Merge pull request #1 from ChawlaAvi/codegen-bot/video-rag-gemini-demo

🎬 Add Video RAG with Gemini Streamlit Demo

Author: ChawlaAvi

video-rag-gemini/.env.example

@@ -0,0 +1,5 @@
+# Gemini API Configuration
+GEMINI_API_KEY=your_gemini_api_key_here
+
+# Get your API key from: https://aistudio.google.com/app/apikey
+

video-rag-gemini/README.md

@@ -0,0 +1,76 @@
+# 🎬 Video RAG with Gemini
+
+A Streamlit demo that allows you to upload videos and chat with them using Google's Gemini AI with multimodal capabilities.
+
+## Features
+
+- 📹 **Video Upload**: Support for multiple video formats (MP4, AVI, MOV, MKV, WEBM)
+- 🤖 **AI-Powered Chat**: Ask questions about your video content using Gemini's advanced video understanding
+- 💬 **Interactive Interface**: Clean chat interface with streaming responses
+- 🔄 **Session Management**: Maintain chat history and video context
+- ⚡ **Real-time Processing**: Upload and process videos with progress feedback
+
+## Setup
+
+1. **Install Dependencies**
+   ```bash
+   pip install -r requirements.txt
+   ```
+
+2. **Get Gemini API Key**
+   - Visit [Google AI Studio](https://aistudio.google.com/app/apikey)
+   - Create a new API key
+   - Keep it secure - you'll enter it in the app
+
+3. **Run the Application**
+   ```bash
+   streamlit run app.py
+   ```
+
+## Usage
+
+1. **Enter API Key**: Input your Gemini API key in the sidebar
+2. **Upload Video**: Choose a video file (supported formats listed above)
+3. **Wait for Processing**: The video will be uploaded and processed by Gemini
+4. **Start Chatting**: Ask questions about your video content!
+
+## Example Questions
+
+- "What is happening in this video?"
+- "Summarize the main events"
+- "Who are the people in this video?"
+- "What objects can you see?"
+- "Describe the setting and environment"
+- "What actions are taking place?"
+
+## Technical Details
+
+- **Video Processing**: Uses Gemini's File API for video upload and processing
+- **Multimodal AI**: Combines video understanding with natural language processing
+- **File Size Limits**: Large files (>100MB) may take longer to process
+- **Supported Formats**: MP4, AVI, MOV, MKV, WEBM
+
+## Limitations
+
+- Video processing time depends on file size and complexity
+- Large files may fail to upload or process
+- API rate limits may apply based on your Gemini API plan
+- Some video formats may not be supported
+
+## Troubleshooting
+
+- **Upload Fails**: Check video format and file size
+- **Processing Stuck**: Wait a few minutes, large files take time
+- **API Errors**: Verify your API key is correct and has sufficient quota
+- **No Response**: Try refreshing the page and re-uploading the video
+
+## Built With
+
+- [Streamlit](https://streamlit.io/) - Web app framework
+- [Google Gemini API](https://ai.google.dev/gemini-api) - Multimodal AI capabilities
+- [Python](https://python.org/) - Backend processing
+
+---
+
+*Part of the AI Engineering Hub - Building practical AI applications*
+

video-rag-gemini/USAGE.md

@@ -0,0 +1,184 @@
+# 🎬 Video RAG Usage Guide
+
+This guide will help you get started with the Video RAG demo using Google's Gemini API.
+
+## Quick Start
+
+### 1. Setup Environment
+
+```bash
+# Clone or navigate to the video-rag-gemini directory
+cd video-rag-gemini
+
+# Install dependencies
+pip install -r requirements.txt
+
+# Test your setup
+python test_setup.py
+```
+
+### 2. Get Gemini API Key
+
+1. Visit [Google AI Studio](https://aistudio.google.com/app/apikey)
+2. Sign in with your Google account
+3. Click "Create API Key"
+4. Copy your API key
+
+### 3. Configure API Key
+
+**Option A: Environment Variable (Recommended)**
+```bash
+# Create .env file
+cp .env.example .env
+
+# Edit .env file and add your API key
+GEMINI_API_KEY=your_actual_api_key_here
+```
+
+**Option B: Enter in App**
+- You can also enter the API key directly in the Streamlit sidebar
+
+### 4. Run the Application
+
+```bash
+streamlit run app.py
+```
+
+The app will open in your browser at `http://localhost:8501`
+
+## Using the App
+
+### Step 1: Enter API Key
+- If you haven't set up the environment variable, enter your Gemini API key in the sidebar
+- The key is masked for security
+
+### Step 2: Upload Video
+- Click "Choose a video file" in the sidebar
+- Supported formats: MP4, AVI, MOV, MKV, WEBM
+- File size limit: ~100MB (larger files may fail)
+- Wait for the video to be processed (this can take several minutes)
+
+### Step 3: Start Chatting
+- Once processing is complete, you'll see example questions
+- Click on example questions or type your own
+- Ask anything about the video content!
+
+## Example Questions
+
+### General Analysis
+- "What is happening in this video?"
+- "Summarize the main events"
+- "Describe the overall scene"
+
+### People & Objects
+- "Who are the people in this video?"
+- "What objects can you see?"
+- "Describe the clothing or appearance of people"
+
+### Actions & Events
+- "What actions are taking place?"
+- "What is the sequence of events?"
+- "What happens at the beginning/middle/end?"
+
+### Environment & Setting
+- "What is the setting or location?"
+- "Describe the environment"
+- "What time of day is it?"
+
+### Specific Details
+- "What colors are prominent in the video?"
+- "What sounds might be present?" (Note: Gemini analyzes visual content)
+- "What emotions are expressed?"
+
+## Tips for Best Results
+
+### Video Quality
+- Use clear, well-lit videos
+- Avoid very shaky or blurry footage
+- Higher resolution generally works better
+
+### Question Types
+- Be specific in your questions
+- Ask about visual elements (Gemini can't hear audio)
+- Break complex questions into simpler parts
+
+### File Management
+- Keep video files under 100MB when possible
+- Use common formats (MP4 is most reliable)
+- Compress large files if needed
+
+## Troubleshooting
+
+### Common Issues
+
+**"Error uploading video"**
+- Check file format and size
+- Ensure stable internet connection
+- Try a different video file
+
+**"Video processing failed"**
+- File may be too large or corrupted
+- Try compressing the video
+- Check if format is supported
+
+**"Error generating response"**
+- API key may be invalid or expired
+- Check your API quota/billing
+- Try a simpler question first
+
+**App is slow or unresponsive**
+- Large videos take time to process
+- Wait a few minutes before trying again
+- Refresh the page if needed
+
+### Getting Help
+
+1. **Check Setup**: Run `python test_setup.py`
+2. **Verify API Key**: Make sure it's correct and has quota
+3. **Test with Small Video**: Try a short, small video first
+4. **Check Logs**: Look at the Streamlit terminal for error messages
+
+## Advanced Usage
+
+### Command Line Demo
+```bash
+# Run the command-line demo
+python demo.py
+```
+
+### Environment Variables
+```bash
+# Set API key for session
+export GEMINI_API_KEY=your_key_here
+
+# Run app
+streamlit run app.py
+```
+
+### Custom Configuration
+You can modify `app.py` to:
+- Change the Gemini model (e.g., gemini-1.5-flash for faster responses)
+- Adjust file size limits
+- Customize the UI theme
+- Add additional video formats
+
+## API Limits & Costs
+
+- **Free Tier**: Limited requests per minute/day
+- **File Size**: ~100MB per file
+- **Processing Time**: Varies by video length and complexity
+- **Rate Limits**: May need to wait between requests
+
+Check [Gemini API pricing](https://ai.google.dev/pricing) for current limits and costs.
+
+## Security Notes
+
+- Never share your API key publicly
+- Use environment variables for production
+- The app doesn't store videos permanently
+- Videos are uploaded to Google's servers for processing
+
+---
+
+*Happy video chatting! 🎬✨*
+