danielrosehill's picture
updated
675b5d2

A newer version of the Streamlit SDK is available: 1.41.1

Upgrade
metadata
title: Prompt & Output Separator
short_description: Separates prompts and outputs using GPT 3.5
colorFrom: blue
colorTo: red
sdk: streamlit
sdk_version: 1.21.0
app_file: app/app.py
pinned: false

alt text

Prompt And Output Separation Utility (V1)

View On Hugging Face Spaces

This utility is designed to enable the easy separation of prompts and outputs when they are recorded together in one long continuous text block.

The utility uses GPT 3.5 in order to send the prompt and output to the large language model and it uses the LLM both to distinguish between these 2 items which are sent back in a JSON response and it also suggests a title

The intended use case for this utility is if you have a lot of prompts and outputs recorded together in text files on your computer and you are undertaking the process of adding these to a database in which case having quickly generated titles as well as separated prompts and outputs to distinguish these and the data structure might be useful

As with many projects, this was a collaboration between my prompting and clumsy debugging and the code generation abilities of Claude Anthropic 3.5 Sonnet.

Screenshots (V1)

alt text

alt text

alt text

alt text

alt text

alt text

Author

Daniel Rosehill
(public at danielrosehill dot com)

Licensing

This repository is licensed under CC-BY-4.0 (Attribution 4.0 International) License

Summary of the License

The Creative Commons Attribution 4.0 International (CC BY 4.0) license allows others to:

  • Share: Copy and redistribute the material in any medium or format.
  • Adapt: Remix, transform, and build upon the material for any purpose, even commercially.

The licensor cannot revoke these freedoms as long as you follow the license terms.

License Terms

  • Attribution: You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
  • No additional restrictions: You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.

For the full legal code, please visit the Creative Commons website.