How to build a simplified Corrective RAG assistant with Amazon Bedrock using LLMs, Embeddings model, Knowledge Bases for Amazon Bedrock, and Agents for Amazon Bedrock.

Production-grade RAG system with hybrid retrieval (Qdrant + Elasticsearch + Neo4j), Corrective RAG via LangGraph, feedback-driven reward model, and RAGAS evaluation dashboard

CRAG with MinerU

An engineering-oriented Agentic RAG system built with FastAPI, LangGraph and Qdrant, featuring multi-user document isolation, hybrid retrieval, reranking, corrective retrieval, document-version-aware conversations and streaming Web UI.

Agentic RAG system with LangGraph, hybrid BM25+FAISS retrieval, cross-encoder reranking, Corrective RAG, FastAPI, RAGAs evaluation, and Docker deployment

adaptive rag, corrective rag and agentic rag examples using langgraph

Corrective RAG with LangGraph: evaluates retrieval quality, routes to web search when needed, refines context, and generates grounded answers.

Corrective-RAG flood and disaster relief assistant for Assam, grounded in 27 official NDMA/ASDMA/CWC/IMD documents, with a live situational map computing real-time flood risk from rainfall and river discharge data on satellite imagery. Falls back to government-only web search when retrieval is unreliable.

Successfully developed a Healthcare AI Clinical Decision Support System, leveraging LangGraph, GPT-4o-mini, and PubMed to deliver real-time patient risk stratification, evidence-based treatment recommendations, and personalized clinical road maps with integrated drug safety validations.

Automated Agentic GitHub PR review bot — GPT-5 agentic system with 3 tools: Corrective RAG (project context), MCP web search (live docs), and ruff linter. Redis-Celery task queue. Structured review comments posted automatically on every PR.

It is a enhanced version of Past Portals with Multi-Modal Input system , C-RAG , Feedback Loop, and Voice-First Conversational AI bot

AutoDocThinker is a production-ready Agentic RAG system that ingests PDFs, DOCX, URLs, and raw text into a Hybrid Search index (ChromaDB + BM25 + RRF + CrossEncoder), then answers natural language queries through four selectable LangGraph workflows — Naive, Advanced, CRAG, and Self-RAG.

Context-aware tool for automated BDD test generation and execution using RAG, VectorDB, and LLaMA.

An intelligent GitHub assistant powered by Corrective RAG (CRAG), built with LangGraph and using MCP, that retrieves and refines information from live GitHub data to deliver accurate answers.

Agentic Corrective RAG with Hybrid Retrieval (Dense ChromaDB + Sparse BM25 + RRF Fusion) and RLHF (Reinforcement Learning from Human Feedback) — built with LangGraph, LangChain, and FastAPI.

Production-grade Corrective RAG system in LangGraph — scores retrieved chunks before generation, falls back to web search when needed, and filters context to sentence level.

Corrective RAG pipeline using LangGraph — evaluates retrieval quality and falls back to web search when local docs are insufficient

Built a multi-agent corrective RAG pipeline with LangChain, ChromaDB, and OpenAI embeddings, including document ingestion, retrieval evaluation, query correction, and context-aware response generation.

Explainable Corrective RAG platform with retrieval evaluation, adaptive routing, source citations, Streamlit/FastAPI demos, and RAGAS benchmarking.

An Adaptive Customer Support Agent implementing Corrective RAG (CRAG) via a LangGraph state machine. It uses Gemini 1.5 Flash to grade local ChromaDB retrievals, dynamically falling back to a live DuckDuckGo web search if the context is irrelevant to eliminate hallucinations.