• 配置镜像源：
• 将conda配置更新为官方的Anaconda通道

conda config --remove-key channels

conda config --add channels defaults

conda config --add channels conda-forge

• 创建环境：

conda create -n graphrag-ollama-local python=3.10

conda activate graphrag-ollama-local

• 安装Ollama
• 安装Ollama依赖

安装IPEX-LLM库，这是Ollama运行所需的依赖：

pip install --pre --upgrade ipex-llm[cpp]

• 使用安装包安装ollama（如果需要切换磁盘则需参考第二个链接）

Ollama-0001-安装 - 知乎 (zhihu.com)

ollama修改模型的下载位置解决C盘空间不足问题_ollama修改模型位置-CSDN博客

• 使用ollama下载使用的开源模型：mistral+nomic-embed-text

• 检查下载是否成功

• 启动服务

出现报错：端口号被占用。Error: listen tcp 127.0.0.1:11434: bind: Only one usage of each socket address-CSDN博客

原因：Windows中默认安装Ollama会开机启动。因此才会在ollama serve时报错。

• 解决问题：退出Ollama:
  快捷键win+x打开任务管理器：启动应用中禁用掉ollama，并在进程中结束ollama的任务。
• 再次尝试ollama serve

成功：

• 在此处，无法输入，类似于卡主不动的样式。
• 需要打开一个新的cmd窗口，输入conda activate graphrag-ollama-local，进行接下来的操作和测试
• 测试ollama是否运行成功：

• 下载源代码

git clone GitHub - TheAiSingularity/graphrag-local-ollama: Local models support for Microsoft's graphrag using ollama (llama3, mistral, gemma2 phi3)- LLM & Embedding extraction

cd graphrag-local-ollama/

• 安装依赖包（非常重要！！！）

pip install -e .

报错解决方案：

方案一：更换镜像源下载；

方案二：要使用git clone源代码，再次运行即可

• 创建GraphRAG目录，并且创建input/目录用于存放原始文档：mkdir ragtest\input
•  将原始文档放入到./ragtest/input目录下（仅支持txt文件，可多个）：xcopy input\* ragtest\input\ /s /e

• 初始化项目：python -m graphrag.index --init --root ./ragtest

若报错，根据报错安装模块

若运行成功，ragtest目录下有output,input,setting.yaml, prompts.env(默认隐藏）五个目录及文件

• 移动 settings.yaml 文件，这是用 ollama 本地模型配置的主要预定义配置文件：

move settings.yaml .\ragtest\

• 修改配置文件（完全粘贴附录中的修改结果）
• 进行索引，构建图：python -m graphrag.index --root ./ragtest

若报错，则首先检查是否完全粘贴。

当前报错情况（未解决）

三、附录

settings.yaml

修改结果如下：

encoding_model: cl100k_base

skip_workflows: []

llm:

  api_key: ${GRAPHRAG_API_KEY}

  type: openai_chat # or azure_openai_chat

  model: mistral

  model_supports_json: false # recommended if this is available for your model.

  # max_tokens: 4000

  # request_timeout: 180.0

  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

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: nomic-embed-text

    api_base:  http://localhost:11434/api

    # 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: 200

  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: yes

  raw_entities: yes

  top_level_nodes: yes

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