声明式智能编程
原名：dspy
DSPy: declarative LM programs, auto-optimize prompts, RAG.
- 分类
- 开发提效
- 版本
- v1.0.0
- 作者
- 弈韬(@ra1nzzz)
- 下载
- 2
- 收藏
- 0
- 发布
- 2026-08-25
- 更新
- 2026-09-15
- TRACE 评分
- 4.2 / 5
内容概览
Use DSPy when you need to: - Build complex AI systems with multiple components and workflows - Program LMs declaratively instead of manual prompt engineering - Optimize prompts automatically using data-driven methods - Create modular AI pipelines that are maintainable and portable - Improve model outputs systematically with optimizers - Build RAG systems, agents, or classifiers with better reliability GitHub Stars : 22,000+ Created By : Stanford NLP Signatures define the structure of your AI task (inputs → outputs): When to use each: - Inline : Quick prototyping, simple tasks - Class : Complex tasks, type hints, better documentation Modules are reusable components that transform inputs to outputs: Basic prediction module: Generates reasoning steps before answering: Agent-like reasoning with tools: Generates and executes code for reasoning: Optimizers improve your modules automatically us…