本地部署graphRAG

安装

python安装12的

通过 pycharm新建项目 ,方便调试，方便在依赖包的代码中添加代码定位错误信息；

安装 graphrag 1.2.0版本。

在终端里输入 pip install graphrag==1.2.0

创建目录ragtest

然后在其下创建子目录input 拷贝一些文件到这个input文件夹，这些文件就是你的私人的知识库里的文件了

初始化

graphrag init --root ./ragtest

修改配置文件

修改.evn文件，注意调整成自己的key GRAPHRAG_API_KEY=sk-XXX

修改setting.yaml

yaml 复制代码

### 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.

encoding_model: cl100k_base # this needs to be matched to your model!

llm:
  api_key: ${GRAPHRAG_API_KEY} # set this in the generated .env file
  type: openai_chat # or azure_openai_chat

  model: deepseek-ai/DeepSeek-V3
  api_base: https://api.siliconflow.cn/v1
  model_supports_json: false # recommended if this is available for your model.
  # audience: "https://cognitiveservices.azure.com/.default"
  # api_base: https://<instance>.openai.azure.com
  # api_version: 2024-02-15-preview
  # organization: <organization_id>
  # deployment_name: <azure_model_deployment_name>

parallelization:
  stagger: 0.3
  # num_threads: 50

async_mode: threaded # or asyncio

embeddings:
  async_mode: threaded # or asyncio
  vector_store: 
    type: lancedb # one of [lancedb, azure_ai_search, cosmosdb]
    db_uri: 'output\lancedb'
    collection_name: default
    overwrite: true
  llm:
    api_key: ${GRAPHRAG_API_KEY}
    type: openai_embedding # or azure_openai_embedding
    model: BAAI/bge-m3
    api_base: https://api.siliconflow.cn/v1
    # api_base: https://<instance>.openai.azure.com
    # api_version: 2024-02-15-preview
    # audience: "https://cognitiveservices.azure.com/.default"
    # organization: <organization_id>
    # deployment_name: <azure_model_deployment_name>

### Input settings ###

input:
  type: file # or blob
  file_type: text # or csv
  base_dir: "input"
  file_encoding: utf-8
  file_pattern: ".*\.txt$"

chunks:
  size: 300
  overlap: 100
  group_by_columns: [id]

### Storage settings ###
## If blob storage is specified in the following four sections,
## connection_string and container_name must be provided

cache:
  type: file # one of [blob, cosmosdb, file]
  base_dir: "cache"

reporting:
  type: file # or console, blob
  base_dir: "logs"

storage:
  type: file # one of [blob, cosmosdb, file]
  base_dir: "output"

## only turn this on if running `graphrag index` with custom settings
## we normally use `graphrag update` with the defaults
update_index_storage:
  # type: file # or blob
  # base_dir: "update_output"

### Workflow settings ###

skip_workflows: []

entity_extraction:
  prompt: "prompts/entity_extraction.txt"
  entity_types: [organization,person,geo,event]
  max_gleanings: 1

summarize_descriptions:
  prompt: "prompts/summarize_descriptions.txt"
  max_length: 500

claim_extraction:
  enabled: false
  prompt: "prompts/claim_extraction.txt"
  description: "Any claims or facts that could be relevant to information discovery."
  max_gleanings: 1

community_reports:
  prompt: "prompts/community_report.txt"
  max_length: 2000
  max_input_length: 3000

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
  transient: 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:
  prompt: "prompts/local_search_system_prompt.txt"

global_search:
  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:
  prompt: "prompts/drift_search_system_prompt.txt"
  reduce_prompt: "prompts/drift_search_reduce_prompt.txt"

basic_search:
  prompt: "prompts/basic_search_system_prompt.txt"

改成这行：Return output as a well-formed JSON-formatted string with the following format,but don't output in markdown format, the output string should be directly usable by json.load():

建立索引

graphrag index --root ./ragtest

查询测试

graphrag query --root ./ragtest --method global --query "虚竹是谁？"

提示词生成

graphrag prompt-tune --root .\ragtest --domain 小说 --language 中文 --chunk-size 200 --output .\prompt-cs 这会在.\prompt-cs下生成针对计算机领域、中文文本的提示词。接下来把新生成的提示词覆盖.\ragtest\prompt下默认的提示词，然后构建索引。

不建议直接覆盖，由于是通过模型生成的提示词，可能会有问题，需要排查。

可能报错

❌ create_final_community_reports ：修改setting.yaml 中的模型与参数，可通过log日志查询问题点，调整参数，例如：

❌ generate_text_embeddings ：

可能的原因

模型参数配置不当 ：模型的参数可能配置不当，例如 max_input_tokens 设置过大或过小，导致模型无法生成有效的 JSON 输出。
模型输入内容复杂或格式不匹配：输入内容可能过于复杂或不符合模型的输入格式要求。
网络问题或 API 调用失败：网络不稳定或 API 调用失败可能导致模型无法正常响应。
模型能力不足：模型可能无法处理某些特定的输入内容，导致生成的输出不符合预期格式。

参考链接：feige.team/docs/aiagen...