Ajay Kommineni

Ajay Kommineni

Gen AI Developer and Enthusiast

About Me

Final-year Computer Science and Engineering student at Vellore Institute of Technology, AP. Passionate about Deep Learning, AI trends, and building large language models (LLMs). My interests extend beyond tech into space exploration and aviation.

Education

BTech in Computer Science and Engineering

VIT AP University

Specialization: AI and ML

2021 - 2025

CGPA: 8.73/10

Projects

PagePod - Multi-Agent Web content Podcast generator

This project uses a multi-agent framework to automatically generate podcasts from website content. It leverages the power of AI to scrape web content, refine it, create a script, and convert it to speech.

View on GitHub

Stock Insight Agentic Framework with Autogen

This is a multi-agent system that uses LLM's to analyze financial data, review market news, and predict company stock performance. Built with the autogen library, it coordinates multiple agents, each assigned a specific role in processing financial information and making predictions

View on GitHub

AI Voice Over and Script Generator for Youtube

This project is a Streamlit application that uses various LLM models to generate YouTube scripts and voiceovers. It aims to assist content creators in producing high-quality YouTube videos with minimal effort.

View on GitHub

Gemma Model Finetuning Using Lora

Finetuned Google's Open source Gemma 2b model on Indian history domain using Lora technique , huggingface transformers library

View on GitHub

Web Page ChatBot using Llama index

Web Page Q&A Chatbot is a Streamlit web application designed to interactively answer questions based on web page data. The chatbot uses LLMS such as Hugging Face, Gemini or OpenAI to provide accurate and context-aware responses.

View on GitHub

Gemini-File with Llama-Index

Gemini-File is a Streamlit web application that allows users to upload PDF files, index their contents using the Gemini search engine from the Llama-Index library, and query the documents.

View on GitHub

Face Emotion Detection using CNN

A project involving training a Convolutional Neural Network (CNN) for facial expression recognition.

View on GitHub

Boston Housing Price Prediction using Regression

A machine learning project for predicting median housing costs in different areas of Boston.

View on GitHub

Fruits/Veggies classifications using Inception V3 & integrating with Google Palm API

A project that uses a fine tuned InceptionV3 model to identify vegetables or fruits in uploaded images also provide nutrition info using Google PaLM API

View on GitHub

Publications

Multimodal Approach to Emotion Recognition using Deep Learning

ICIMIA (International Conference on Intelligent Machines, Innovation and Automation) · Dec 23, 2023

View Publication

Paddy Crop Disease Detection using LeNet and MobileNet Models

INDIACom 2024

View Publication

Certifications

  • AI and ML Externship Certificate, Google Developers
  • LMOPS1x: Introduction to Generative AI, EDX

Contact