Hardware Design Engineer | Python Developer | Data Scientist
An AI-powered hospital chatbot built with the Ollama 3.2 LLM model and Retrieval-Augmented Generation (RAG) to deliver accurate, secure, and context-aware responses. Designed to streamline communication in healthcare settings by providing instant access to health information, medical advice, appointment scheduling, and more.
GitHub RepositorySentimentSpectrum is a web application designed by usiing Flask framework to predict customer sentiment for eCommerce websites like Flipkart using a BERT-based pre-trained model. This application offers real-time sentiment analysis with labels such as Positive, Negative, and Neutral, providing valuable insights into customer feedback. The project is built using the Flask framework and integrates various tools for data collection, processing, visualization, and machine learning, making it ideal for applications in data science, machine learning (ML), and artificial intelligence (AI).
GitHub RepositoryDeveloped a web-based machine learning model to recommend music tracks clustered by mood using audio features, enabling personalized playlists and enhanced user experiences. The goal of this project is to develop a machine learning model that clusters music tracks based on their mood using key audio features. This enables personalized music recommendations and playlists for users, enhancing their listening experience. This project uses unsupervised learning to cluster songs based on their attributes, providing insight into how various musical qualities like energy, danceability, and valence relate to different moods.
GitHub RepositoryA few months ago, I developed a web application called SentimentSpectrum using the Flask framework. This project aimed to predict customer sentiment for eCommerce websites like Flipkart
In today’s fast-evolving digital landscape, businesses and individuals rely heavily on proprietary SaaS tools for essential tasks like website creation, data management, and email marketing. Solutions like
RAG, or Retrieval Augmented Generation, provides LLMs with the ability to retrieve information from one or multiple data sources and use that information to answer user queries. Setting up a basic RAG system is relatively straightforward;