Welcome to OmenFusionAi_Bot, your AI-powered Telegram assistant! This bot combines multiple AI capabilities including chat, image generation, voice interaction, and more.
/chat
- Have an intelligent conversation with the bot- Powered by Groq's advanced language models
- Context-aware conversations with memory
- Supports multiple languages
- 🖼️ Interactive Image Analysis: Send any image to get analysis options:
- 📝 Describe Image: Get detailed analysis using Groq's LLaMA model
- 🔍 Generate Caption: Get creative captions using Replicate
- 🎨 Smart Image Generation: Generate images from text descriptions
- Set your own Replicate API key with
/setreplicateapi
/analyze_video
- Get AI insights from video content/summarize_youtube
- Get summaries of YouTube videos- Supports full videos and clips
- Generates key points and timestamps
- Extracts main topics and themes
- Supports video files up to 50MB
- Powered by Google's Gemini Vision
/settings
- Configure bot settings/setgroqapi
- Set your Groq API key/setreplicateapi
- Set your Replicate API key/clear_chat
- Clear chat history/help
- View all commands
Try the bot now: @AIFusionCom_Bot
- Install dependencies:
pip install -r requirements.txt
- Configure environment variables in
.env
:
API_KEY=your_gemini_api_key
TELEGRAM_BOT_TOKEN=your_telegram_token
ROOT_PASSWORD=your_admin_password
ADMIN_USER_ID=your_admin_telegram_id
- Run the bot:
python app.py
- Python 3.8+
- Telegram Bot Token
- Google Gemini API Key
- Internet connection
- (Optional) Groq API Key - Can be set via
/setgroqapi
- (Optional) Replicate API Key - Can be set via
/setreplicateapi
- Uses Google's Gemini Pro for text and Gemini Vision for images/videos
- Implements efficient file handling and cleanup
- Includes error handling and user feedback
- Supports multiple file formats for videos and images
- Environment variables for sensitive data
- Admin-only maintenance commands
- Secure file handling
- API keys can be set individually by each user
- API keys are stored securely in memory
- Send any image to the bot
- Choose from two options:
- 📝 Describe Image: Get a detailed analysis of the image
- 🔍 Generate Caption: Get a creative caption
- Or use direct commands:
- Reply to an image with
/describe
for analysis - Reply to an image with
/caption
for a caption
- Reply to an image with
- Get your Groq API key from Groq
- Set it in the bot:
/setgroqapi your_api_key
- Get your Replicate API key from Replicate
- Set it in the bot:
/setreplicateapi your_api_key
Send a video (up to 50MB) and get detailed insights about:
- What's happening in the video
- Key objects and people
- Notable actions or events
- Overall context and setting
- Database for storing user data and settings
- Audio analysis
- Video summarization
Feel free to submit issues and enhancement requests!
- AI Models:
- Groq LLM for chat
- Gemini Pro for text analysis
- Gemini Vision for media analysis
- Replicate for image generation
- Backend: Python 3.8+ with asyncio
- Storage: In-memory with Redis support
- API Integration: REST APIs with rate limiting
- Security: AES encryption for API keys
Common issues and solutions:
- API Key Issues: Ensure keys are entered without quotes
- Video Upload Fails: Check file size and format
- Rate Limits: Wait a few minutes between requests
- Memory Issues: Use
/clear_chat
to reset context
This project is licensed under the MIT License - see the LICENSE file for details.