metadata

title: Convert To Json
emoji: 🔬📅📊
colorFrom: blue
colorTo: green
sdk: gradio
sdk_version: 5.33.1
app_file: app.py
pinned: true
license: mit
short_description: Convert Free Text Into Json Using AI
tags:
  - mcp-server-track

youtube : https://youtu.be/PtWkJHNmo9k

for a faster & functional experience using ZeroGPU please visit : https://huggingface.co/spaces/Tonic/Convert-to-Json

🌊 Osmosis Structure - Text to JSON Converter

A powerful web application that converts unstructured text into well-formatted JSON using the Osmosis Structure 0.6B model. This tool is specifically designed for structured data extraction and format conversion tasks.

🌟 Features

Intelligent Text Processing: Automatically identifies and extracts key information from unstructured text
Schema Support: Optionally provide a JSON schema to structure the output according to your needs
Customizable Generation: Fine-tune the output with adjustable parameters:
- Temperature
- Max tokens
- Top-p sampling
- Top-k sampling
User-Friendly Interface: Clean and intuitive Gradio interface
Example Templates: Pre-configured examples to help you get started
GPU Acceleration: Optimized for GPU when available

🚀 Quick Start

Clone the repository:

git clone https://github.com/yourusername/Convert-to-Json.git
cd Convert-to-Json

Install dependencies:

pip install -r requirements.txt

Run the application:

python app.py

💻 Usage

Basic Usage

Enter your unstructured text in the input field
(Optional) Provide a JSON schema to structure the output
Adjust generation parameters if needed
Click "Convert" or press Enter
View the structured JSON output

Example Input

The conference will be held on June 10-12, 2024 at the Grand Hotel in San Francisco. 
Registration fee is $500 for early bird (before May 1) and $650 for regular registration. 
Contact info@conference.com for questions.

Example Schema

{
  "type": "object",
  "properties": {
    "event_start_date": {
      "type": "string",
      "format": "date"
    },
    "event_end_date": {
      "type": "string",
      "format": "date"
    },
    "location": {
      "type": "string"
    },
    "registration_fees": {
      "type": "object",
      "properties": {
        "early_bird_price": {
          "type": "number"
        },
        "regular_price": {
          "type": "number"
        },
        "early_bird_deadline": {
          "type": "string",
          "format": "date"
        }
      }
    },
    "contact_email": {
      "type": "string"
    }
  }
}

Example Output

{
  "event_start_date": "2024-06-10",
  "event_end_date": "2024-06-12",
  "location": "Grand Hotel, San Francisco",
  "registration_fees": {
    "early_bird_price": 500.0,
    "regular_price": 650.0,
    "early_bird_deadline": "2024-05-01"
  },
  "contact_email": "info@conference.com"
}

⚙️ Generation Parameters

Max Tokens: Controls the maximum length of the generated output (default: 512)
Temperature: Controls randomness in generation (default: 0.6)
- Lower values (e.g., 0.3) make output more focused and deterministic
- Higher values (e.g., 0.9) make output more diverse and creative
Top-p: Nucleus sampling parameter (default: 0.95)
Top-k: Number of highest probability tokens to consider (default: 20)

🛠️ Technical Details

Model: Osmosis Structure 0.6B parameters
Architecture: Qwen3 (specialized for structured data)
Purpose: Converting unstructured text to structured JSON format
Optimizations: Fine-tuned for data extraction and format conversion tasks

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request. For major changes, please open an issue first to discuss what you would like to change.

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

Thanks to the Hugging Face team for their excellent tools and resources
Special thanks to Yuvi Sharma and all the folks at Hugging Face for the community grant

🌟 Join Our Community

Join our active builder's community on Discord
Follow us on Hugging Face
Check out our GitHub
Contribute to MultiTonic