GraphRAG的介绍

目前微软已经开源了GraphRAG的完整项目代码。对于某一些LLM的下游任务则可以使用GraphRAG去增强自己业务的RAG的表现。项目给出了两种使用方式：

1. 在打包好的项目状态下运行，可进行尝试使用。
2. 在源码基础上运行，适合为了下游任务的微调时使用。
   如果需要利用Ollama部署本地大模型的可以参考我的另一篇博客
   以下在通过自身的实践之后的给出对这两种方式的使用教程，如果还有什么问题在评论区交流。

一、在源码基础上运行（便于后续修改）

1. 准备环境（在终端运行）

（1）创建虚拟环境（已安装好anaconda），此处建议使用python3.11:

conda create -n GraphRAG python=3.11
conda activate GraphRAG

2. 下载源码并进入目录

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

3. 下载依赖并初始化项目

(1)安装poetry资源包管理工具及相关依赖：

pip install poetry 
poetry install

（2）初始化

poetry run poe index --init --root .   

正确运行后，此处会在graphrag目录下生成output、prompts、.env、settings.yaml文件

4. 下载并将待检索的文档document放入./input/目录下

mkdir ./input
curl https://www.xxx.com/xxx.txt > ./input/book.txt  #示例，可以替换为任何的txt文件

5.修改相关配置文件

（1）修改.env文件（默认是隐藏的）中的api_key

vi .env  #进入.env文件，并修改为自己的api_key

修改后是全局配置，后续不需要再次修改了

（2）修改settings.yaml文件，修改其中的使用的llm模型和对应的api_base

提前说明，因为GraphRAG需要多次调用大模型和Embedding，默认使用的是openai的GPT-4,花费及其昂贵（土豪当我没说，配置也不需要改 ），建议大家可以使用其他模型或国产大模型的api

我这里使用的是agicto提供的APIkey(主要是新用户注册可以免费获取到10块钱的调用额度，白嫖还是挺爽的)。我在这里主要就修改了API地址和调用模型的名称，修改完成后的settings文件完整内容如下：

（代码行后有标记的为需要修改的地方），如果用的是agicto则则不用修改settings.yaml

encoding_model: cl100k_base
skip_workflows: []
llm:
  api_key: ${GRAPHRAG_API_KEY}
  type: openai_chat # or azure_openai_chat
  model: deepseek-chat  #修改
  model_supports_json: false # recommended if this is available for your model.
  api_base: https://api.agicto.cn/v1 #修改
  # max_tokens: 4000
  # request_timeout: 180.0
  # 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

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
  llm:
    api_key: ${GRAPHRAG_API_KEY}
    type: openai_embedding # or azure_openai_embedding
    model: text-embedding-3-small #修改
    api_base: https://api.agicto.cn/v1 #修改
    # api_base: https://<instance>.openai.azure.com
    # 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
    # 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
    # target: required # or optional
  

chunks:
  size: 300
  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:
  ## 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: 0

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: 0

community_report:
  ## 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: false
  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
  # max_tokens: 12000

global_search:
  # max_tokens: 12000
  # data_max_tokens: 12000
  # map_max_tokens: 1000
  # reduce_max_tokens: 2000
  # concurrency: 32

6.构建GraphRAG的索引（耗时较长，取决于document的长度）

poetry run poe index --root .   

成功后如下：

⠋ GraphRAG Indexer 
├── Loading Input (InputFileType.text) - 1 files loaded (0 filtered) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:00 0:00:00
├── create_base_text_units
├── create_base_extracted_entities
├── create_summarized_entities
├── create_base_entity_graph
├── create_final_entities
├── create_final_nodes
├── create_final_communities
├── join_text_units_to_entity_ids
├── create_final_relationships
├── join_text_units_to_relationship_ids
├── create_final_community_reports
├── create_final_text_units
├── create_base_documents
└── create_final_documents
🚀 All workflows completed successfully.

7.进行查询

此处GraphRAG提供了两种查询方式
1）全局查询 ：更侧重全文理解

poetry run poe query --root . --method global "本文主要讲了什么"   

运行成功后可以看到输出结果

2）局部查询：更侧重细节

poetry run poe query --root . --method local "本文主要讲了什么"   

运行成功后可以看到输出结果

8. 总结

上述过程为已经验证过的，如果报错可以检查是否正确配置api_key及api_base

二、在python包的基础上进行（快速尝试）

1. 环境安装

pip install graphrag

2. 初始化项目

创建一个临时的文件夹graphrag，用于存在运行时数据

mkdir ./graphrag/input
curl https://www.xxx.com/xxx.txt > ./myTest/input/book.txt  // 这里是示例代码，根据实际情况放入自己要测试的txt文本即可。
cd ./graphrag
python -m graphrag.index --init

3. 配置相关文件（可参考上述的配置文件过程）

4. 执行并构建图索引

python -m graphrag.index

5.进行查询

1）全局查询

python -m graphrag.query --root ../myTest --method global "这篇文章主要讲述了什么内容?"

2）局部查询

python -m graphrag.query --root ../myTest --method local "这篇文章主要讲述了什么内容?"

总结

通过以上两种方式，我们已经尝试了利用源码和python资源包进行配置GraphRAG的方式。大家可以按照自己的需求尝试以上两种方法。如果还有问题，欢迎在评论区讨论！