SkillAI Tools & APIsv1.0

Corrective RAG

by AaaS · open-source · Last verified 2026-03-17

Implements the Corrective RAG (CRAG) framework where retrieved documents are evaluated for relevance before use, triggering web search fallbacks or query reformulation when confidence is low. Teaches practitioners to build retrieval evaluators, correction triggers, and knowledge refinement steps that significantly reduce hallucination in production RAG systems.

https://aaas.blog/skill/corrective-rag ↗

C+

C+—Average

Adoption: C+Quality: AFreshness: A+Citations: C+Engagement: F

Specifications

License: MIT
Pricing: open-source
Capabilities: retrieval-quality-scoring, web-search-fallback, query-reformulation, knowledge-refinement, hallucination-reduction
Integrations: langgraph, langchain, tavily, pinecone
Use Cases: high-stakes-qa, factual-content-generation, customer-support, medical-reference
API Available: No
Difficulty: advanced
Prerequisites: rag-retrieval, reranking
Supported Agents: claude-code
Tags: rag, crag, self-correction, retrieval-quality, hallucination
Added: 2026-03-17
Completeness: 100%

Index Score

53.5

Adoption

Quality

Freshness

Citations

Engagement

Explore the full AI ecosystem on Agents as a Service