【GraphRAG+Ollama本地部署】新鲜滚热辣的小白操作
文章目录
- 【GraphRAG+Ollama本地部署】新鲜滚热辣的小白操作
- 环境准备+源码下载
- 一、Anaconda虚拟环境创建及配置
- 二、Ollama模型下载
- 三、创建数据目录
- 四、项目初始化
- 四、修改配置文件settings.yaml
- 五、修改.env文件
- 六、修改虚拟环境graphR里graphrag包的源码
- 七、建立索引
- 八、开始查询
环境准备+源码下载
1.操作系统：Ubuntu20.04
2.VSCode编译器
3.Python 3.11
4.Ollama安装
5.GraphRAG代码下载：https://github.com/microsoft/graphrag.git
一、Anaconda虚拟环境创建及配置
1.conda create --name graphR python=3.11
2.pip install graphrag==0.3.6（新版本的graphrag容易报错：No module named graphrag.index.main ）
3.pip install ollama
（接下来操作期间若出现未提及包的未安装提示，就按照提示安装即可）
二、Ollama模型下载
1.ollama serve （启动ollama）
2.ollama pull mistral：v0.2
3.ollama pull nomic-embed-text:latest
三、创建数据目录
在graphrag代码文件夹中创建一个ragtest文件夹，并在ragtest文件夹中创建一个input文件夹，把txt数据放在input文件夹中
四、项目初始化
1.python -m graphrag.index --init --root ./ragtest
（在graphrag代码文件夹中打开终端，并激活graphR虚拟环境，运行上述代码，随后在ragtest文件夹中会出现setting.yaml，prompts，.env等文件，正常情况下是有图中6个东西的，但是有时候一开始只有几个，后面建立索引的时候其余的也会自动生成）
四、修改配置文件settings.yaml
按照下面的代码修改即可
encoding_model: cl100k_base
skip_workflows: []
llm:
api_key: ollama
type: openai_chat # or azure_openai_chat
model: mistral:v0.2
model_supports_json: true # recommended if this is available for your model.
max_tokens: 1024
# 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
# 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
# target: required # or all
# 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
llm:
api_key: ollama
type: openai_embedding # or azure_openai_embedding
model: nomic-embed-text:latest
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
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:
## strategy: fully override the entity extraction strategy.
## type: one of graph_intelligence, graph_intelligence_json and nltk
## 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: 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: 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
# llm_temperature: 0 # temperature for sampling
# llm_top_p: 1 # top-p sampling
# llm_n: 1 # Number of completions to generate
# max_tokens: 12000
global_search:
# llm_temperature: 0 # temperature for sampling
# llm_top_p: 1 # top-p sampling
# llm_n: 1 # Number of completions to generate
# max_tokens: 12000
# data_max_tokens: 12000
# map_max_tokens: 1000
# reduce_max_tokens: 2000
# concurrency: 32五、修改.env文件
按照下面的代码修改即可
GRAPHRAG_API_KEY=ollama
GRAPHRAG_CLAIM_EXTRACTION_ENABLED=True六、修改虚拟环境graphR里graphrag包的源码
1.找到graphrag包位置：/home//.conda/envs/graphR/lib/python3.11/site-packages
2.修改第一个文件：/home//.conda/envs/graphR/lib/python3.11/site-packages/graphrag/llm/openai/openai_embeddings_llm.py
"""The EmbeddingsLLM class."""
from typing_extensions import Unpack
from graphrag.llm.base import BaseLLM
from graphrag.llm.types import (
EmbeddingInput,
EmbeddingOutput,
LLMInput,
)
from .openai_configuration import OpenAIConfiguration
from .types import OpenAIClientTypes
import ollama # 增加依赖
class OpenAIEmbeddingsLLM(BaseLLM[EmbeddingInput, EmbeddingOutput]):
"""A text-embedding generator LLM."""
_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 {}),
}
# 修改此处
#embedding = await self.client.embeddings.create(
# input=input,
# **args,
#)
#return [d.embedding for d in embedding.data]
embedding_list = []
for inp in input:
embedding = ollama.embeddings(model="nomic-embed-text:latest", prompt=inp)
embedding_list.append(embedding["embedding"])
return embedding_list3.修改第二个文件：/home/***/.conda/envs/graphR/lib/python3.11/site-packages/graphrag/query/llm/oai/embedding.py
"""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.logging import StatusLogger
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
# 增加依赖
import ollama
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: StatusLogger | 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)
#修改embedding、chunk_len
embedding = ollama.embeddings(model='nomic-embed-text:latest', prompt=chunk)['embedding']
chunk_len = len(chunk)
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()
return chunk_embeddings
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 = (
self.sync_client.embeddings.create( # type: ignore
input=text,
model=self.model,
**kwargs, # type: ignore
)
.data[0]
.embedding
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 self.async_client.embeddings.create( # type: ignore
input=text,
model=self.model,
**kwargs, # type: ignore
)
).data[0].embedding 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)4.修改第三个文件：/home/***/.conda/envs/graphR/lib/python3.11/site-packages/graphrag/query/llm/text_utils.py
"""Text Utilities for LLM."""
from collections.abc import Iterator
from itertools import islice
import tiktoken
def num_tokens(text: str, token_encoder: tiktoken.Encoding | None = None) -> int:
"""Return the number of tokens in the given text."""
if token_encoder is None:
token_encoder = tiktoken.get_encoding("cl100k_base")
return len(token_encoder.encode(text)) # type: ignore
def batched(iterable: Iterator, n: int):
"""
Batch data into tuples of length n. The last batch may be shorter.
Taken from Python's cookbook: https://docs.python.org/3/library/itertools.html#itertools.batched
"""
# batched('ABCDEFG', 3) --> ABC DEF G
if n < 1:
value_error = "n must be at least one"
raise ValueError(value_error)
it = iter(iterable)
while batch := tuple(islice(it, n)):
yield batch
def chunk_text(
text: str, max_tokens: int, token_encoder: tiktoken.Encoding | None = None
):
"""Chunk text by token length."""
if token_encoder is None:
token_encoder = tiktoken.get_encoding("cl100k_base")
tokens = token_encoder.encode(text) # type: ignore
# 增加下行代码，将tokens解码成字符串
tokens = token_encoder.decode(tokens)
chunk_iterator = batched(iter(tokens), max_tokens)
#yield from (token_encoder.decode(list(chunk)) for chunk in chunk_iterator)
yield from chunk_iterator七、建立索引
1.打开ollama，可以看到模型运行状态
2.python -m graphrag.index --root ./ragtest
（回到第四步打开的终端页面，运行这行代码，并出现图中结果即建立完成）
八、开始查询
1.局部查询：python -m graphrag.query --root ./ragtest --method local "who is Marley?"
2.全局查询：python -m graphrag.query --root ./ragtest --method global "who is Marley?"
（注意：我在查询的时候会出现没有graphrag.logging的错误提示，直接把源码中graphrag文件夹里面的logging文件夹复制到虚拟环境中graphrag包里相应位置就解决了）
参考博文：
1.https://blog.csdn.net/weixin_42107217/article/details/141649920
2.https://blog.csdn.net/gaotianhao123/article/details/140640415
3.https://blog.csdn.net/m0_56378800/article/details/140319467