← All blueprints

Corrective RAG LangGraph

blueprint · 3 agents
20000★ stars

What it does

The CRAG paper as a LangGraph tutorial: a retrieval grader scores each document, weak retrievals trigger query rewriting and a web-search fallback, and generation only runs on context that passed. The defensive-retrieval companion to Adaptive RAG.

From the community

langchain-ai/langgraphopen-source example · MIT · indexed by SocketCatview source ↗

Agent flow

1 · Retriever
Pull from the index
vectorstore
2 · Grader
Score relevance
no tools · reasoning
3 · Fallback
Rewrite & web-search
tavily search
get the code
View the source on GitHub ↗

This blueprint lives in its authors' repository. SocketCat indexes it and links you to the real thing.

More in Core patterns

Browse all →

Supervisor Team

com.socketcat/supervisor-team
LangGraph

A supervisor decides who works next — a researcher who searches or a coder who edits the repo — and assembles the result when the work is done.

★ 21402 servers
⑂ 312

Deep Research

com.socketcat/deep-research
LangGraph

Splits a hard question into sub-questions, researches them in parallel to keep the wall-clock low, then synthesizes one brief with citations.

★ 17551 server
⑂ 254

Agentic RAG

com.socketcat/agentic-rag
LangGraph

Retrieval that doesn't trust its first search: it grades the results, rewrites the query when they're weak, and only answers once the context is good.

★ 16801 server
⑂ 241