feat(search): add SQLite FTS5 post-build search index script - #801
Open
jeevantelukula wants to merge 1 commit into
Open
jeevantelukula wants to merge 1 commit into
jeevantelukula wants to merge 1 commit into
Conversation
Sphinx's searchindex.js stores only boolean term membership with no TF-IDF or field weighting, works good for manual browser search but gives poor ranking for programmatic (MCP/AI agent) search queries. Add build_searchindex.py that runs after sphinx-build via html make target, parses HTML output, extracts the weighted fields (based on title, code_blocks, image_alt and body_text) and writes searchindex.db with a BM25-ranked FTS5 index. MCP server queries this DB to return accurately ranked doc pages to AI agents. Also add beautifulsoup4 additionally to docker deps. Signed-off-by: Telukula Jeevan Kumar Sahu <j-sahu@ti.com>
jeevantelukula
requested review from
StaticRocket,
VeeruPrudhvi,
cshilwant,
gehariprasath,
praneethbajjuri and
uditkumarti
as code owners
September 25, 2026 10:01
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Sphinx's searchindex.js stores only boolean term membership with no TF-IDF or field weighting, works good for manual browser search but gives poor ranking for programmatic (MCP/AI agent) search queries.
Add build_searchindex.py that runs after sphinx-build via html make target, parses HTML output, extracts the weighted fields (based on title, code_blocks, image_alt and body_text) and writes searchindex.db with a BM25-ranked FTS5 index. MCP server queries this DB to return accurately ranked doc pages to AI agents.
Also add beautifulsoup4 additionally to docker deps.