-
π Currently building AI-powered applications and LLM-based systems, especially Retrieval-Augmented Generation (RAG) pipelines and intelligent chatbots. Recently developed MediCare-AI, a medical assistant using LangChain, Pinecone vector database, and OpenAI models for context-aware responses.
-
π± Exploring deeper into LLM application design, prompt engineering, vector databases, and scalable AI deployment using Docker, CI/CD pipelines, and cloud infrastructure.
-
π― Open to collaborating on AI/ML projects, LLM-powered tools, intelligent automation systems, and open-source developer tools that solve real-world problems.
-
π€ Interested in improving production-ready AI systems, including optimizing retrieval pipelines, vector search performance, and scalable ML application architecture.
-
π« Reach me on LinkedIn: https://www.linkedin.com/in/hetdesai03/ or explore my work on GitHub.
JavaScript CSS3 HTML5 Python Windows Terminal AWS Azure Google Cloud Bootstrap Django FastAPI Flask MySQL MongoDB SQLite Supabase Adobe NumPy Matplotlib Pandas PyTorch scikit-learn GitHub Actions GitHub Git Docker Notion Postman