Skip to main content

A utility package for RAG operations

Project description

WhiskerRAG

MIT License Python Version PyPI version

WhiskerRAG 是为 PeterCat 和 Whisker 项目开发的 RAG(Retrieval-Augmented Generation)工具包,提供完整的 RAG 相关类型定义和方法实现。

特性

  • 领域建模类型
  • 插件接口描述
  • Github、S3 数据源加载器
  • OpenAI Emedding

安装

使用 pip 安装:

pip install whiskerrag

快速开始

该工具包提供两个核心模块:whiskerrag_utils 和 whiskerrag_types

from whiskerrag_types.interface import DBPluginInterface, TaskEngineInterface
from whiskerrag_types.model import Knowledge, Task, Tenant, PageParams, PageResponse

开发指南

环境设置

  1. 克隆项目
git clone https://github.com/your-username/whiskerRAG-toolkit.git
cd whiskerRAG-toolkit
  1. 创建并激活虚拟环境
make setup
source venv/bin/activate

开发工作流

  1. 代码格式化
make format
  1. 运行测试
# 运行所有测试
make test

# 运行特定测试文件
make test-file file=tests/test_specific.py
  1. 代码检查
# 运行所有检查(lint, type check, test)
make check

# 仅运行 lint
make lint

# 仅运行类型检查
make lint-mypy
  1. 生成测试覆盖率报告
make coverage

分支管理

创建新的功能分支:

make branch name=feature/new-feature

构建和发布

  1. 构建包
make build
  1. 检查构建的包
make check-build
  1. 发布到 TestPyPI
make upload-test
  1. 发布到 PyPI
make upload
  1. 创建新版本发布
# 本地发布
make release-local new_version=X.Y.Z

其他命令

  • 清理构建文件和缓存:
make clean
  • 更新依赖版本:
make update-deps
  • 运行 pre-commit 钩子:
make pre-commit

项目结构

whiskerRAG-toolkit/
├── src/
│   ├── whiskerrag_utils/
│   └── whiskerrag_types/
├── requirements.txt
├── requirements-dev.txt
├── setup.py
└── Makefile

贡献指南

  1. Fork 本仓库
  2. 创建特性分支 (make branch name=feature/amazing-feature)
  3. 提交更改 (git commit -m 'Add some amazing feature')
  4. 推送到分支 (git push origin feature/amazing-feature)
  5. 开启 Pull Request

许可证

本项目采用 MIT 许可证 - 查看 LICENSE 文件了解详情

联系方式

项目维护者 - @petercat-ai

项目链接:https://github.com/petercat-ai/whiskerrag_toolkit

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

whiskerrag-0.0.2.tar.gz (13.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

whiskerrag-0.0.2-py3-none-any.whl (19.7 kB view details)

Uploaded Python 3

File details

Details for the file whiskerrag-0.0.2.tar.gz.

File metadata

  • Download URL: whiskerrag-0.0.2.tar.gz
  • Upload date:
  • Size: 13.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.10.11

File hashes

Hashes for whiskerrag-0.0.2.tar.gz
Algorithm Hash digest
SHA256 a044e06cc2343f698851ff8183f2692c2d8284ddb6ce95b6b236f6d952dd3e61
MD5 f5ffc7d84e71d8c084884766317f3e9b
BLAKE2b-256 dde56f105883493fc0c427a61ceea9b614c30e2ac1665552f4bf16d8e4e3ac9f

See more details on using hashes here.

File details

Details for the file whiskerrag-0.0.2-py3-none-any.whl.

File metadata

  • Download URL: whiskerrag-0.0.2-py3-none-any.whl
  • Upload date:
  • Size: 19.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.10.11

File hashes

Hashes for whiskerrag-0.0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 930561c609793f7457b4a0750d6f38c3cd45a9bc87d0af22df40eb851459ca4f
MD5 f6886ab38772a2dab8e87fa2ec524bc4
BLAKE2b-256 974bfaa97d4473bafca7db8987bf83e472e95c99aea13dc4c4fd9e7c6697523b

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page