Delete README.md

README.md

@@ -1,161 +0,0 @@
-# NVIDIA NIM RAG Demo
-
-A Streamlit-based Retrieval-Augmented Generation (RAG) application that uses NVIDIA AI endpoints to answer questions about PDF documents. This demo showcases the integration of NVIDIA's AI models for document embeddings and question answering.
-
-## Features
-
-- **Document Processing**: Load and process PDF documents from a specified directory
-- **Vector Embeddings**: Generate embeddings using NVIDIA's `nv-embedqa-e5-v5` model
-- **Question Answering**: Answer questions using NVIDIA's Llama 3.3 70B model
-- **Retrieval-Augmented Generation**: Combine document retrieval with generative AI for accurate responses
-- **Interactive UI**: Clean Streamlit interface for easy interaction
-- **Error Handling**: Comprehensive error handling and user feedback
-
-## Prerequisites
-
-- Python 3.8 or higher
-- NVIDIA API key (obtain from [NVIDIA AI Foundation Models](https://build.nvidia.com/explore/discover))
-- Internet connection for API calls
-
-## Installation
-
-1. Clone or download this repository
-2. Navigate to the project directory
-3. Create a virtual environment (recommended):
-   ```bash
-   python -m venv venv
-   venv\Scripts\activate  # On Windows
-   # or
-   source venv/bin/activate  # On macOS/Linux
-   ```
-
-4. Install the required packages:
-   ```bash
-   pip install -r requirements.txt
-   ```
-
-## Setup
-
-1. Create a `.env` file in the project root directory
-2. Add your NVIDIA API key to the `.env` file:
-   ```
-   NVIDIA_API_KEY=your-api-key-here
-   ```
-   Replace `your-api-key-here` with your actual API key from NVIDIA.
-
-3. Place your PDF documents in the `us_census/` directory (or modify the code to point to your document directory)
-
-## Usage
-
-### Running the Main Application
-
-Run the fixed and optimized version:
-```bash
-streamlit run fixed_finalapp.py
-```
-
-### Alternative Versions
-
-- `streamlit_app.py`: Enhanced version with better error handling and user guidance
-- `finalapp.py`: Basic version with core functionality
-- `app.py`: Simple OpenAI-compatible API test script
-
-### How to Use the App
-
-1. Open the Streamlit app in your browser (usually at `http://localhost:8501`)
-2. Click "Create Document Embeddings" to process the PDF documents
-3. Wait for the embeddings to be created (this may take a few minutes for large document sets)
-4. Enter your question in the text input field
-5. View the AI-generated answer and relevant document excerpts
-
-## Configuration
-
-### Environment Variables
-
-- `NVIDIA_API_KEY`: Your NVIDIA API key (required)
-
-### Document Directory
-
-The app loads PDFs from the `./us_census` directory by default. To change this:
-- Modify the `PyPDFDirectoryLoader` path in the `vector_embedding()` function
-
-### Model Parameters
-
-You can adjust model parameters in the code:
-- Temperature: Controls randomness (0.0 to 1.0)
-- Max completion tokens: Maximum response length
-- Embedding model: Currently set to `nvidia/nv-embedqa-e5-v5`
-- LLM model: Currently set to `meta/llama-3.3-70b-instruct`
-
-## Project Structure
-
-```
-├── app.py                 # Simple API test script
-├── finalapp.py           # Basic Streamlit RAG app
-├── fixed_finalapp.py     # Optimized Streamlit RAG app
-├── streamlit_app.py      # Enhanced Streamlit RAG app
-├── requirements.txt      # Python dependencies
-├── .env                  # Environment variables (create this)
-├── .env.example          # Environment variables template
-├── us_census/            # Directory for PDF documents
-│   ├── document1.pdf
-│   ├── document2.pdf
-│   └── ...
-├── TODO.md               # Development task tracking
-└── README.md            # This file
-```
-
-## Dependencies
-
-Key libraries used:
-- `streamlit`: Web app framework
-- `langchain-nvidia-ai-endpoints`: NVIDIA AI model integration
-- `langchain-community`: Document loading and processing
-- `faiss-cpu`: Vector database for embeddings
-- `python-dotenv`: Environment variable management
-- `pypdf`: PDF document processing
-
-## Troubleshooting
-
-### Common Issues
-
-1. **API Key Error**: Ensure your `.env` file contains a valid `NVIDIA_API_KEY`
-2. **SSL Certificate Error**: The app uses the correct NVIDIA API endpoints; ensure internet connectivity
-3. **Document Loading Error**: Check that PDF files exist in the specified directory
-4. **Embedding Creation Failure**: Verify API key validity and internet connection
-
-### Error Messages
-
-- "NVIDIA_API_KEY not found": Add your API key to the `.env` file
-- "No documents found": Ensure PDFs are in the correct directory
-- "Error creating embeddings": Check API key and network connection
-
-## Contributing
-
-1. Fork the repository
-2. Create a feature branch
-3. Make your changes
-4. Test thoroughly
-5. Submit a pull request
-
-## License
-
-This project is for educational and demonstration purposes. Please check NVIDIA's terms of service for API usage.
-
-## Acknowledgments
-
-- NVIDIA for providing AI endpoints
-- LangChain for the RAG framework
-- Streamlit for the web app framework
-- FAISS for vector similarity search
-
-## Support
-
-For issues related to:
-- NVIDIA API: Visit [NVIDIA AI Foundation Models](https://build.nvidia.com/explore/discover)
-- LangChain: Check [LangChain documentation](https://python.langchain.com/)
-- Streamlit: See [Streamlit documentation](https://docs.streamlit.io/)
-
----
-
-**Note**: This is a demonstration application. For production use, consider implementing additional security measures, error handling, and performance optimizations.