feat: structure RAG context output to respect relationship directionality #807#808
Open
suhaniiz wants to merge 2 commits into
Open
feat: structure RAG context output to respect relationship directionality #807#808suhaniiz wants to merge 2 commits into
suhaniiz wants to merge 2 commits into
Conversation
|
@suhaniiz is attempting to deploy a commit to the param20h's projects Team on Vercel. A member of the Team first needs to authorize it. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
📋 PR Checklist
🔗 Related Issue
Closes #807
📝 What does this PR do?
This PR resolves the issue where the knowledge graph relationship context returned to the LLM had its subject/object orientation scrambled due to alphabetical key deduplication.
get_entity_contextto capture the matched query entity explicitly as the primarysubject.dedup_keyto maintain safe weight accumulation and co-occurrence deduplication.item['subject']anditem['object']).This ensures that the final RAG context sentences present information naturally from the user's search intent perspective (e.g., "Apple is related to Fruit" instead of randomly outputting "Fruit is related to Apple").
🗂️ Type of Change
🧪 How was this tested?
uvicorn app.main:app --reload)📸 Screenshots (if UI change)
N/A
The core underlying graph structure remains safely undirected (
nx.Graph). This fix handles orientation layout gracefully strictly at the dictionary tracking and response formulation levels, ensuring zero breaking changes to existing data pipeline parsers.✅ Self-Review Checklist
dev, notmainmainbranch or any HuggingFace deployment config