# Gemini Fullstack LangGraph Quickstart

An example fullstack application that pairs a React frontend with a LangGraph-powered research agent, showing how to build a conversational AI that generates search queries, searches the web, and answers with citations.

This project is a fullstack example combining a React frontend with a LangGraph-powered backend agent, demonstrating research-augmented conversational AI built on Google's Gemini models.

Given a user's query, the agent dynamically generates search terms, queries the web through the Google Search API, reflects on the results to identify remaining knowledge gaps, and iteratively refines its search until it can provide a well-supported answer with citations.

The frontend is built with React and Vite, and the backend is a LangGraph and FastAPI application containing the research agent's logic; both support hot-reloading during local development.

Website: https://ai.google.dev/gemini-api/docs/google-search