Skip to main content

SAGE Middleware - Domain Operators and Service Components (L4)

Project description

SAGE Middleware(中间件)

用于构建带有 AI 能力的流式数据应用的中间件层

Python Version License PyPI

📋 Overview

SAGE Middleware 是 SAGE 框架的 L4 中间件层,提供高性能的数据处理组件和 AI 能力集成。它集成了多家大模型提供商、异步任务调度、安全鉴权以及核心数据处理组件(向量数据库、流处理引擎等)。

🧭 Governance / 团队协作制度

本仓库协作规范与质量门槛请参考:

  • .github/copilot-instructions.md
  • quickstart.sh
  • hooks/pre-commit
  • hooks/pre-push

✨ Key Features

  • 🤖 LLM 推理
    • sageLLM ✅ 推荐:统一 LLM 推理引擎,支持 CUDA/Ascend/Mock 后端
  • 🔎 检索与向量:RAG、BM25、FAISS 等
  • 📋 任务调度:Celery 异步任务
  • 🔐 安全鉴权:JWT、密码学工具
  • ⚙️ 核心组件:
    • sage_db:数据库/向量存储相关组件(含 C/C++ 扩展)
    • sage_flow:高性能向量流处理(可能包含扩展或独立子模块)

🚀 Installation

Basic Installation

pip install isage-middleware

Development Installation

git clone https://github.com/intellistream/SAGE.git
cd SAGE/packages/sage-middleware
pip install -e .

说明:中间件组件(sage_db/sage_flow/sage_tsdb 等)现已随源码直接提供或通过 pip 依赖分发,无需初始化任何子模块。

With Optional Dependencies

# 安装全部能力包(ML + Vector + Memory + Stream)
pip install isage-middleware[capability-all]

# 仅安装 ML 能力包
pip install isage-middleware[capability-ml]

# 仅安装向量能力包
pip install isage-middleware[capability-vector]

# 仅安装内存能力包
pip install isage-middleware[capability-memory]

# 仅安装流式能力包
pip install isage-middleware[capability-stream]

📖 Quick Start

LLM 推理(推荐:sageLLM)

from sage.middleware.operators.llm import SageLLMGenerator

# 自动选择最佳后端
generator = SageLLMGenerator(
    model_path="Qwen/Qwen2.5-7B-Instruct",
  base_url="http://127.0.0.1:8901/v1",  # 单一推理端口(可省略使用默认)
    temperature=0.7,
    max_tokens=2048,
)

result = generator.execute("你好,世界!")
print(result)

API 客户端

from sage.middleware.api.client import APIClient
from sage.middleware.auth.jwt import JWTManager

client = APIClient()
jwt_manager = JWTManager()

resp = client.chat_completion(
    provider="openai",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp)

📖 说明:LLM 推理默认使用 sageLLM,建议通过统一配置管理模型后端。

📦 Package Structure

sage-middleware/
├── src/
│   └── sage/
│       └── middleware/
│           ├── __init__.py
│           ├── operators/          # Dataflow operators
│           │   ├── llm/           # LLM operators (sageLLM)
│           │   ├── rag/           # RAG operators
│           │   └── agentic/       # Agent operators
│           ├── components/         # Core components
│           │   ├── sage_db/       # Vector database (C++ extensions)
│           │   ├── sage_flow/     # Stream processing (C++ extensions)
│           │   ├── sage_tsdb/     # Time-series DB (C++ extensions)
│           │   ├── sage_mem/      # Memory management
│           │   └── sage_refiner/  # Context compression
│           ├── api/                # API clients
│           └── auth/               # Authentication
├── tests/
│   ├── unit/
│   └── integration/
├── docs/
│   └── governance/                # Team collaboration
├── README.md
├── pyproject.toml
└── setup.py

🔧 Configuration

配置可以通过以下方式提供:

  • 环境变量
  • YAML/TOML 配置文件
  • 直接通过 API 参数

配置示例

# config.yaml
middleware:
  auth:
    secret_key: "your-secret-key"  # pragma: allowlist secret
    algorithm: "HS256"
  providers:
    openai:
      api_key: "sk-..."  # pragma: allowlist secret
      base_url: "https://api.openai.com/v1"

📚 Documentation

🧪 Testing

# 重依赖声明与调用点一致性审计(Issue #8)
python tools/dependency_audit.py --check

# 运行单元测试
pytest tests/unit -v

# 运行集成测试
pytest tests/integration -v

# 运行所有测试并生成覆盖率报告
pytest --cov=sage.middleware --cov-report=html

🤝 Contributing

欢迎贡献!请参阅:

新增中间件组件规范

当添加新的中间件组件时,请遵循以下要求:

  1. 目录结构: 在 src/sage/middleware/components/ 下创建组件目录
  2. C++ 扩展: 如包含 C++ 扩展,必须遵守依赖约束(参见下文详细规范)
  3. 构建脚本: 提供标准的 build.sh,支持 --install-deps
  4. setup.py 集成: 在 setup.py 中添加构建方法
  5. 测试: 添加单元测试和集成测试
  6. 文档: 更新 README 和相关文档

📄 License

本项目采用 MIT License - 详见 LICENSE 文件

🔗 Related Packages

  • sage-kernel: 核心计算引擎(L3)
  • sage-common: 通用工具(L1)
  • sage-libs: 可复用算法库(L3)
  • sage-platform: 平台服务(L2)
  • isage-vdb: 向量数据库(独立包)
  • isage-neuromem: 内存管理系统(独立包)
  • isage-refiner: 上下文压缩(独立包)

📮 Support


Part of the SAGE Framework | 主仓库

Project details


Download files

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

Source Distribution

isage_middleware-0.2.4.35.tar.gz (997.8 kB view details)

Uploaded Source

Built Distribution

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

isage_middleware-0.2.4.35-py2.py3-none-any.whl (1.2 MB view details)

Uploaded Python 2Python 3

File details

Details for the file isage_middleware-0.2.4.35.tar.gz.

File metadata

  • Download URL: isage_middleware-0.2.4.35.tar.gz
  • Upload date:
  • Size: 997.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.14

File hashes

Hashes for isage_middleware-0.2.4.35.tar.gz
Algorithm Hash digest
SHA256 788403e4a32a667b438f0cd2acd71dfd5c3f42bd1dc3342bfcf4e883d84167c0
MD5 faa674162332cd0eccec99b1d6975b28
BLAKE2b-256 3105a3ff294181fb95aec43cbccf56748f46d161d64fa53fac99b68420757cd5

See more details on using hashes here.

File details

Details for the file isage_middleware-0.2.4.35-py2.py3-none-any.whl.

File metadata

File hashes

Hashes for isage_middleware-0.2.4.35-py2.py3-none-any.whl
Algorithm Hash digest
SHA256 6ff0cc07b59cb931d46ebfef9d897f8897e60edc253655012a9725d3d5d667fa
MD5 87e437b72a3b1d1f3d5a141c10ff3c60
BLAKE2b-256 4c9464cff31286adb3d64f637012493b9d14cf973b88060b6350def0dc0e455f

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