one-pager-generator / README.md
phxdev's picture
Upload folder using huggingface_hub
4ca689a verified

A newer version of the Gradio SDK is available: 5.41.0

Upgrade
metadata
title: AI One-Pager Generator
emoji: πŸ“„
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: 4.44.0
app_file: app.py
pinned: false
license: mit
suggested_hardware: t4-medium
suggested_storage: small

πŸ“„ AI One-Pager Generator

An intelligent Gradio application that generates professional one-page documents on any topic using Hugging Face transformers.

Features

  • Topic-based Generation: Create one-pagers on any subject
  • Customizable Parameters:
    • Target audience specification
    • Tone selection (Professional, Casual, Academic, Persuasive, Informative)
    • Length control (Short, Medium, Long)
    • Key points input
  • Professional Formatting: Structured output with title, executive summary, key points, and conclusion
  • Easy to Use: Simple web interface powered by Gradio

Installation

  1. Clone this repository
  2. Install dependencies:
pip install -r requirements.txt
  1. Run the application:
python app.py

Usage

  1. Enter your topic in the "Topic" field
  2. Specify your target audience
  3. List key points you want covered
  4. Select the appropriate tone and length
  5. Click "Generate One-Pager"
  6. Copy and use your generated document!

Deployment to Hugging Face Spaces

This app is ready to be deployed to Hugging Face Spaces:

  1. Create a new Space on Hugging Face
  2. Upload these files to your Space
  3. Your app will be automatically deployed!

Model Information

This application uses Qwen 2.5-7B-Instruct locally, plus MCP (Model Context Protocol) client support for connecting to external AI services like Claude and OpenAI. This hybrid approach provides both privacy (local) and enhanced capabilities (MCP).

Models Available:

  • Local: Qwen 2.5-7B-Instruct (fallback to 1.5B on free tier)
  • MCP-Claude: Connect to Anthropic's Claude via MCP
  • MCP-OpenAI: Connect to OpenAI's models via MCP

Note: Local models work offline and are private. MCP models require API access but offer enhanced capabilities.

License

MIT License