This repository implements an Advanced Retrieval-Augmented Generation (RAG) pipeline with context-aware query decomposition for high-quality information retrieval. It includes redundancy filtering, cross-encoder–based document reranking, and controlled generation.
nlp information-retrieval ai context-aware semantic-search pinecone document-search rag full-stack-application fastapi vector-database cross-encoder langchain retrieval-augmented-generation query-routing step-back-prompting
-
Updated
Nov 27, 2025 - Jupyter Notebook