Add vector query planning using centroids and cluster probing
- Dominant language
- Java
- Stars
- 6.2k
- Forks
- 2.5k
- Avg merge
- 2d 8h
- Merged PRs (30d)
- 111
Description
Parent: #19094
Related: #18676
## Summary
Add vector query planning using centroids and cluster probing.
## Scope
- load manifest, centroid, and quantizer metadata
- select probe clusters
- derive posting ranges to scan
- support query planning inputs needed by the Spark path
## Acceptance Criteria
- planning logic is isolated from scoring and reranking
- probe selection behavior is explicit
- posting ranges are derived from metadata state
Contributor guide
No contributing guide indexed for this repository
Research direction
Start with parent issue #19094 and related issue #18676, then trace the Spark path and its query-planning entry points. Review how manifest, centroid, quantizer, and posting-range metadata are represented. Done means isolated planning logic with explicit probe selection and ranges derived from metadata, without scoring or reranking.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- java, spark
- Domain
- data-engineering, search
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 42/100