An AI-powered Python tool for generating lunar visibility reports using LLMs (Large Language Models) such as Gemini, Groq, and LLaMA3 (via Ollama). Designed for astronomers, developers, and researchers interested in moon sighting, Hilal reports, and Islamic calendar computations.

🤖 Yui-Bot: A tsundere-inspired Telegram chatbot (K-ON! Yui Hirasawa) with memory, vent mode, fun commands & Gemini API.

AI-powered stock analysis and investment recommendation app using CrewAI agents, Gemini LLM, DuckDuckGo Search and real-time market data. Generates comprehensive reports, news summaries, and buy/hold/sell advice.

An iterative pipeline for optimizing prompt engineering strategies to generate high-quality structured requirements documents. Uses Dynamic Adaptive Prompt Optimization (DAPO) and an LLM-as-a-Judge to evaluate and refine prompts automatically.

Secure Cloud Run gRPC proxy for Vertex AI. Enables simple API key auth via gRPC metadata, using secure server-side IAM. Includes full Terraform setup.

Simulate realistic price negotiations between Buyer and Seller agents using LLM-generated messages and agent logic.

AI-powered hotel booking assistant built with Streamlit and Google ADK. Search, compare, and book hotels conversationally with real-time booking flow.

A futuristic, mobile-first, full-stack chatbot web application powered by Gemini LLM. Designed for developers, creators, and digital visionaries to transform natural language prompts into intelligent conversations, code, and creative outputs – all within a sleek, glassmorphism UI with multi-theme support.

The gemini integration for building tool and make it like agent

Interactive AI chatbot powered by Google Gemini LLM and built with Streamlit. Features conversational AI assistant "ReX" with emoji integration, dynamic backgrounds, auto-scrolling chat interface, and real-time responses using Vertex AI.

Clinical decision support with BigQuery AI (semantic search + AI-generated care cards)

This a Code Translator and Enhancer

A full-stack system that ingests emails, classifies them, extracts action items, summarizes content, and generates reply drafts using LLM-driven prompts. Built with FastAPI, Streamlit, SQLite/PostgreSQL, and Gemini LLM, it provides an interactive inbox, dynamic prompt management, and an AI assistant for inbox-wide reasoning.

A FastAPI and Gemini LLM-powered invoice reimbursement system that uses Retrieval Augmented Generation (RAG) to analyze documents against HR policies and provides an intelligent chatbot interface.

Backend modules I developed for the Fanshawe College Capstone project "Smart Travel System" including Smart Itinerary generation and Sentiment Insights using FastAPI, Google Places API, and Gemini LLM.

📚 Public dataset of 1000 books scraped from Books to Scrape using Python, crawl4ai, and Gemini LLM — provided in JSON & CSV formats for AI, RAG, and data science projects.

A full-stack system that ingests emails, classifies them, extracts action items, summarizes content, and generates reply drafts using LLM-driven prompts. Built with FastAPI, Streamlit, SQLite/PostgreSQL, and Gemini LLM, it provides an interactive inbox, dynamic prompt management, and an AI assistant for inbox-wide reasoning.

🚀 AI-powered financial market intelligence system using Google Gemini, LangChain, RAG & multi-agent orchestration. Real-time stock analysis, sentiment analysis, and ML-based predictions.

An intelligent platform to analyze legal PDFs with OCR, summarization, fraud detection, and natural language Q&A. Built with Spring Boot + Gemini LLM + Azure OCR, it enables users to upload legal documents, chat with them, detect suspicious content, and generate summaries in real time.