Ollama_VLM 🤖🧠📷

This notebook demonstrates a multimodal interaction system using:

• 🎤 Voice input (SpeechRecognition)
• 📷 Live image input (OpenCV)
• 🧠 Vision-Language reasoning (LLaVA via Ollama)
• 🔊 Spoken responses (pyttsx3)

How it works:

1. Captures webcam image
2. Listens for a question
3. Sends both to LLaVA (Ollama) for processing
4. Speaks the result

Perfect for building AI-powered robotic assistants!

---

Run locally with: pip install cv2 pyttsx3 speechrecognition ollama numpy

Ensure ollama and llava are properly set up on your machine.