graphrag+ollama的两个“坑”与解决办法

https://microsoft.github.io/graphrag/posts/get_started/

根据官方的步骤，修改setting到ollama本地，会出现如下两个常见问题：

找起来很费时间 ，分享给大家希望有帮助

global提问报错：json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)

解决办法：

I found out that my local Ollama instance (0.3.0) seemed to ignore the system prompt and I got it working by manually stitching together the two prompts into one: File: /graphrag/query/structured_search/global_search/search.py ,

https://github.com/microsoft/graphrag/issues/575

一定要看清楚报错的是哪个文件夹下的/graphrag/query/structured_search/global_search/search.py

修改这个search.py

搜索：_map_response_single_batch，然后修改

map_response_single_batch
#search_messages = [
#  {"role": "system", "content": search_prompt},
#  {"role": "user", "content": query},
#]
search_messages = [ {"role": "user", "content": search_prompt + "\n\n### USER QUESTION ### \n\n" + query} ]

local提问报错：ZeroDivisionError: Weights sum to zero, can't be normalized

解决办法：

Yes this is due to your locally run embedding model, not returning the weights in a correct format. OpenAI uses internally base64 encoded floats, and most other models will return floats as numbers.

https://github.com/microsoft/graphrag/issues/619

https://github.com/microsoft/graphrag/issues/345

一定要看清楚报错的是哪个文件夹下的graphrag\query\llm\oai\embedding.py

修改这个embedding.py

# Copyright (c) 2024 Microsoft Corporation.
# Licensed under the MIT License

"""OpenAI Embedding model implementation."""

import asyncio
from collections.abc import Callable
from typing import Any

import numpy as np
import tiktoken
from tenacity import (
    AsyncRetrying,
    RetryError,
    Retrying,
    retry_if_exception_type,
    stop_after_attempt,
    wait_exponential_jitter,
)

from graphrag.query.llm.base import BaseTextEmbedding
from graphrag.query.llm.oai.base import OpenAILLMImpl
from graphrag.query.llm.oai.typing import (
    OPENAI_RETRY_ERROR_TYPES,
    OpenaiApiType,
)
from graphrag.query.llm.text_utils import chunk_text
from graphrag.query.progress import StatusReporter

from langchain_community.embeddings import OllamaEmbeddings


class OpenAIEmbedding(BaseTextEmbedding, OpenAILLMImpl):
    """Wrapper for OpenAI Embedding models."""

    def __init__(
        self,
        api_key: str | None = None,
        azure_ad_token_provider: Callable | None = None,
        model: str = "text-embedding-3-small",
        deployment_name: str | None = None,
        api_base: str | None = None,
        api_version: str | None = None,
        api_type: OpenaiApiType = OpenaiApiType.OpenAI,
        organization: str | None = None,
        encoding_name: str = "cl100k_base",
        max_tokens: int = 8191,
        max_retries: int = 10,
        request_timeout: float = 180.0,
        retry_error_types: tuple[type[BaseException]] = OPENAI_RETRY_ERROR_TYPES,  # type: ignore
        reporter: StatusReporter | None = None,
    ):
        OpenAILLMImpl.__init__(
            self=self,
            api_key=api_key,
            azure_ad_token_provider=azure_ad_token_provider,
            deployment_name=deployment_name,
            api_base=api_base,
            api_version=api_version,
            api_type=api_type,  # type: ignore
            organization=organization,
            max_retries=max_retries,
            request_timeout=request_timeout,
            reporter=reporter,
        )

        self.model = model
        self.encoding_name = encoding_name
        self.max_tokens = max_tokens
        self.token_encoder = tiktoken.get_encoding(self.encoding_name)
        self.retry_error_types = retry_error_types

    def embed(self, text: str, **kwargs: Any) -> list[float]:
        """
        Embed text using OpenAI Embedding's sync function.

        For text longer than max_tokens, chunk texts into max_tokens, embed each chunk, then combine using weighted average.
        Please refer to: https://github.com/openai/openai-cookbook/blob/main/examples/Embedding_long_inputs.ipynb
        """
        token_chunks = chunk_text(
            text=text, token_encoder=self.token_encoder, max_tokens=self.max_tokens
        )
        chunk_embeddings = []
        chunk_lens = []
        for chunk in token_chunks:
            try:
                embedding, chunk_len = self._embed_with_retry(chunk, **kwargs)
                chunk_embeddings.append(embedding)
                chunk_lens.append(chunk_len)
            # TODO: catch a more specific exception
            except Exception as e:  # noqa BLE001
                self._reporter.error(
                    message="Error embedding chunk",
                    details={self.__class__.__name__: str(e)},
                )

                continue
        chunk_embeddings = np.average(chunk_embeddings, axis=0, weights=chunk_lens)
        chunk_embeddings = chunk_embeddings / np.linalg.norm(chunk_embeddings)
        return chunk_embeddings.tolist()

    async def aembed(self, text: str, **kwargs: Any) -> list[float]:
        """
        Embed text using OpenAI Embedding's async function.

        For text longer than max_tokens, chunk texts into max_tokens, embed each chunk, then combine using weighted average.
        """
        token_chunks = chunk_text(
            text=text, token_encoder=self.token_encoder, max_tokens=self.max_tokens
        )
        chunk_embeddings = []
        chunk_lens = []
        embedding_results = await asyncio.gather(*[
            self._aembed_with_retry(chunk, **kwargs) for chunk in token_chunks
        ])
        embedding_results = [result for result in embedding_results if result[0]]
        chunk_embeddings = [result[0] for result in embedding_results]
        chunk_lens = [result[1] for result in embedding_results]
        chunk_embeddings = np.average(chunk_embeddings, axis=0, weights=chunk_lens)  # type: ignore
        chunk_embeddings = chunk_embeddings / np.linalg.norm(chunk_embeddings)
        return chunk_embeddings.tolist()

    def _embed_with_retry(
        self, text: str | tuple, **kwargs: Any
    ) -> tuple[list[float], int]:
        try:
            retryer = Retrying(
                stop=stop_after_attempt(self.max_retries),
                wait=wait_exponential_jitter(max=10),
                reraise=True,
                retry=retry_if_exception_type(self.retry_error_types),
            )
            for attempt in retryer:
                with attempt:
                    embedding = (
                        OllamaEmbeddings(
                            model=self.model,
                        ).embed_query(text)
                        or []
                    )
                    return (embedding, len(text))
        except RetryError as e:
            self._reporter.error(
                message="Error at embed_with_retry()",
                details={self.__class__.__name__: str(e)},
            )
            return ([], 0)
        else:
            # TODO: why not just throw in this case?
            return ([], 0)

    async def _aembed_with_retry(
        self, text: str | tuple, **kwargs: Any
    ) -> tuple[list[float], int]:
        try:
            retryer = AsyncRetrying(
                stop=stop_after_attempt(self.max_retries),
                wait=wait_exponential_jitter(max=10),
                reraise=True,
                retry=retry_if_exception_type(self.retry_error_types),
            )
            async for attempt in retryer:
                with attempt:
                    embedding = (
                        await OllamaEmbeddings(
                            model=self.model,
                        ).embed_query(text) or [] )
                    return (embedding, len(text))
        except RetryError as e:
            self._reporter.error(
                message="Error at embed_with_retry()",
                details={self.__class__.__name__: str(e)},
            )
            return ([], 0)
        else:
            # TODO: why not just throw in this case?
            return ([], 0)

改了哪些部分？

增加了一行

from langchain_community.embeddings import OllamaEmbeddings

然后修改两处embedding

搜索：for attempt in retryer:

搜索：async for attempt in retryer: with attempt: