Adaptive RAG LangGraph
blueprint · 3 agents
20000★ stars
What it does
Combines query routing with self-corrective retrieval: a router sends the question to the vectorstore or straight to web search, graders check relevance of retrieved documents and detect hallucination in the draft answer, and the graph rewrites or re-routes until the answer is grounded.
Agent flow
1 · Router
Pick the retrieval path
no tools · reasoning
2 · Retriever
Vectorstore or web
vectorstore, tavily
3 · Graders
Check relevance & grounding
no tools · reasoning
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