feat(capability): add LLM re-rank to capability matching#21
Merged
Conversation
Add LLM re-rank pipeline after vector search: wider recall (15 candidates, configurable) followed by dedicated LLM relevance evaluation and filtering. Re-rank runs inside InvokerForMatch, transparent to the main LLM, with graceful degradation on failure and Redis caching for repeated queries. - Add RerankEnabled, RerankRecallLimit, RerankCacheTTL and Rerank Provider config - Add Temperature and TimeoutSeconds to Provider struct - Implement rerankCapabilities with Chat-based LLM judgment - Integrate into InvokerForMatch with fallback to original results - Add Redis cache layer with xxhash keys and short TTL for empty results - Create 14 unit tests covering happy path, errors, edge cases
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Add LLM re-rank pipeline after vector search: wider recall (15 candidates, configurable) followed by dedicated LLM relevance evaluation and filtering. Re-rank runs inside InvokerForMatch, transparent to the main LLM, with graceful degradation on failure and Redis caching for repeated queries.