专注于流处理、AI系统与智能数据库的研究与开发
Focused on Stream Processing, AI Systems, and Intelligent Databases
SAGE (Streaming-Augmented Generative Execution) 是一个高性能、模块化的 AI 推理框架生态系统，通过数据流抽象实现透明、可扩展的 LLM 驱动系统。
SAGE is a high-performance, modular AI inference framework ecosystem that enables transparent, scalable LLM-powered systems through dataflow abstractions.
🎯 SAGE
主框架 | Main Framework 声明式、可组合的流式增强生成执行框架，用于通过数据流抽象构建透明的 LLM 驱动系统。 A declarative, composable framework for building transparent LLM-powered systems through dataflow abstractions. 特性 | Features:
|
📚 SAGE-Pub
文档中心 | Documentation Hub SAGE 系统的官方对外文档仓库，包含快速开始、架构图、API 文档等。 Official public documentation repository for the SAGE system, including quick start guides, architecture diagrams, and API documentation. 内容 | Contents:
|
💾 sageDB
向量数据库核心 | Vector Database Core 高性能向量数据库 C++ 核心库，支持可插拔 ANNS 架构和多模态特性。 High-performance C++20 vector database library with pluggable ANNS architecture and multimodal support. 核心能力 | Core Capabilities:
|
🌊 sageFlow
向量流处理引擎 | Vector Stream Processing Engine 向量原生流处理引擎，专为实时 LLM 生成任务维护和物化语义状态快照而设计。 Vector-native stream processing engine designed to maintain and materialize semantic state snapshots for real-time LLM generation tasks. 特性 | Features:
|
⏱️ sageTSDB时序数据库 | Time Series Database SAGE 生态系统的时序数据库组件，用于处理时间序列数据。 Time series database component of the SAGE ecosystem for handling temporal data streams. |
数据库基准测试 | Database Benchmark SAGE 数据库组件的性能基准测试套件。 Performance benchmark suite for SAGE database components. |
🧠 sageLLMLLM 集成模块 | LLM Integration Module SAGE 生态系统的大语言模型集成组件，提供统一的 LLM 接口。 Large Language Model integration component for the SAGE ecosystem, providing unified LLM interfaces. |
示例代码库 | Examples Repository SAGE 框架的示例代码和使用案例集合。 Collection of example code and use cases for the SAGE framework. |
🧩 neuromem记忆管理引擎 | Memory Management Engine SAGE 项目的记忆体组件，RAG 应用的独立内存管理引擎。 Memory component of the SAGE project, a standalone memory management engine for RAG applications. |
📊 sageData基准数据集 | Benchmark Datasets SAGE 基准测试的共享数据集和资源库。 Shared test datasets and resources for SAGE benchmarks. |
🔢 LibAMM
近似矩阵乘法库 | Approximate Matrix Multiplication Library 聚合了主流 AMM 算法的高性能库，支持标准化评估和高效实验管理，兼容 LibTorch (C++)。 Aggregates prevalent AMM algorithms for standardized evaluations and efficient experiment management, compatible with LibTorch (C++). 特性 | Features:
|
🔍 hnswlib
HNSW 近似最近邻搜索库 | HNSW Approximate Nearest Neighbor Search 头文件库，实现 HNSW 算法的快速近似最近邻搜索，支持 C++ 和 Python 绑定。 Header-only C++ HNSW implementation with Python bindings for fast approximate nearest neighbor search. 特性 | Features:
|
|
并发 HNSW 库 | Concurrent HNSW Library 支持并发操作的 HNSW 实现，提供快速并发的近似最近邻搜索。 Header-only C++/Python library for fast and concurrent approximate nearest neighbor search. 状态 | Status: 🚧 开发中 | In Development |
Parlay-HNSW 基线 | Parlay-HNSW Baseline 基于 Parlay 框架的 HNSW 实现，作为 ConcurrentHNSW 的基线。 Parlay-based HNSW implementation serving as baseline for ConcurrentHNSW. 状态 | Status: 🚧 开发中 | In Development |
|
内积 DiskANN 实现 | Inner Product DiskANN 基于图结构的可扩展、快速、新鲜和过滤的近似最近邻搜索索引实现。 UNOFFICIAL implementation of IP-DiskANN: Graph-structured indices for scalable, fast, fresh and filtered approximate nearest neighbor search. 状态 | Status: 🚧 待集成 | To Be Integrated |
- sage-db_outdated - SAGE 数据库的早期版本（已过时）| Early version of SAGE database (outdated)
- MorphStream ⭐ 141 - 可扩展的事务性流处理引擎 | Scalable transactional stream processing engine
- Sesame ⭐ 26 - [SIGMOD'23] 数据流聚类实证研究 | Data stream clustering empirical study
- AllianceDB ⭐ 16 - 分布式数据库系统 | Distributed database system
- CANDOR-Benchmark ⭐ 25 - 性能基准测试套件 | Performance benchmark suite
- PDSC - 并行数据流聚类基准 | Parallel data stream clustering benchmark
- SentiStream ⭐ 7 - 情感分析流处理 | Sentiment analysis stream processing
- StreamLearning - 流式学习框架 | Stream learning framework
- StreamProcessing_ReadingList ⭐ 69 - 流处理文献阅读列表 | Stream processing reading list
- Awesome-Online-Continual-Learning - 在线持续学习资源 | Online continual learning resources
# 标准安装 | Standard installation (recommended)
pip install isage[standard]
# 核心安装 | Core installation only
pip install isage[core]from sage.kernel.api.local_environment import LocalEnvironment
from sage.libs.io.source import FileSource
from sage.middleware.operators.rag import DenseRetriever, QAPromptor, OpenAIGenerator
from sage.libs.io.sink import TerminalSink
# 创建执行环境 | Create execution environment
env = LocalEnvironment("rag_pipeline")
# 构建声明式管道 | Build declarative pipeline
(
env.from_source(FileSource, {"file_path": "questions.txt"})
.map(DenseRetriever, {"model": "sentence-transformers/all-MiniLM-L6-v2"})
.map(QAPromptor, {"template": "Answer based on: {context}\nQ: {query}\nA:"})
.map(OpenAIGenerator, {"model": "gpt-3.5-turbo"})
.sink(TerminalSink)
)
# 执行管道 | Execute pipeline
env.submit()详细文档请访问：SAGE Documentation
For detailed documentation, visit: SAGE Documentation
我们欢迎各种形式的贡献！请查看各个仓库的 CONTRIBUTING.md 文件了解详情。
We welcome contributions of all kinds! Please check the CONTRIBUTING.md file in each repository for details.
- 💬 WeChat/微信群: 加入微信群
- 💬 QQ群: IntelliStream课题组讨论QQ群
- 💬 Slack: Join our Slack
- 🌐 Website: intellistream.github.io
各项目许可证详见各仓库的 LICENSE 文件。大多数项目采用 MIT 或 Apache 2.0 许可证。
License details can be found in each repository's LICENSE file. Most projects use MIT or Apache 2.0 licenses.
⭐ 如果我们的项目对您有帮助，请给我们一个 Star！
If our projects help you, please give us a Star!
