Build a Self-Corrective RAG App with LangGraph Cloud

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/vbarda/pandas-rag-...
Notebook: github.com/vbarda/pandas-rag-...
LangGraph Cloud docs: langchain-ai.github.io/langgr...
Check out our other resources for self-RAG and corrective RAG below
- Self-RAG video: • Self-reflective RAG wi...
- Self-RAG notebook: github.com/langchain-ai/langg...
- Corrective RAG video: • Building Corrective RA...
- Corrective RAG notebook: github.com/langchain-ai/langg...

[@ai-touch9]

good content, i appreciate the concept of Self-Corrective RAG.
May i know where exactly this use case is used, i mean for organization chatbot they wouldnt be interested in going for web search, if they are going for web search there is no need for pre-loading couple of urls.. i'm just curios to know where this comes handy..

[@darkmatter9583]

hi , love your videos thank you very much for the effort, this title looked good, but you are using chroma thats vector but if i want lang graph and neo4j?

[@93simongh]

self-hosted version tutorial: ruclips.net/video/uZoz3T3Z6-w/видео.html