之前介绍了知识图谱与检索增强的融合探索GraphRAG。
https://blog.csdn.net/liliang199/article/details/151189579
这里尝试在CPU环境，基于GraphRAG+Ollama，验证GraphRAG构建知识图谱和检索增强查询过程。
1 环境安装
1.1 GraphRAG安装
在本地cpu环境，基于linux conda安装python，pip安装graphrag，过程如下。
conda create -n graphrag python=3.10
conda activate graphrag
pip install graphrag==0.5.0 -i https://pypi.tuna.tsinghua.edu.cn/simple
安装graphrag 0.5.0（之后版本可能和ollama有兼容问题）
1.2 Ollama LLM安装
假设ollama已安装，具体安装过程参考
https://blog.csdn.net/liliang199/article/details/149267372
这里ollama下载llm模型mistral和embedding模型nomic-embed-text
ollama pull nomic-embed-text
ollama pull mistral
默认ollama模型上下文长度为2048，不能有效支持GraphRAG，需要对上下文长度进行修改。
导出现有llm模型配置，配置文件为Modelfile
ollama show --modelfile mistral:latest > Modelfile
修改Modelfile，在PARAMETER区域添加如下配置，支持10k上下文，可依据具体情况设定。
PARAMETER num_ctx 10000
修改后示例如下
基于修改后的Modelfile，创建新的ollama模型，指令如下。
ollama create mistral:10k -f Modelfile
查看新创建模型
ollama list
2 GraphRAG图谱构建验证
2.1 测试数据准备
首先创建工作目录
mkdir ragtest/input -p
输入为如下小1000行的文本，获取命令如下。
https://www.gutenberg.org/cache/epub/7785/pg7785.txt
wget https://www.gutenberg.org/cache/epub/7785/pg7785.txt -O ragtest/input/Transformers_intro.txt
此时，./ragtest包含测试数据，初始化指令如下。
graphrag init --root ./ragtest
生成参数配置文件ragtest/settings.yaml
2.2 环境变量设置
设置GRAPHRAG_API_KEY和GRAPHRAG_CLAIM_EXTRACTION_ENABLED
export GRAPHRAG_API_KEY=ollama
export GRAPHRAG_CLAIM_EXTRACTION_ENABLED=True
设置参数GRAPHRAG_CLAIM_EXTRACTION_ENABLED=True，否则无法生成协变量，Local Search出错。
2.3 模型参数配置
模型参数配置文件ragtest/settings.yaml
修改llm model为mistral:10k，embedding model为nomic-embed-text
调用本地ollama llm服务，所以设置api_base: http://localhost:11434/v1
本地cpu部署，计算很慢，所以设置一个很长的request_timeout: 18000
没有GPU，过大concurrent_requests没效果，反而导致超时，设置concurrent_requests: 1
### 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: mistral:10kapi_base: http://localhost:11434/v1
request_timeout: 18000
concurrent_requests: 1
model_supports_json: true # 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: 50async_mode: threaded # or asyncio
embeddings:
async_mode: threaded # or asyncio
vector_store:
type: lancedb
db_uri: 'output/lancedb'
container_name: default
overwrite: true
llm:
api_key: ${GRAPHRAG_API_KEY}
type: openai_embedding # or azure_openai_embedding
model: nomic-embed-text
api_base: http://localhost:11434/v1
request_timeout: 18000concurrent_requests: 1
# api_base: https://<instance>.openai.azure.com
# api_version: 2024-02-15-preview
# audience: "https://cognitiveservices.azure.com/.default"
# organization: <organization_id>
# deployment_name: <azure_model_deployment_name>### Input settings ###
input:
type: file # or blob
file_type: text # or csv
base_dir: "input"
file_encoding: utf-8
file_pattern: ".*\\.txt$"chunks:
size: 1200
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 providedcache:
type: file # or blob
base_dir: "cache"reporting:
type: file # or console, blob
base_dir: "logs"storage:
type: file # or blob
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: 1summarize_descriptions:
prompt: "prompts/summarize_descriptions.txt"
max_length: 500claim_extraction:
enabled: false
prompt: "prompts/claim_extraction.txt"
description: "Any claims or facts that could be relevant to information discovery."
max_gleanings: 1community_reports:
prompt: "prompts/community_report.txt"
max_length: 2000
max_input_length: 8000cluster_graph:
max_cluster_size: 10embed_graph:
enabled: false # if true, will generate node2vec embeddings for nodesumap:
enabled: false # if true, will generate UMAP embeddings for nodessnapshots:
graphml: false
raw_entities: false
top_level_nodes: 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/#querylocal_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"
2.4 数据索引构建
然后就是构建索引，这里需要设置--reporter "rich"，不设置会报错。
nohup graphrag index --root ./ragtest --reporter "rich" > run.log &
本地CPU运行ollama其实不太有效，耗时太长，导致各种奇怪超时和报错，所以最好有GPU。
另外，虽然可以调用外部LLM服务，但GraphRAG索引会消耗大量tokens，这需要不差钱。
附录
问题1: Invalid value for '--reporter'
Invalid value for '--reporter' (env var: 'None'): <ReporterType.RICH: 'rich'> is not one of 'rich', 'print', 'none'. │
补全输出参数"none"/"print"/"rich"，比如 --reporter "rich"
reference
---
GraphRAG
https://github.com/msolhab/graphrag
Project Gutenberg
https://www.gutenberg.org/
Global Search Notebook
https://microsoft.github.io/graphrag/examples_notebooks/global_search/
GraphRAG-知识图谱与检索增强的融合探索
https://blog.csdn.net/liliang199/article/details/151189579
GraphTest - 直接使用阿里API，总体费用相对可控。
https://github.com/NanGePlus/GraphragTest
GraphRAG（最新版）+Ollama本地部署，以及中英文示例
https://juejin.cn/post/7439046849883226146
傻瓜操作：GraphRAG、Ollama 本地部署及踩坑记录
https://blog.csdn.net/weixin_42107217/article/details/141649920
)
)
