一、前言

微软近期发布了知识图谱工具 GraphRAG 2.0.0，支持基于本地大模型（Ollama）快速构建知识图谱，显著提升了RAG（检索增强生成）的效果。本文手把手教你如何从零部署，并附踩坑记录和性能实测！

二、环境准备

1. 创建虚拟环境

推荐使用 Python 3.12.4（亲测兼容性较佳）：

conda create -n graphrag200 python=3.12.4
conda activate graphrag200

2. 拉取源码

建议通过Git下载最新代码（Windows用户需提前安装Git）：

git clone https://github.com/microsoft/graphrag.git
cd graphrag

    （附：若直接下载压缩包解压，解压完后需创建一个仓库，不然后续会报错）

        创建仓库方法：

git init
git add .
git commit -m "Initial commit"

3. 安装依赖

一键安装所需依赖包：

pip install -e .

4. 创建输入文件夹

用于存放待处理的文档（Windows可以直接手动创建）：

mkdir -p ./graphrag_ollama/input

将数据集放入input目录即可。

三、关键配置修改

1. 初始化项目

执行初始化命令（注意与旧版参数不同）：

python -m graphrag init --root ./graphrag_ollama

2. 修改settings.yaml

核心配置项（需按需调整）：

• 模型设置：使用Ollama本地模型

 注意修改一下圈出的几个地方

测试小文件时，建议把chunks改小：

 修改结果如下：

• ### This config file contains required core defaults that must be set, along with a handful of common optional settings.
  ### For a full list of available settings, see https://microsoft.github.io/graphrag/config/yaml/
  
  ### LLM settings ###
  ## There are a number of settings to tune the threading and token limits for LLM calls - check the docs.
  
  models:
    default_chat_model:
      type: openai_chat # or azure_openai_chat
      api_base: http://192.168.0.167:11434/v1
      # api_version: 2024-05-01-preview
      auth_type: api_key # or azure_managed_identity
      api_key: ${GRAPHRAG_API_KEY} # set this in the generated .env file
      # audience: "https://cognitiveservices.azure.com/.default"
      # organization: <organization_id>
      model: deepseek-r1:32b
      # deployment_name: <azure_model_deployment_name>
      encoding_model: cl100k_base # automatically set by tiktoken if left undefined
      model_supports_json: true # recommended if this is available for your model.
      concurrent_requests: 25 # max number of simultaneous LLM requests allowed
      async_mode: threaded # or asyncio
      retry_strategy: native
      max_retries: -1                   # set to -1 for dynamic retry logic (most optimal setting based on server response)
      tokens_per_minute: 0              # set to 0 to disable rate limiting
      requests_per_minute: 0            # set to 0 to disable rate limiting
    default_embedding_model:
      type: openai_embedding # or azure_openai_embedding
      api_base: http://192.168.0.167:11434/v1
      # api_version: 2024-05-01-preview
      auth_type: api_key # or azure_managed_identity
      api_key: ${GRAPHRAG_API_KEY}
      # audience: "https://cognitiveservices.azure.com/.default"
      # organization: <organization_id>
      model: bge-m3:latest
      # deployment_name: <azure_model_deployment_name>
      encoding_model: cl100k_base # automatically set by tiktoken if left undefined
      model_supports_json: true # recommended if this is available for your model.
      concurrent_requests: 25 # max number of simultaneous LLM requests allowed
      async_mode: threaded # or asyncio
      retry_strategy: native
      max_retries: -1                   # set to -1 for dynamic retry logic (most optimal setting based on server response)
      tokens_per_minute: 0              # set to 0 to disable rate limiting
      requests_per_minute: 0            # set to 0 to disable rate limiting
  
  vector_store:
    default_vector_store:
      type: lancedb
      db_uri: output\lancedb
      container_name: default
      overwrite: True
  
  embed_text:
    model_id: default_embedding_model
    vector_store_id: default_vector_store
  
  ### Input settings ###
  
  input:
    type: file # or blob
    file_type: text # or csv
    base_dir: "input"
    file_encoding: utf-8
    file_pattern: ".*\\.txt$$"
  
  chunks:
    size: 200
    overlap: 50
    group_by_columns: [id]
  
  ### Output settings ###
  ## If blob storage is specified in the following four sections,
  ## connection_string and container_name must be provided
  
  cache:
    type: file # [file, blob, cosmosdb]
    base_dir: "cache"
  
  reporting:
    type: file # [file, blob, cosmosdb]
    base_dir: "logs"
  
  output:
    type: file # [file, blob, cosmosdb]
    base_dir: "output"
  
  ### Workflow settings ###
  
  extract_graph:
    model_id: default_chat_model
    prompt: "prompts/extract_graph.txt"
    entity_types: [organization,person,geo,event]
    max_gleanings: 1
  
  summarize_descriptions:
    model_id: default_chat_model
    prompt: "prompts/summarize_descriptions.txt"
    max_length: 500
  
  extract_graph_nlp:
    text_analyzer:
      extractor_type: regex_english # [regex_english, syntactic_parser, cfg]
  
  extract_claims:
    enabled: false
    model_id: default_chat_model
    prompt: "prompts/extract_claims.txt"
    description: "Any claims or facts that could be relevant to information discovery."
    max_gleanings: 1
  
  community_reports:
    model_id: default_chat_model
    graph_prompt: "prompts/community_report_graph.txt"
    text_prompt: "prompts/community_report_text.txt"
    max_length: 2000
    max_input_length: 8000
  
  cluster_graph:
    max_cluster_size: 10
  
  embed_graph:
    enabled: false # if true, will generate node2vec embeddings for nodes
  
  umap:
    enabled: false # if true, will generate UMAP embeddings for nodes (embed_graph must also be enabled)
  
  snapshots:
    graphml: false
    embeddings: false
  
  ### Query settings ###
  ## The prompt locations are required here, but each search method has a number of optional knobs that can be tuned.
  ## See the config docs: https://microsoft.github.io/graphrag/config/yaml/#query
  
  local_search:
    chat_model_id: default_chat_model
    embedding_model_id: default_embedding_model
    prompt: "prompts/local_search_system_prompt.txt"
  
  global_search:
    chat_model_id: default_chat_model
    map_prompt: "prompts/global_search_map_system_prompt.txt"
    reduce_prompt: "prompts/global_search_reduce_system_prompt.txt"
    knowledge_prompt: "prompts/global_search_knowledge_system_prompt.txt"
  
  drift_search:
    chat_model_id: default_chat_model
    embedding_model_id: default_embedding_model
    prompt: "prompts/drift_search_system_prompt.txt"
    reduce_prompt: "prompts/drift_search_reduce_prompt.txt"
  
  basic_search:
    chat_model_id: default_chat_model
    embedding_model_id: default_embedding_model
    prompt: "prompts/basic_search_system_prompt.txt"
  

  四、构建知识图谱

  执行索引命令（算力警告：亲测4090-24G显卡处理2万字需3小时）：

  python -m graphrag index --root ./graphrag_ollama

  五、知识图谱查询

  支持多种查询方式，按需选择：

• 方法	命令示例	用途
  全局查询	python -m graphrag query --method global --query "知识图谱定义"	跨文档综合分析
  局部查询	python -m graphrag query --method local --query "知识图谱定义"	单文档精准检索
  DRIFT查询	python -m graphrag query --method drift --query "知识图谱定义"	动态漂移分析
  基础查询	python -m graphrag query --method basic --query "知识图谱定义"	传统RAG检索

六、注意事项

1. 模型路径：确保Ollama服务已启动，且模型名称与配置一致（如deepseek-r1:32b需提前拉取）。

2. 算力需求：小规模数据集建议使用GPU加速，CPU模式耗时可能成倍增加。

3. 文件编码：输入文档需为UTF-8编码，否则可能报错。

4. 配置备份：修改settings.yaml前建议备份原始文件。

七、总结

GraphRAG 2.0.0大幅优化了知识图谱的构建效率，结合本地模型可实现隐私安全的行业级应用。若遇到部署问题，欢迎在评论区留言交流！

相关资源：

 GraphRAG GitHub仓库

Ollama模型库

原创声明：本文为作者原创，未经授权禁止转载。如需引用请联系作者。

---

点赞关注，技术不迷路！ 👍
你的支持是我更新的最大动力！ ⚡