Announcing our new Paper: The Prompt Report, with Co-authors from OpenAI & Microsoft!
Check it out →PromptTools is an open-source library for experimenting with, testing, and evaluating prompts, LLMs, and vector databases.
PromptTools offers a playground for comparing prompts and models in three modes:
In addition to the playground, PromptTools offers and SDK for writing tests and evaluation functions to experiment with and evaluate prompts at scale.
You can check out a tutorial video here.