This project focuses on developing a real-time, intelligent healthcare assistant powered by Agentic RAG (Retrieval-Augmented Generation) and the LangChain framework. Designed to provide multimodal support—text, voice, and document-based inputs—it aims to assist medical personnel and individuals in remote or defense settings. The system ensures timely interventions, supports diagnosis, and enables efficient access to critical medical knowledge, making it especially valuable in underserved or resource-constrained environments.Â
Emo-Ai voice chatbot Project 1 - An Emotionally Intelligent Voice Chatbot Using Deep Learning with Retrieval-Augmented Generation and Few-Shot Voice Cloning for Personalized Human-Computer Interaction
This project proposes the development of an advanced voice chatbot capable of emotionally intelligent conversations, powered by Retrieval-Augmented Generation (RAG) and few-shot voice cloning. The chatbot leverages state-of-the-art deep learning techniques to understand user intention, detect emotional tone, and generate contextually relevant and emotionally appropriate responses, Additionally, the system incorporates a voice cloning module that can replicate a specific person’s voice using minimal training data, enabling personalized interactions in the desired voice. Emo-Ai voice chatbotÂ
I'll update this project soon.Â
 project -3  Predicting Weather and Climate Risks with Machine Learning
This is my 3rd-semester project for my M.Sc. degree at Central University of South Bihar. This advanced project focuses on predicting weather and climate risks by leveraging the power of machine learning Geoclim and vast datasets from Google Earth Engine. The goal is to develop predictive models that analyze environmental data to forecast potential weather-related hazards. By integrating geospatial data processing with sophisticated algorithms, GeoclimAI helps in understanding climate patterns, assessing risks, and providing valuable insights for better decision-making in climate-sensitive industries. This project stands at the intersection of environmental science and AI, showcasing the potential of data-driven approaches in addressing global climate challenges.
 project -3 stockSage - where we developed StockSage, an AI-power stocksage red stock analysis bot.Â
OUR PROJECT utilizes Google Gemini 1.5 Pro Model API for advanced generative capabilities, yfinance for real-time stock data retrieval, and Hugging Face tokenization for efficient text processing and predictions. The project is a step toward building an advanced Generative AI solution for the financial domain, helping investors make informed decisions through real-time insights and predictions. Â
 project 2 - Generative AI application MOvie-Transcirptor  to build this project my aim to creating audio data set to train AI powered voice chatbots that are able to clone the specific voice MovieTranscriptorÂ
 VisionEdge: Advanced Object Detection with Deep Learning and RCNN
VisionEdge is an advanced object detection visionEdge ystem that leverages the power of deep learning through the RCNN (Region-based Convolutional Neural Networks) algorithm. This project focuses on accurately identifying and classifying objects within images, even in complex and cluttered environments. By utilizing the RCNN architecture, VisionEdge can detect objects with high precision, making it suitable for applications such as autonomous vehicles, surveillance, and image analysis. This project represents my exploration into the field of computer vision, showcasing how cutting-edge neural networks can be applied to solve real-world challenges in image recognition.
I'll update this project soon.Â