JRC1995/ZeroPromptSearch
Implementation of an LLM prompting pipeline combined with wrappers for auto-decomposing reasoning steps and for search through the reasoning-step-space (eg. by beam search, MCTS etc.) guided by self-evaluation.
This tool helps researchers and developers working with Large Language Models (LLMs) to automatically break down complex problems into manageable steps. You input a complex question or problem, and it outputs a series of smaller reasoning steps, iteratively refined through self-evaluation to find the best possible solution path. It's designed for those pushing the boundaries of what LLMs can achieve in reasoning tasks.
No commits in the last 6 months.
Use this if you need to explore and optimize how an LLM can methodically solve multi-step problems by breaking them down and searching for the best solution pathway.
Not ideal if you are looking for a simple, out-of-the-box solution for common text generation tasks without deep involvement in LLM reasoning architecture.
Stars
15
Forks
4
Language
Python
License
—
Category
Last pushed
May 07, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/JRC1995/ZeroPromptSearch"
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