marklysze/AutoGenPromptTesting
Prompt testing Local LLMs for Microsoft's AutoGen
This project helps developers evaluate how well different local Large Language Models (LLMs) perform specific tasks within an AutoGen multi-agent system. It takes various local LLMs and different prompt engineering techniques as input, then measures how accurately the LLM selects the correct 'speaker' or agent in a simulated debate scenario. The ideal user is a developer building multi-agent AI applications with AutoGen, specifically when using local, self-hosted LLMs that might not be as capable as commercial alternatives.
No commits in the last 6 months.
Use this if you are an AI application developer working with AutoGen and need to understand how to optimize prompts for local LLMs to achieve reliable multi-agent coordination.
Not ideal if you are looking for a fully structured, production-ready framework for generalized prompt testing, or if you are exclusively using highly capable private LLMs like ChatGPT.
Stars
10
Forks
1
Language
Python
License
—
Category
Last pushed
Feb 27, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/marklysze/AutoGenPromptTesting"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
dottxt-ai/outlines
Structured Outputs
takashiishida/arxiv-to-prompt
Transform arXiv papers into a single LaTeX source that can be used as a prompt for asking LLMs...
microsoft/promptpex
Test Generation for Prompts
Spr-Aachen/LLM-PromptMaster
A simple LLM-Powered chatbot software.
AI-secure/aug-pe
[ICML 2024 Spotlight] Differentially Private Synthetic Data via Foundation Model APIs 2: Text