About This Resource

A framework for defining and optimizing language model programs. It uses structured modules and evaluation examples to improve prompts or other program components against a chosen objective.

Saved Notes

Original notes saved with this link. They may describe an earlier version.

GitHub - stanfordnlp/dspy: DSPy: The framework for programming—not prompting—language models

DSPy Documentation

DSPy: Programming—not prompting—Foundation Models

DSPy is the open-source framework for programming—rather than prompting—language models. It allows you to iterate fast on building modular AI systems and provides algorithms for optimizing their prompts and weights, whether you're building simple classifiers, sophisticated RAG pipelines, or Agent loops.

Assessment: Trial

I’ve heard a lot of users in the community exclaiming their praise on DSPy, and seeing that it’s from Stanford NLP, it should be worth a try. The project overview alone gives me vibes that this is has potential similar to LangChain and such.