finitearth/capo
We introduce CAPO, a novel prompt optimization algorithm that integrates racing and multi-objective optimization for cost-efficiency and leverages few-shot examples and task descriptions, outperforming SOTA discrete prompt optimization methods.
This project helps machine learning practitioners or AI application developers create highly effective prompts for large language models while keeping costs down. You provide task descriptions and optionally some example inputs and desired outputs, and it generates optimized prompts that improve model performance and reduce the number of tokens used. This is for anyone building applications powered by large language models who needs to achieve the best possible results efficiently.
No commits in the last 6 months.
Use this if you need to automatically generate high-performing, cost-efficient prompts for large language models on various natural language tasks.
Not ideal if you are looking for an actively maintained tool, as this specific repository is for archival and reproducibility purposes; refer to the 'promptolution' repository for current development.
Stars
15
Forks
1
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Aug 03, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/finitearth/capo"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
linshenkx/prompt-optimizer
一款提示词优化器，助力于编写高质量的提示词
Undertone0809/promptulate
🚀Lightweight Large language model automation and Autonomous Language Agents development...
CTLab-ITMO/CoolPrompt
Automatic Prompt Optimization Framework
microsoft/sammo
A library for prompt engineering and optimization (SAMMO = Structure-aware Multi-Objective...
Eladlev/AutoPrompt
A framework for prompt tuning using Intent-based Prompt Calibration