Home LangGraph
Post
Cancel

LangGraph

정보

LangChain 공식 홈페이지 LangGraph 정의

LangGraph is a library for building stateful, multi-actor applications with LLMs, built on top of (and intended to be used with) LangChain. It extends the LangChain Expression Language with the ability to coordinate multiple chains (or actors) across multiple steps of computation in a cyclic manner. It is inspired by Pregel and Apache Beam. The current interface exposed is one inspired by NetworkX.

The main use is for adding cycles to your LLM application. Crucially, this is NOT a DAG framework. If you want to build a DAG, you should just use LangChain Expression Language.

Cycles are important for agent-like behaviors, where you call an LLM in a loop, asking it what action to take next.

정리

  • TeddyNote 유튜브: LangChain 이 만든 #LangGraph 출시! LangGraph 의 멀티 에이전트 콜라보레이션 찍먹하기
  • 샘플 노트북

    다중 에이전트 협업(Multi-Agent Collaboration)

  • divide-and-conquer 접근법

엄연한 로직, flow가 존재함

This post is licensed under CC BY 4.0 by the author.

RAG 우리가 절대 쉽게 결과물을 얻을 수 없는 이유 노트

Obsidian to Notion 자동화