Conversational Image Recognition Chatbot

This research introduces a Conversational Image Recognition Chatbot powered by generative AI, designed to enable users to interact naturally with both text and visual inputs. The system combines intelligent dialogue with image understanding, allowing users to upload images, ask context-specific questions, and receive meaningful responses in real time. At its core is Google’s Gemini 2.0 Flash model, which supports multimodal processing and delivers fast, focused replies based on both textual prompts and visual content. The application is built using the Flask framework on the backend, with a clean, responsive frontend powered by HTML templates and Bootstrap. It handles image uploads using the Python Imaging Library (PIL) and supports RESTful API endpoints for seamless communication between the client and server. Adjustable AI parameters offer flexibility in response generation, while error handling ensures stable, user-friendly performance. This chatbot bridges the gap between image recognition and natural language conversation, offering a unified platform for educational, creative, and productivity- based use cases. The project demonstrates how generative AI can be effectively applied to enhance human-computer interaction by making both visual and verbal inputs part of a single conversational experience.