Spaces:
Running
Running
| title: Ai Search System | |
| emoji: 📚 | |
| colorFrom: indigo | |
| colorTo: green | |
| sdk: gradio | |
| sdk_version: 5.29.1 | |
| app_file: app.py | |
| pinned: false | |
| license: mit | |
| short_description: Ai based search engine | |
| AI Search System | |
| This AI Search System uses Microsoft Phi-2 to search the web and provide comprehensive answers with sources. It's optimized to work efficiently on Hugging Face's free tier resources. | |
| Features | |
| 🌐 Web search capability using Wikipedia and other sources | |
| 💡 AI-generated answers with citations | |
| 📚 Source listing with links | |
| 🔗 Related topics suggestions | |
| ⚡ Optimized for performance on free tier | |
| Model | |
| This app uses microsoft/phi-2, a powerful yet efficient 2.7B parameter language model that provides excellent reasoning capabilities while being lightweight enough to run on limited resources. | |
| How to Use | |
| Enter your search query in the input box | |
| Click "Search" or press Enter | |
| Review the answer with citations | |
| Check sources for more information | |
| Explore related topics by clicking on them | |
| Optimizations | |
| This system is specifically optimized for Hugging Face's free tier: | |
| Uses the efficient Phi-2 model (2.7B parameters) | |
| Implements 4-bit quantization for low memory usage | |
| Employs caching for frequent queries | |
| Utilizes greedy decoding for faster responses | |
| Focuses on reliable data sources | |
| Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference | |