Selected Work
Projects That
Actually Ship
View All →
Gem AI | Production-Ready Contextual Engine
Developed a high-performance, context-aware AI assistant designed for full-stack integration. Unlike standard wrappers, Aeon AI leverages FastAPI and LangChain (LCEL) to manage persistent, session-based memory through RunnableWithMessageHistory. This allows the engine to maintain user identity and complex context across multiple interactions, serving as a scalable API backbone for production environments.
MediMindAI | Medical RAG System
Built a specialized Medical Retrieval-Augmented Generation (RAG) system that provides grounded answers to health queries. By utilizing Gemini Embeddings for semantic search and ChromaDB for vector storage, the app ensures that responses are retrieved directly from trusted medical datasets, significantly reducing AI hallucinations.