corrective-rag

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

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

Self-correcting agentic RAG with LangGraph — combines Adaptive, Corrective, and Self-RAG. Routes queries, grades retrieved documents, and checks answers for hallucinations. Runs fully local on Ollama.

Self-updating research assistant using RAPTOR, corrective RAG, and arXiv retrieval.

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.

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.

CRAG with MinerU

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

adaptive rag, corrective rag and agentic rag examples using langgraph

A self-correcting Agentic RAG pipeline with MongoDB Vector Search, built to run entirely on constrained local hardware.

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

Autonomous 10-Agent LangGraph Swarm transforming messy industrial feeds into 252-column master catalog truth with in-memory DuckDB (27K brands, 161K LOVs), SHA-256 DBOM cryptographic provenance, AST parametric search, and closed-loop active learning.

Runnable LangGraph, CRAG, and GraphRAG lab tested against a production hybrid-RAG baseline.

A Corrective RAG application which downloads a YouTube video, transcribes it, generate embeddings and store them in ChromaDB to allow users to perform Q&A over the Video content. This implements LLM-as-a-Judge for retrieval accuracy, Query-rewriting and WebSearch as a fallback.

Agentic RAG system with five workflow modes from Naive to Deep, routing each question to the cheapest path that answers it well, fusing dense and BM25 retrieval through Reciprocal Rank Fusion with CrossEncoder reranking, verifying groundedness and citations, and gating risky answers behind a human-in-the-loop approval queue.

A full-stack Next.js RAG assistant for Udemy course subtitles. Features advanced query translation, hybrid vector/SQL retrieval, Reciprocal Rank Fusion (RRF), LangGraph-based Corrective RAG (CRAG), and input/output guardrails.

企业级 Agentic RAG 技术文档问答系统