add tag-based indexing#3
Merged
Merged
Conversation
Documents are now indexed with structured tags (source, content_type, domain, topic, namespace, lexicon_type, language) using a hybrid vocabulary: controlled core enums plus generated tags derived from content metadata. Tags are stored in txtai's tags column and queried via SQL WHERE clauses, replacing the previous post-retrieval filtering that frequently returned empty results when top-k ANN candidates were dominated by other sources. Key changes: - parser: add tags field to ContentChunk, tag builder functions per source, encode_tags() for pipe-delimited txtai storage - indexer: write tags at index time, persist in chunk_meta.json, SQL-filtered _filtered_search() with fallback, backward-compat for old indexes without tags - tools: add content_type filter to search_atproto_docs - tests: update regression tests for tag-aware fake embeddings, add test_tags.py (37 tests covering encoding, builders, filtered search, metadata round-trip), add compare_search_quality.py
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Documents are now indexed with structured tags (source, content_type,
domain, topic, namespace, lexicon_type, language) using a hybrid
vocabulary: controlled core enums plus generated tags derived from
content metadata. Tags are stored in txtai's tags column and queried
via SQL WHERE clauses, replacing the previous post-retrieval filtering
that frequently returned empty results when top-k ANN candidates were
dominated by other sources.