|
|
--- |
|
|
title: System Prompt Depersonaliser |
|
|
emoji: 😻 |
|
|
colorFrom: yellow |
|
|
colorTo: green |
|
|
sdk: gradio |
|
|
sdk_version: 5.29.0 |
|
|
app_file: app.py |
|
|
pinned: false |
|
|
short_description: Converts personal system prompts for general use |
|
|
--- |
|
|
|
|
|
# System Prompt Depersonaliser |
|
|
|
|
|
This application helps you convert personalized LLM system prompts into depersonalized versions that can be shared with and used by a wider audience. |
|
|
|
|
|
## What It Does |
|
|
|
|
|
The System Prompt Depersonaliser: |
|
|
|
|
|
1. Takes a personalized system prompt as input |
|
|
2. Identifies and removes personal elements such as: |
|
|
- Names |
|
|
- Specific hardware or software configurations |
|
|
- Location-specific references |
|
|
- Unique use cases or workflows |
|
|
- Personal preferences or requirements |
|
|
3. Replaces personal references with generic alternatives |
|
|
4. Maintains the core functionality and purpose of the original prompt |
|
|
5. Preserves the overall structure and flow of instructions |
|
|
|
|
|
## How to Use |
|
|
|
|
|
1. Enter your personalized system prompt in the input box |
|
|
2. Choose whether to use Hugging Face's model (free) or OpenAI (requires API key) |
|
|
3. If using OpenAI, enter your API key in the provided field |
|
|
4. Click "Depersonalize" to generate the depersonalized version |
|
|
5. Copy the result from the output box |
|
|
|
|
|
## Example |
|
|
|
|
|
**Before Depersonalization:** |
|
|
``` |
|
|
Your task is to help Daniel identify the best way to backup his Open SUSE Linux desktop on his local network. On the local network Daniel has a Synology NAS. You should prioritise direct guidance for incremental backup tools. |
|
|
``` |
|
|
|
|
|
**After Depersonalization:** |
|
|
``` |
|
|
Your task is to assist users in deploying optimal backup strategies over local area networks. Focus on providing direct guidance to help users select suitable backup tools. |
|
|
``` |
|
|
|
|
|
## Technical Details |
|
|
|
|
|
- Built with Gradio for the user interface |
|
|
- Uses either Hugging Face's free-tier models or OpenAI's API for text transformation |
|
|
- Deployed as a Hugging Face Space |
|
|
|
|
|
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference |
|
|
|
