What happens when your RAG system retrieves the wrong documents?
Or when the retrieved context is not enough to answer the question?
A traditional RAG pipeline usually doesn't think twice and its path is so its a single attempt generated answer.
"Retrieve → Generate → Answer"
What I built
Retrieve → Reason → Verify → Correct → Answer
I created a collection of self contained notebooks demonstrating different Agentic RAG patterns with LangGraph. Each notebook focuses on a practical pattern that you can understand, experiment with and adapt to your own AI projects.
What happens when your RAG system retrieves the wrong documents? Or when the retrieved context is not enough to answer the question?
A traditional RAG pipeline usually doesn't think twice and its path is so its a single attempt generated answer. "Retrieve → Generate → Answer"
What I built
Retrieve → Reason → Verify → Correct → Answer
I created a collection of self contained notebooks demonstrating different Agentic RAG patterns with LangGraph. Each notebook focuses on a practical pattern that you can understand, experiment with and adapt to your own AI projects.
Free version: https://github.com/ChandulaSenevirathna/Agentic_RAG
Advanced version: https://chandula7.gumroad.com/l/Advanced_RAG_LangGraph_Patte...
I read through the notebooks and learn lot of stuff about langgraph i dint knew before huge thnx for this.
I will add more useful notebooks in future
That makes sense why i was getting some very bad results in my project....
Now you can make better results
Can you add a notebook about Fan out methods in langgraph
Sure i will note that