DSPy

by Stanford NLP

Read the original →

Build modular model programs and improve them against a metric.

DSPy separates task signatures, execution modules and optimization. Its examples show how prompts can be adjusted using training examples and a scoring function rather than maintained only through manual edits.

Level
Advanced
Models
any
Category
Prompting
Tags
Source date
date not stated
Added
2026-10-18
Last verified
2026-10-18
Status
ok
Prerequisites
Requires implementation experience or critical reading of technical methods and system trade-offs.
Subcategory
prompt optimization
Region
West
Original language
en
Access
free
Resource reuse
open: Source states MIT. Applies to the linked resource, not every referenced model or dataset. Facet definitions

Summary in our own words. Rights remain with the original creator. Credit and correction policy.

Plain-text Markdown copy