Spaces:
Build error
Build error
| title: RAGsystem | |
| emoji: 🌍 | |
| colorFrom: green | |
| colorTo: blue | |
| sdk: gradio | |
| sdk_version: 5.25.2 | |
| app_file: app.py | |
| pinned: false | |
| short_description: RAG System with Phi-2 | |
| # PDF RAG System with Phi-2 | |
| This application allows you to upload PDF documents and ask questions about their content. It uses a Retrieval-Augmented Generation (RAG) pipeline with the Phi-2 language model. | |
| ## Features | |
| - PDF document upload and processing | |
| - Text and table extraction from PDFs | |
| - Hybrid search combining vector embeddings and BM25 | |
| - Query expansion for better search results | |
| - Streaming response generation | |
| ## How to Use | |
| 1. Upload your PDF files | |
| 2. Process the documents | |
| 3. Ask questions about the content | |
| 4. Adjust retrieval and generation parameters as needed | |
| ## Technical Details | |
| - Uses Phi-2 language model via llama.cpp | |
| - Sentence Transformers for document embeddings | |
| - FAISS for vector search | |
| - BM25 for keyword search | |
| - Hybrid retrieval with configurable weighting | |