Graphrag复现及问题定位

1.首先在github上下载GraphRAG源码：https://github.com/microsoft/graphrag
2.从readme中找到[Read the docs](https://microsoft.github.io/graphrag)<br/>，进入这个网址后，     点击Get Started
3.按照官方的步骤：①pip install graphrag       ②mkdir -p ./ragtest/input
③curl https://www.gutenberg.org/cache/epub/24022/pg24022.txt > ./ragtest/input/book.txt
④python -m graphrag.index --init --root ./ragtest⑤python -m graphrag.index --root ./ragtest
4.修改/ragtest文件下的.env(换成自己的API密钥)
5.修改/ragtest文件下的setting.yaml，以下是我的一些配置
---------------------------------------------------------------------------------------------------------------------------------
还有一点注意事项，如果你已经在.env这里复制了密钥，则api_key: ${GRAPHRAG_API_KEY}这里需要这么写，因为有$这个符号，表明它是要找GRAPHRAG_API_KEY这个变量，
   此时需要设置成api_key: ${GRAPHRAG_API_KEY}。
   如果没有$这个符号，可以直接写密钥，此时为：api_key: {换成自己的API密钥}）

我用的是GPT3.5的API_KEY，因为GPT4有点子昂贵
--------------------------------------------------------------------------------------------------------------------------------

encoding_model: cl100k_base
skip_workflows: []
llm:
  api_key: ${GRAPHRAG_API_KEY}# 注意，这里就是我说的注意事项
  type: openai_chat # or azure_openai_chat
  model: gpt-3.5-turbo-16k
  model_supports_json: false # true # recommended if this is available for your model.
  # max_tokens: 4000
  # request_timeout: 180.0
  api_base: http://10.211.10.238:31000/v1
  # api_version: 2024-02-15-preview
  # organization: <organization_id>
  # deployment_name: <azure_model_deployment_name>
  tokens_per_minute: 10_000 # set a leaky bucket throttle
  requests_per_minute: 20 # 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
  llm:
    api_key: ${GRAPHRAG_API_KEY} # 注意，这里就是我说的注意事项
    type: openai_embedding # or azure_openai_embedding
    model: text-embedding-ada-002
    api_base: http://10.211.10.238:31000/v1
    # api_version: 2024-02-15-preview
    # organization: <organization_id>
    # deployment_name: <azure_model_deployment_name>
    tokens_per_minute: 10_000 # set a leaky bucket throttle
    requests_per_minute: 20 # 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: 1 #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_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: 5000 # 2000
  max_input_length: 15000 # 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