DSPy：用代码而非提示词构建人工智能
DSPy是一个声明式框架，旨在通过模块化编程方式构建人工智能软件。
它允许开发者使用结构化代码迭代，而不是依赖易出错的文本提示，并通过算法将人工智能程序编译为有效提示和语言模型权重。
DSPy将人工智能软件构建过程从手动调整提示词或训练作业，转变为基于自然语言模块的组合，从而提高软件的可靠性、可维护性和跨模型/策略的兼容性。
该框架可以看作是人工智能编程的更高层级语言，类似于从汇编语言到C语言或指针算术到SQL的转变，并提供类似`dspy.ChainOfThought`、`dspy.ReAct`等模块来简化开发流程。
查看原文开头（英文 · 仅前 3 段）
Programming—not prompting—LMs¶
DSPy is a declarative framework for building modular AI software. It allows you to iterate fast on structured code, rather than brittle strings, and offers algorithms that compile AI programs into effective prompts and weights for your language models, whether you're building simple classifiers, sophisticated RAG pipelines, or Agent loops.
Instead of wrangling prompts or training jobs, DSPy (Declarative Self-improving Python) enables you to build AI software from natural-language modules and to generically compose them with different models, inference strategies, or learning algorithms. This makes AI software more reliable, maintainable, and portable across models and strategies.
※ 出于版权考虑，仅引用前 3 段。完整内容请阅读原文。