Improve RAG grounding and ingestion pipeline#7
Merged
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
improves grounding for document QA by tightening retrieval-to-generation flow and adding a lightweight ingestion pipeline check.
Changes included:
increased context passed to generation from the top reranked results
added retriever and reranker score filtering to reduce vague or weakly grounded answers
simplified the QA prompt for better behavior with smaller instruct models
standardized the fallback response to Information not found in the document.
added a lightweight ingestion smoke test for routing, table processing, and chunk generation
This should make uploaded-PDF responses more precise and reduce hallucinated or overly vague answers while keeping the current lightweight RAG setup intact