本地ollama的LLM模型运行微软GraphRAG

标签：00 GraphRAG text 100% Indexer LLM loaded ollama

pip install graphrag
pip install ollama

1、ollama安装

直接从modelscope下载ollama安装包

modelscope download --model=modelscope/ollama-linux --local_dir ./ollama-linux

# 运行ollama安装脚本

sudo chmod 777 ./ollama-linux/ollama-modelscope-install.sh
sh ./ollama-linux/ollama-modelscope-install.sh

#启动ollama，最好在后台执行,该进程不可以中断

ollama serve

2、下载模型

在ollama中部署以下两个模型：mistral和nomic-embed-text

# llm
ollama pull mistral
# embedding
ollama pull nomic-embed-text

3、初始化工目录

在当前目录下新建一个目录./ragtest/input，用于存放我们初始化graphrag需要的相关文件。其中ragtest到时候系统会参数其他配置文件和目录，input目录需要我们自己放置要解析的txt文件。

mkdir -p ./ragtest/input

运行命令graphrag.index --init。由于我们在上一步中已经配置了一个名为ragtest的目录，因此我们可以运行以下命令：

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

4、修改settings.yaml等配置

默认graphRag使用的openia的key，要改用本地的llm需要修改相应的代码和配置，我已经整理好修改步骤，按如下步骤修改即可。

1）settings.yaml配置文件

根据红色的位置，修改ragtest目录下的settings.yaml相应的内容

2）openai_embeddings_llm.py嵌入式向量脚本


class OpenAIEmbeddingsLLM(BaseLLM[EmbeddingInput, EmbeddingOutput]):
    _client: OpenAIClientTypes
    _configuration: OpenAIConfiguration

    def __init__(self, client: OpenAIClientTypes, configuration: OpenAIConfiguration):
        self._client = client
        self._configuration = configuration

    async def _execute_llm(
        self, input: EmbeddingInput, **kwargs: Unpack[LLMInput]
    ) -> EmbeddingOutput | None:
        args = {
            "model": self._configuration.model,
            **(kwargs.get("model_parameters") or {}),
        }
        embedding_list = []
        for inp in input:
            embedding = ollama.embeddings(model="nomic-embed-text", prompt=inp)
            embedding_list.append(embedding["embedding"])
        return embedding_list

屏蔽脚本原来OpenAIEmbeddingsLLM函数，用上面最新脚本替换。若找不到文件位置，使用下列命令查找

find / -name openai_embeddings_llm.py

2）embedding.py本地（local）查询脚本


    def embed(self, text: str, **kwargs: Any) -> list[float]:
        """Embed text using Ollama's nomic-embed-text model."""
        try:
            embedding = self.ollama_client.embeddings(model="nomic-embed-text", prompt=text)
            return embedding["embedding"]
        except Exception as e:
            self._reporter.error(
                message="Error embedding text",
                details={self.__class__.__name__: str(e)},
            )
            return np.zeros(self.embedding_dim).tolist()

    async def aembed(self, text: str, **kwargs: Any) -> list[float]:
        """Embed text using Ollama's nomic-embed-text model asynchronously."""
        try:
            embedding = await self.ollama_client.embeddings(model="nomic-embed-text", prompt=text)
            return embedding["embedding"]
        except Exception as e:
            self._reporter.error(
                message="Error embedding text asynchronously",
                details={self.__class__.__name__: str(e)},
            )
            return np.zeros(self.embedding_dim).tolist()

屏蔽embedding.py脚本原来以上两个原函数，使用的新脚本替换

5、运行GraphRAG

前面的步骤完成后，运行索引，创建graph。

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

执行结果日志：

Logging enabled at ragtest/output/20240903-093443/reports/indexing-engine.log
⠹ GraphRAG Indexer 
⠹ GraphRAG Indexer les loaded (0 filtered) ━━━━━━ 100% 0:00:… 0:00:…
├── Loading Input (text) - 1 files loaded (0 filtered) ━━━━━━ 100% 0:00:… 0:00:…
⠹ GraphRAG Indexer 
├── Loading Input (text) - 1 files loaded (0 filtered) ━━━━━━ 100% 0:00:… 0:00:…
⠹ GraphRAG Indexer 
├── Loading Input (text) - 1 files loaded (0 filtered) ━━━━━━ 100% 0:00:… 0:00:…
⠹ GraphRAG Indexer 
├── Loading Input (text) - 1 files loaded (0 filtered) ━━━━━━ 100% 0:00:… 0:00:…
⠼ GraphRAG Indexer 
├── Loading Input (text) - 1 files loaded (0 filtered) ━━━━━━ 100% 0:00:… 0:00:…
⠼ GraphRAG Indexer 
├── Loading Input (text) - 1 files loaded (0 filtered) ━━━━━━ 100% 0:00:… 0:00:…
⠼ GraphRAG Indexer 
├── Loading Input (text) - 1 files loaded (0 filtered) ━━━━━━ 100% 0:00:… 0:00:…
⠼ GraphRAG Indexer 
├── Loading Input (text) - 1 files loaded (0 filtered) ━━━━━━ 100% 0:00:… 0:00:…
⠼ GraphRAG Indexer 
├── Loading Input (text) - 1 files loaded (0 filtered) ━━━━━━ 100% 0:00:… 0:00:…
⠼ GraphRAG Indexer 
├── Loading Input (text) - 1 files loaded (0 filtered) ━━━━━━ 100% 0:00:… 0:00:…
⠼ GraphRAG Indexer 
├── Loading Input (text) - 1 files loaded (0 filtered) ━━━━━━ 100% 0:00:… 0:00:…
⠼ GraphRAG Indexer 
├── Loading Input (text) - 1 files loaded (0 filtered) ━━━━━━ 100% 0:00:… 0:00:…
/usr/local/lib/python3.10/site-packages/numpy/core/fromnumeric.py:59: 
FutureWarning: 'DataFrame.swapaxes' is deprecated and will be removed in a 
future version. Please use 'DataFrame.transpose' instead.
  return bound(*args, **kwds)
⠼ GraphRAG Indexer 
├── Loading Input (text) - 1 files loaded (0 filtered) ━━━━━━ 100% 0:00:… 0:00:…
└── create_base_text_units

标签：00,GraphRAG,text,100%,Indexer,LLM,loaded,ollama	

From： https://blog.csdn.net/m0_38007743/article/details/141852489