Repository navigation
Round 14: improve retrieval quality and document workflows - #140
Merged
Merged
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Round 14 adds lossless Turkish article chunking for new revisions, optional BGE reranking, and query embedding outside the shared SQLite search lock. The frozen dev benchmark selects vector weight 8 with reranking off by default (MRR 0.3953 → 0.5663).
The SDK and CLI now report terminal chunk failures promptly and support deletion by source. Search cache configuration is explicit, OpenAI/Ollama SDKs become core dependencies, and tag releases use PyPI trusted publishing.
Validation at 95c554f:
Benchmark methodology and limitations are recorded in docs/retrieval-and-graph.md. Ambiguous admitted chunk prefixes fail closed with HTTP 409, as documented and tested.