In this tutorial, we create a Self-Corrective RAG application for answering questions about Pandas documentation using LangGraph Cloud. We implement ideas from both self-RAG and corrective RAG to flexibly handle model hallucinations. You'll see how to check for hallucinations after an answer is generated, and check for answer relevancy before returning the user question.
GitHub repo: github.com/vba...
Notebook: github.com/vba...
LangGraph Cloud docs: langchain-ai.g...
Check out our other resources for self-RAG and corrective RAG below
- Self-RAG video: • Self-reflective RAG wi...
- Self-RAG notebook: github.com/lan...
- Corrective RAG video: • Building Corrective RA...
- Corrective RAG notebook: github.com/lan...