GraphRAG 本地部署、调试、到图形化展示过程记录

GraphRAG 本地部署、调试、到图形化展示过程记录

GraphRAG 是一种结构化的、分层的检索增强生成（RAG）方法，而不是使用纯文本片段的语义搜索方法。GraphRAG 过程包括从原始文本中提取出知识图谱，构建社区层级(这种结构通常用来描述个体、群体及它们之间的关系，帮助理解信息如何在社区内部传播、知识如何共享以及权力和影响力如何分布)，为这些社区层级生成摘要，然后在执行基于 RAG 的任务时利用这些结构。

一、本地部署

部署相对简单，看看网页即可
参考网页 https://www.graphrag.club/
大模型我用的是本地的ollama

1.查看python版本

3.10到3.12 都行

# 
python --version
Python 3.10.12

2.安装 GraphRAG

pip install graphrag

3.准备一个示例数据集

创建数据集文件夹

mkdir -p ./ragtest/input

准备一个丑小鸭的故事

sudo vi ./ragtest/input/chouxiaoya.txt

4.设置工作区变量

python -m graphrag.index --init --root ./ragtest

5.修改配置文件

.env

GRAPHRAG_API_KEY=ollama
GRAPHRAG_CLAIM_EXTRACTION_ENABLED=True

settings.yaml

encoding_model: cl100k_base
skip_workflows: []
llm:
  api_key: ollama
  type: openai_chat # or azure_openai_chat
  model: qwen2.5:7b
  model_supports_json: true # recommended if this is available for your model.
  max_tokens: 10000
  request_timeout: 210.0
  api_base: http://localhost:11434/v1/
  # api_version: 2024-02-15-preview
  # organization: <organization_id>
  # deployment_name: <azure_model_deployment_name>
  # tokens_per_minute: 150_000 # set a leaky bucket throttle
  # requests_per_minute: 10_000 # set a leaky bucket throttle
  # max_retries: 10
  # max_retry_wait: 10.0
  # sleep_on_rate_limit_recommendation: true # whether to sleep when azure suggests wait-times
  # concurrent_requests: 25 # the number of parallel inflight requests that may be made
  # temperature: 0 # temperature for sampling
  # top_p: 1 # top-p sampling
  # n: 1 # Number of completions to generate

parallelization:
  stagger: 0.3
  # num_threads: 50 # the number of threads to use for parallel processing

async_mode: threaded # or asyncio

embeddings:
  ## parallelization: override the global parallelization settings for embeddings
  async_mode: threaded # or asyncio
  # target: required # or all
  # batch_size: 16 # the number of documents to send in a single request
  # batch_max_tokens: 8191 # the maximum number of tokens to send in a single request
  llm:
    api_key: ollama
    type: openai_embedding # or azure_openai_embedding
    model: mxbai-embed-large:latest
    api_base: http://localhost:11434/v1/
    # api_version: 2024-02-15-preview
    # organization: <organization_id>
    # deployment_name: <azure_model_deployment_name>
    # tokens_per_minute: 150_000 # set a leaky bucket throttle
    # requests_per_minute: 10_000 # set a leaky bucket throttle
    # max_retries: 10
    # max_retry_wait: 10.0
    # sleep_on_rate_limit_recommendation: true # whether to sleep when azure suggests wait-times
    # concurrent_requests: 25 # the number of parallel inflight requests that may be made

chunks:
  size: 1200
  overlap: 100
  group_by_columns: [id] # by default, we don't allow chunks to cross documents

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

cache:
  type: file # or blob
  base_dir: "cache"
  # connection_string: <azure_blob_storage_connection_string>
  # container_name: <azure_blob_storage_container_name>

storage:
  type: file # or blob
  base_dir: "output/${timestamp}/artifacts"
  # connection_string: <azure_blob_storage_connection_string>
  # container_name: <azure_blob_storage_container_name>

reporting:
  type: file # or console, blob
  base_dir: "output/${timestamp}/reports"
  # connection_string: <azure_blob_storage_connection_string>
  # container_name: <azure_blob_storage_container_name>

entity_extraction:
  ## strategy: fully override the entity extraction strategy.
  ##   type: one of graph_intelligence, graph_intelligence_json and nltk
  ## llm: override the global llm settings for this task
  ## parallelization: override the global parallelization settings for this task
  ## async_mode: override the global async_mode settings for this task
  prompt: "prompts/entity_extraction.txt"
  entity_types: [organization,person,geo,event]
  max_gleanings: 1

summarize_descriptions:
  ## llm: override the global llm settings for this task
  ## parallelization: override the global parallelization settings for this task
  ## async_mode: override the global async_mode settings for this task
  prompt: "prompts/summarize_descriptions.txt"
  max_length: 500

claim_extraction:
  ## llm: override the global llm settings for this task
  ## parallelization: override the global parallelization settings for this task
  ## async_mode: override the global async_mode settings for this task
  # enabled: true
  prompt: "prompts/claim_extraction.txt"
  description: "Any claims or facts that could be relevant to information discovery."
  max_gleanings: 1

community_reports:
  ## llm: override the global llm settings for this task
  ## parallelization: override the global parallelization settings for this task
  ## async_mode: override the global async_mode settings for this task
  prompt: "prompts/community_report.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
  # num_walks: 10
  # walk_length: 40
  # window_size: 2
  # iterations: 3
  # random_seed: 597832

umap:
  enabled: false # if true, will generate UMAP embeddings for nodes

snapshots:
  graphml: true
  raw_entities: false
  top_level_nodes: false

local_search:
  # text_unit_prop: 0.5
  # community_prop: 0.1
  # conversation_history_max_turns: 5
  # top_k_mapped_entities: 10
  # top_k_relationships: 10
  # llm_temperature: 0 # temperature for sampling
  # llm_top_p: 1 # top-p sampling
  # llm_n: 1 # Number of completions to generate
  # max_tokens: 12000

global_search:
  # llm_temperature: 0 # temperature for sampling
  # llm_top_p: 1 # top-p sampling
  # llm_n: 1 # Number of completions to generate
  # max_tokens: 12000
  # data_max_tokens: 12000
  # map_max_tokens: 1000
  # reduce_max_tokens: 2000
  # concurrency: 32

6.运行

python -m graphrag.index --root ./ragtest

二、调试

头疼的问题：Columns must be same length as key

1.查看日志

根据图片中信息 Logging enabled at /opt/gpt/graphrag/ragtest/output/20240930-135858/reports/indexing-engine.log

tail -333f /opt/gpt/graphrag/ragtest/output/20240930-135858/reports/indexing-engine.log

2.查看到报错信息

3.处理方法

墙裂推荐解决方案：必坑指南 点击打开 仔细看，用心看
总结一下，就是把 ./ragtest/cache/entity_extraction 路径下的chat_*全都删除

sudo rm -rf ./ragtest/cache/entity_extraction/chat_*

再次运行

python -m graphrag.index --root ./ragtest

完美！！！

三、图形化展示

参考视频 图形化方案 需要一个梯子
没有梯子的先下软件吧 gephi

好看无极限，各位自己慢慢调吧。

简简单单的一张图

收工！！！