https://github.com/jmpaz/promptlib

A collection of prompts for use with GPT-4 via ChatGPT, OpenAI API w/ Gradio frontend & notebook
https://github.com/jmpaz/promptlib

chatgpt gpt-3 gpt-4 gradio langchain large-language-models openai prompt-engineering prompt-programming prompts

Last synced: 2 months ago
JSON representation

A collection of prompts for use with GPT-4 via ChatGPT, OpenAI API w/ Gradio frontend & notebook

• Host: GitHub
• URL: https://github.com/jmpaz/promptlib
• Owner: jmpaz
• Created: 2023-01-31T23:30:10.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2023-08-08T05:14:32.000Z (over 1 year ago)
• Last Synced: 2024-08-29T10:15:57.979Z (5 months ago)
• Topics: chatgpt, gpt-3, gpt-4, gradio, langchain, large-language-models, openai, prompt-engineering, prompt-programming, prompts
• Language: Jupyter Notebook
• Homepage: https://bento.me/promptlib
• Size: 58.6 KB
• Stars: 189
• Watchers: 7
• Forks: 18
• Open Issues: 3
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• project-awesome - jmpaz/promptlib - A collection of prompts for use with GPT-4 via ChatGPT, OpenAI API w/ Gradio frontend & notebook (Jupyter Notebook)
• awesome-llm-prompt-libraries - promptlib

README

        
# PromptLib

## About

A WIP collection of refined, value-dense, novel and/or exceptional prompts for instruction-tuned large language models, especially GPT-4 and ChatGPT's [legacy model](https://chat.openai.com/chat?model=text-davinci-002-render-paid).

Many are projects in and of themselves — natural language programs for which ChatGPT serves as a decent frontend. Prompts are generally structured in a to-be-standardized psuedocode-like format (inserted as a user message); more on this later.

|  | 

|:--:| 

| *Gradio frontend* |

## Context

New users operating LLMs via interfaces like ChatGPT may observe the model doing a decent-to-excellent job of performing basic or complex tasks when given simple question/instructions, but often outputs are lackluster, and not for fault of the model.

This project seeks to demonstrate that the quality and presentation of natural (& sometimes not-so-natural) language fed to a model *substantially* influences the quality of its outputs.

Collectively, we only barely tapped into GPT-3's potential, and we're incredibly far from reaching GPT-4's.

Prompts in this library are natural-language programs (both in their literal/written structure and in the scale & exponential value of their outputs) which act upon concepts & data, represented as text.

The project serves as a base for tools & utilities to be built out over time for explorers, developers, knowledge workers and eventually the general public.

## Prompts

- See available prompts [here](prompts/) – try pasting [one](https://github.com/jmpaz/promptlib/blob/main/prompts/fun/prompt-eng/prompt.txt) into ChatGPT.

## Credits

- [Base Gradio template](https://github.com/hwchase17/langchain-gradio-template)

## License

`(coming soon)`