feat(retrieval): word-level map-unit BM25 tokens - #380
Merged
Conversation
Replace character-level CJK tokenization with the shared jieba path and bump map-unit index format to v2 so query hashes match stored tokens. Add --tokens-only/--skip-current-format for lightweight reindex after tokenizer changes without rebuilding manifests or namespace snapshots. Co-authored-by: Cursor <cursoragent@cursor.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
text_utils), aligned withdocument_chunkspublication.MAP_UNIT_INDEX_FORMAT_VERSIONto 2; classic and map-nav scoring treat older indexes as incomplete.--tokens-only(rebuild map-unit tokens/index only) and--skip-current-format(resume-friendly).Production after merge/deploy
Do not run full
--apply(rewrites manifests/snapshots again). Use:python /app/scripts/backfill_map_unit_indexes.py --apply --tokens-only # optional resume: python /app/scripts/backfill_map_unit_indexes.py --apply --tokens-only --skip-current-format python /app/scripts/backfill_map_unit_indexes.py --check--checkmust report all namespaces READY (format_version=2).Test plan
make check(ruff + pyright)test_knowhere_hybrid_tokenize.py(word tokens, no single-char CJK)--checkMade with Cursor