Skip to content
This page is not translated yet — showing the original. We never ship machine translation as a placeholder.
Needs tinkeringMIT⚪ Tested only

GraphRAG

In one line:GraphRAG 是一个给要让模型读懂整本文档集的人用的开源流水线,先建知识图谱再回答问题。

GraphRAG 是一个给要让模型读懂整本文档集的人用的开源流水线,先建知识图谱再回答问题。

Official source

We host and mirror nothing — the official page is the source of truth.

No hotlinkable official icon; showing a generated placeholderG Microsoft Researchhttps://github.com/microsoft/graphragOpen official page
Official sourceYou are leaving AIWorksWell for Microsoft Research. That site is not under our control; its content, privacy and security are its own responsibility. Please judge for yourself.

Install prompt

Copy it, paste it into your AI (Claude Code, Codex, ChatGPT…), and it installs and verifies for you.

48 lines
我需要你帮我在我的机器上安装并运行一个软件。

【软件信息】
名称:GraphRAG
用途:GraphRAG 是一个给要让模型读懂整本文档集的人用的开源流水线,先建知识图谱再回答问题。
官方来源:https://github.com/microsoft/graphrag
许可:MIT
Scroll inside the box with your mouse wheel — copying still gives you the full prompt1486 chars

Copy → paste into your own AI → it installs for you

Contact the original author (Microsoft Research)

Bugs in the software itself go to the author's own official channel — that is where they actually receive them. We pass things on; we do not answer for the author.

Install failed?

Paste the raw error — once triaged and verified it is written back here, so the next person's AI avoids it. No login needed.

About this entry

What it is

GraphRAG 是微软研究院开源的数据流水线与转换套件(MIT 许可),用大模型从非结构化文本里抽出结构化数据。来源:https://microsoft.github.io/graphrag/https://microsoft.github.io/graphrag/

  • 先建知识图谱,再让模型在图上回答通盘性问题
  • 官方定位是"叙事类私有数据"——答案散在大量段落里的那种
  • 提供命令行快速上手

Getting it running

主推「复制提示词」——粘贴给你的 AI(Claude Code / Codex / ChatGPT)代装。人工兜底:pip 装包,按官方命令行快速上手建一个索引,再对同一批文档提一个需要通盘理解的问题。验证:能给出带着图结构依据的回答。来源:https://microsoft.github.io/graphrag/get_started/https://microsoft.github.io/graphrag/get_started/

以上坑来自 https://microsoft.github.io/graphrag/https://microsoft.github.io/graphrag/ 与它的官方文档。

来源与署名

Mentioned from:GitHub · 原作者 Microsoft Research(MIT)。

Summary for AI

GraphRAG 是一条数据流水线,先用大模型从非结构化文本里抽出结构化事实,建成知识图谱,再让模型在这张图上回答需要通盘理解的问题。官方点明它问的是"叙事类私有数据"那一类问题——答案散在很多段落里、单次检索拼不出来的那种。它配了命令行快速上手,构建索引这一步开销不小。

A self-contained answer paragraph — this is the part AI search quotes. · Page reviewed 2026-10-22

FAQ

和普通 RAG 的区别在哪?

普通 RAG 按片段检索;它先建图,回答需要跨很多段落的问题。

能直接上生产吗?

官方说这份代码是方法演示,不是官方支持的产品。

Pitfalls / known issues

All recorded from real installs, and injected into the prompt above.

  • •官方明说这是方法演示,不是受支持的产品。
  • •建索引很贵,官方自己提醒先读文档、从小规模开始。
  • •抽取质量依赖模型,实体与关系抽错会一路错到答案。

You might also like

We store, mirror and repackage nothing. Every install path points to the author’s own official page.

Nothing here has been reviewed by an app store. Judge the source and licence yourself; you install at your own risk.