C
Corrective RAG (CRAG)
Self-correcting RAG pipeline that detects and fixes retrieval errors
Open SourceFree
About
Corrective RAG (CRAG) implements a self-correcting retrieval pipeline: after initial retrieval, a grader agent evaluates whether the retrieved documents actually answer the question. If the retrieval is poor, CRAG triggers web search as a fallback, then re-evaluates. This loop dramatically reduces hallucination from irrelevant context — a common RAG failure mode. Part of the awesome-llm-apps collection.
Details
| Pattern | loop |
| Steps | Retrieve documents from vector store → Grade relevance of retrieved documents → If poor: trigger web search fallback → Re-evaluate and generate grounded response |
| Use Cases | Robust document Q&A, Hallucination reduction, Production RAG pipelines |
Tags
ragself-correctingretrievalworkflow
Quick Info
- Organization
- Shubham Saboo
- Pricing
- open-source
- Free Tier
- Yes
- Updated
- Apr 1, 2026
104.2Ktoday74
Also in Workflows
A
AI Competitor Intelligence Team
Multi-agent team that tracks and analyzes the competitive landscape
OSSFree
Shubham Saboo
104.2Ktoday74
A
AI Finance Agent Team
Collaborative multi-agent team for comprehensive financial analysis
OSSFree
Shubham Saboo
104.2Ktoday74
A
AI Legal Agent Team
Multi-agent legal analysis team with cloud and local deployment options
OSSFree
Shubham Saboo
104.2Ktoday74