Skip to main content

GraphRag-API


0.3.x 版本以后graphrag官方有好几个bug,提了pr之后一直没人审核。只能等官方bug解决了。

不建议升级!!!

新版本不止是bug!!

GraphRag-API 在 GraphRag 库的基础上扩展,提供了 API 调用功能,用于执行本地和全局搜索。此扩展允许用户通过 RESTful API 调用,轻松地将 GraphRag 的强大搜索功能集成到他们的应用程序中。

功能

  • 本地搜索:在指定的本地数据集内进行搜索。
  • 全局搜索:在更广泛的全球数据集中进行搜索。
  • 可配置参数:通过配置文件或 API 调用自定义搜索参数。
  • RESTful API:通过 HTTP 请求轻松与其他应用程序和服务集成。

安装

先决条件

确保已安装 Python 3.8+。

通过 pip 安装

使用 pip 安装 GraphRag-API:

pip install graphrag_api

从源码安装

  1. 克隆源码库:
git clone https://github.com/nightzjp/graphrag_api
  1. 进入项目目录并安装依赖:
cd graphrag_api
pip install -r requirements.txt

使用

初始化

  1. 命令行初始化
graphrag init --root ./rag  # graphrag初始化
python index_test.py --init --root rag  # graphrag_api初始化

2代码初始化

from graphrag_api.index import GraphRagIndexer


indexer = GraphRagIndexer(root="rag", init=True)

indexer.run()

索引创建

  1. 命令行初始化(会生成rag目录)
graphrag index --root ./rag  # graphrag初始化
python index_test.py --root rag  # graphrag_api初始化
  1. 代码初始化
from graphrag_api.index import GraphRagIndexer


indexer = GraphRagIndexer(root="rag")

indexer.run()
  1. 修改配置文件(自动生成,需要修改相应配置)

.env文件

GRAPHRAG_API_KEY=<API_KEY>

settings.yaml文件

encoding_model: cl100k_base
skip_workflows: []
llm:
  api_key: ${GRAPHRAG_API_KEY}
  type: openai_chat # or azure_openai_chat
  model: gpt-4o-mini  # mini性价比比较高
  model_supports_json: true # recommended if this is available for your model.

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: text-embedding-3-small
    
input:
  type: file # or blob
  file_type: csv # or text  这里以csv为例
  base_dir: "input"
  file_encoding: utf-8
  file_pattern: ".*\\.csv$"
  source_column: "question"  # csv-key
  text_column: "answer"  # csv-key

q.csv文件示例

question,answer
"你是谁","你猜啊"

搜索

  1. 命令行初始化
python -m graphrag query \
--root ./ragtest \
--method global(local) \
"What are the top themes in this story?"  # graphrag初始化

python search_test.py --root rag --method global(local) "What are the top themes in this story?"  # graphrag初始化

2代码初始化

from graphrag_api.search import SearchRunner

search_runner = SearchRunner(root_dir="rag")

search_runner.run_local_search(query="What are the top themes in this story?", streaming=False)
search_runner.run_global_search(query="What are the top themes in this story?", streaming=False)

# 对于输出的结果可能带有一些特殊字符,可以采用以下函数去除特殊字符或自行处理。
search_runner.remove_sources(search_runner.run_local_search(query="What are the top themes in this story?")[0])

报告问题

如果遇到任何问题,请在 GitHub 上提交 issue。

许可证

此项目依据 MIT 许可证授权。有关详细信息,请参阅 LICENSE 文件。

致谢

此项目基于 GraphRag 库。特别感谢原项目的贡献者。


如果有任何需要进一步调整的地方,请告诉我!

Metadata

Release files for graphrag-api 1.0.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for graphrag-api 1.0.1
File Size Uploaded
graphrag_api-1.0.1.tar.gz 13.3 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for graphrag-api 1.0.1
File Interpreter ABI Platform
graphrag_api-1.0.1-py3-none-any.whl Python 3 none any Details

Total release size: 25.8 kB

Release files / graphrag_api-1.0.1.tar.gz

Download URL graphrag_api-1.0.1.tar.gz
Size 13.3 kB
Tags Source
SHA-256 checksum
How to use checksums
1b0c7eb611285a3b9beb867aa2e60f1a6f82d18a9b98de8c7d8a5fd917a1f857
BLAKE2b-256 checksum
How to use checksums
bf1f262ac5829630ae44109afac05cfb75437a324e1ca7257f1af0d213b32959
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/5.1.1 CPython/3.12.1

Release files / graphrag_api-1.0.1-py3-none-any.whl

Download URL graphrag_api-1.0.1-py3-none-any.whl
Size 12.4 kB
Tags Python 3
SHA-256 checksum
How to use checksums
db60446bc9103375aaaf5ee2bdc10fd6848cff8b66c3b00faf4c8c694f4f8f64
BLAKE2b-256 checksum
How to use checksums
f310fe79ceaa14118d6536697611a73ba4065f2ad319a61f0e36547e2066b941
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/5.1.1 CPython/3.12.1

Release history Release notifications | RSS feed

This release

1.0.1 This release

2 release files

1.0.0

2 release files

0.9.0

2 release files

0.5.0

2 release files

0.3.6

2 release files

0.3.5

2 release files

0.3.3

2 release files

0.3.2

2 release files

0.3.1

2 release files

0.3.0

2 release files

0.2.2

2 release files

0.2.1

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page