fix(knowledge): keep rerank passages nonempty#345
Draft
SiyaoZheng wants to merge 1 commit into
Draft
Conversation
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Ensure knowledge rerank providers always receive a non-empty passage without changing the content returned by the search API.
Knowledge-topic content is loaded from SQLite before reranking. A valid topic can have blank content, which previously passed an empty document to the configured rerank provider. Some providers reject empty documents, while others return unstable scores.
This change adds a dedicated
rerank_contentfield with the fallback ordercontent -> summary -> topic_name -> topic id -> generic label. The originalcontentfield remains authoritative and unchanged forSearchHit.content.Area
Verification
Checklist
main..envfiles, dependency folders, or generated output.Notes for Reviewers
The tests cover SQLite content, metadata fallbacks, the all-blank case, and preservation of the API-facing content value.
By submitting this pull request, I agree that my contribution is licensed under the Apache License 2.0.