarmed HNSW queries without IO.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- rust
- Domain
- search
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 55/100