Touqeer Abbasi@touqeer_abbasi

NutriCo is built on the foundation of user-centered design, collecting specific user details such as age, weight, gender, and dietary preferences to offer personalized nutrition advice. The chatbot engages users in a conversational manner, asking questions and responding with relevant, detailed recommendations. Key Features: Interactive Conversations: NutriCo interacts with users in a natural, engaging format, making the experience intuitive and enjoyable. Personalized Advice: By collecting essential user details, NutriCo provides recommendations tailored to individual needs. Real-time Interaction: Users receive instant responses, allowing for dynamic and responsive dialogues. User-friendly Interface: The chat interface features clear icons and styled chat bubbles, ensuring a visually appealing and easy-to-navigate experience. Technical Details: Backend: Powered by Python and the OpenAI API, enabling robust and accurate response generation. Frontend: Developed using Streamlit for an interactive web-based interface. Data Management: Utilizes session state to handle user information and conversation history efficiently. Benefits: NutriCo's personalized approach ensures that each user receives advice tailored to their specific needs. The chatbot is available 24/7, providing instant support and keeping users engaged through its conversational format.

In-Car AI Agents is an innovative project designed to make in-car artificial intelligence smarter and more responsive in offline scenarios. Currently, most AI-powered car assistants rely on internet connectivity to process commands, leaving drivers without key functionalities in areas with poor or no network coverage. Our solution aims to address this gap by deploying edge-based AI models that can function without Wi-Fi, allowing drivers to interact with their cars using voice commands for basic operations such as controlling the air conditioning, navigation prompts, and music playback. The system uses pre-trained voice recognition models and offline edge computing to deliver real-time responses to the driver’s requests, all processed locally. Additionally, the project explores simple computer vision tasks like lane detection, integrated to run without network dependency. Our vision is to make cars smarter, safer, and more autonomous without requiring constant internet access. By providing an MVP, we aim to showcase how AI in cars can be optimized for offline use, thus improving the overall driving experience in areas where internet connectivity is unreliable.