feat: hybrid search with LanceDB FTS + RRF reranking#6
Merged
Conversation
Combine vector similarity with keyword matching using LanceDB's built-in tantivy FTS index and RRFReranker. FTS index rebuilds automatically after sync. Falls back to vector-only when unavailable. No new dependencies or config needed.
tobocop2
force-pushed
the
feature/hybrid-search
branch
from
6b37f25 to
e5e1172
Compare
Convert SearchChunk from a TypedDict (dict with type hints) to a proper Pydantic BaseModel. LanceDB dicts are converted at the store boundary via _from_row(). All downstream code uses dot access instead of bracket access. clean_result() simplifies to model_dump(exclude_none=True). Eliminates underscore-prefixed field names (_distance, _relevance_score) that were LanceDB artifacts leaking through the entire codebase.
tobocop2
force-pushed
the
feature/hybrid-search
branch
2 times, most recently
from
543c4ff to
847c417
Compare
tobocop2
force-pushed
the
feature/hybrid-search
branch
from
b2c03ab to
fdf8f43
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Hybrid search using LanceDB's built-in tantivy FTS index and
RRFReranker. No new dependencies or config needed.syncSearchChunkTypedDict with a Pydantic model — dot access everywhere, no more underscore-prefixed LanceDB field names leaking throughAlso, redesign website 😬