Harsh Gidwani
AI & Data Science student passionate about real-world projects
about
Harsh is an Integrated Btech student specializing in AI & Data Science @ MIT WPU with a passion for
solving complex problems and building smart, real-world solutions. With a strong foundation in Python,
machine learning, and generative AI, he focuses on creating meaningful, high-quality tech that drives
impact. Whether it's a deep learning model or a full-stack project, he brings consistency, clarity, and
creative energy to every line of code.
Let’s build something extraordinary together!
skills
Languages
- HTML
- CSS
- JavaScript
- Python
- C++
- C
Frameworks
- LangChain
- TensorFlow
- Scikit-Learn
- Bootstrap
- Tailwind
- OLLAMA
Tools
- Git
- VS Code
- Google Colab
- Jupyter notebook
- Github
- Figma
Ready to learn more about my journey?
Discover my complete story, achievements, and what drives my passion for AI and technology.
projects
LCEL Chatbot
Advanced AI chatbot using LangChain Expression Language with context-aware responses, memory retention, and real-time streaming.
BERT Visualization
Interactive tool visualizing BERT's attention patterns, token embeddings, and layer representations for NLP explainability.
Customer Churn Analysis
ML solution predicting churn probability — XGBoost, feature importance, and 89% accuracy with 0.92 AUC on validation data.
YouTube Summarizer
GenAI tool extracting and summarizing YouTube video transcripts — supports multiple languages and customizable summary lengths.
NLP Resume Parser
Automated resume data extraction using spaCy — skills, experience, education across PDF, DOCX for efficient recruitment workflows.
OpenAI Chatbot
Multi-turn conversational chatbot powered by OpenAI APIs with contextual awareness and natural language generation via Flask.
Ollama LLM Chatbot
Fully private local LLM chatbot using Ollama — zero external API calls, runs entirely on-device for maximum data privacy.
IMDB Sentiment Analysis
Sentiment analysis pipeline comparing SVM, Naive Bayes, and LSTM models on IMDB reviews with rich visualization output.
