| --- |
| title: Medini AI Space |
| emoji: 🤖 |
| colorFrom: blue |
| colorTo: purple |
| sdk: gradio |
| sdk_version: 5.46.0 |
| app_file: app.py |
| pinned: false |
| --- |
| |
| # Medini AI Space |
|
|
| ## Overview |
| Medini AI is a generative AI application built on Hugging Face Spaces. It uses a text generation model (`PuruAI/Medini_Intelligence`) and a sentence embedding model (`all-MiniLM-L6-v2`) to provide AI-generated responses to user prompts. |
|
|
| ## Features |
| - Interactive Gradio interface. |
| - Public embedding model, no authentication token required. |
| - Fallback to GPT-2 if main model fails. |
| - Logging for debugging and monitoring. |
|
|
| ## How to Run |
| 1. Ensure all dependencies are installed: |
| ```bash |
| pip install -r requirements.txt |
| ``` |
| 2. Launch the app: |
| ```bash |
| python app.py |
| ``` |
| 3. Open the URL provided by Gradio to interact with the AI. |
|
|
| ## Notes |
| - No Hugging Face token is required for public model access. |
| - Handles model load failures gracefully. |
| - Recommended to deploy on Hugging Face Spaces for easy hosting. |
