[Hyderabad] [Veera Venkata Satyanarayana Bandi] - Vibe Coding Submission#5
Open
Venkatbandi002 wants to merge 4 commits intonasscomAI:masterfrom
Conversation
…raints -> applied R.I.C.E framework to enforce exact categories and severity rules
…E framework specifying CMC policy scope, refusals, and correct JSON-RPC formatting
…ed RICE constraints and strict RAG logic
|
Hi there, participant! Thanks for joining our RAG-to-MCP Workshop! We're reviewing your PR for the 3 Use Cases (UC-0A, UC-RAG, UC-MCP). Once your submission is validated and merged, you'll be awarded your completion badge! Next Steps:
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR implements the strict R.I.C.E. (Role, Intent, Context, Enforcement) framework across both the UC-RAG and UC-Mcp modules to eliminate context blending, hallucination, and scope leakage. For the RAG server, it updates agents.md and skills.md with explicit operational boundaries and configures rag_server.py to use sentence-aware boundary chunking (max 400 tokens) alongside ChromaDB and SentenceTransformer for retrieval. It enforces a strict .6 similarity threshold, requiring the LLM to cite document sources and exclusively utilize retrieved context, defaulting to a standardized refusal template otherwise. Additionally, it updates the UC-Mcp tool definitions to clarify exact municipal policy scopes and properly formats responses for JSON-RPC compliance, effectively resolving previous issues with chunk boundary failures, wrong context retrieval, and vague RAG capabilities.