Building intelligent agricultural AI systems

Building intelligent agricultural AI systems requires combining machine learning with contextual knowledge retrieval and multi-step reasoning, making architecture and orchestration critical challenges.

Designed and contributed to an AI-powered Crop Yield Prediction and Farm Advisory System using machine learning, RAG, and agentic AI. Integrated ChromaDB and Hugging Face embeddings for semantic knowledge retrieval, leveraged LangGraph for multi-step reasoning, and used Groq LLM APIs to generate structured crop insights and recommendations. Built an interactive Streamlit interface for predictions and advisory reports.

Delivered an end-to-end AI solution for data-driven agricultural decision-making while strengthening expertise in machine learning pipelines, vector databases, Retrieval-Augmented Generation, agentic workflows, and LLM-powered applications.