Agentic RAG for Korean RFP intelligence — extractive grounded-answer pipeline with metadata-first retrieval, comparison-aware balanced top-k, and bootstrap-CI eval rigor (ADR-driven).
-
Updated
Jun 10, 2026 - Python
Agentic RAG for Korean RFP intelligence — extractive grounded-answer pipeline with metadata-first retrieval, comparison-aware balanced top-k, and bootstrap-CI eval rigor (ADR-driven).
Course study RAG tutor with keyword, embedding, and hybrid retrieval, grounded answers, chunk_id evidence, and Streamlit UI.
Add a description, image, and links to the grounded-answer topic page so that developers can more easily learn about it.
To associate your repository with the grounded-answer topic, visit your repo's landing page and select "manage topics."