Repository files navigation

This project demonstrates a fullstack application using a React frontend and a LangGraph-powered backend agent. The agent is designed to perform comprehensive research on a user's query by dynamically generating search terms, querying the web using Google Search, reflecting on the results to identify knowledge gaps, and iteratively refining its search until it can provide a well-supported answer with citations. This application serves as an example of building research-augmented conversational AI using LangGraph and Google's Gemini models.

• 💬 Fullstack application with a React frontend and LangGraph backend.
• 🧠 Powered by a LangGraph agent for advanced research and conversational AI.
• 🔍 Dynamic search query generation using Google Gemini models.
• 🌐 Integrated web research via Google Search API.
• 🤔 Reflective reasoning to identify knowledge gaps and refine searches.
• 📄 Generates answers with citations from gathered sources.
• 🔄 Hot-reloading for both frontend and backend during development.

The project is divided into two main directories:

• frontend/: Contains the React application built with Vite.
• backend/: Contains the LangGraph/FastAPI application, including the research agent logic.

Follow these steps to get the application running locally for development and testing.

1. Prerequisites:

• Node.js and npm (or yarn/pnpm)
• Python 3.11+
• GEMINI_API_KEY: The backend agent requires a Google Gemini API key.
  1. Navigate to thebackend/ directory.
  2. Create a file named.env by copying thebackend/.env.example file.
  3. Open the.env file and add your Gemini API key:GEMINI_API_KEY="YOUR_ACTUAL_API_KEY"

2. Install Dependencies:

Backend:

cd backendpip install.

Frontend:

cd frontendnpm install

3. Run Development Servers:

Backend & Frontend:

make dev

This will run the backend and frontend development servers. Open your browser and navigate to the frontend development server URL (e.g.,http://localhost:5173/app).

Alternatively, you can run the backend and frontend development servers separately. For the backend, open a terminal in thebackend/ directory and runlanggraph dev. The backend API will be available athttp://127.0.0.1:2024. It will also open a browser window to the LangGraph UI. For the frontend, open a terminal in thefrontend/ directory and runnpm run dev. The frontend will be available athttp://localhost:5173.

The core of the backend is a LangGraph agent defined inbackend/src/agent/graph.py. It follows these steps:

1. Generate Initial Queries: Based on your input, it generates a set of initial search queries using a Gemini model.
2. Web Research: For each query, it uses the Gemini model with the Google Search API to find relevant web pages.
3. Reflection & Knowledge Gap Analysis: The agent analyzes the search results to determine if the information is sufficient or if there are knowledge gaps. It uses a Gemini model for this reflection process.
4. Iterative Refinement: If gaps are found or the information is insufficient, it generates follow-up queries and repeats the web research and reflection steps (up to a configured maximum number of loops).
5. Finalize Answer: Once the research is deemed sufficient, the agent synthesizes the gathered information into a coherent answer, including citations from the web sources, using a Gemini model.

For quick one-off questions you can execute the agent from the command line. Thescriptbackend/examples/cli_research.py runs the LangGraph agent and prints thefinal answer:

cd backendpython examples/cli_research.py"What are the latest trends in renewable energy?"

In production, the backend server serves the optimized static frontend build. LangGraph requires a Redis instance and a Postgres database. Redis is used as a pub-sub broker to enable streaming real time output from background runs. Postgres is used to store assistants, threads, runs, persist thread state and long term memory, and to manage the state of the background task queue with 'exactly once' semantics. For more details on how to deploy the backend server, take a look at theLangGraph Documentation. Below is an example of how to build a Docker image that includes the optimized frontend build and the backend server and run it viadocker-compose.

Note: For the docker-compose.yml example you need a LangSmith API key, you can get one fromLangSmith.

Note: If you are not running the docker-compose.yml example or exposing the backend server to the public internet, you should update theapiUrl in thefrontend/src/App.tsx file to your host. Currently theapiUrl is set tohttp://localhost:8123 for docker-compose orhttp://localhost:2024 for development.

1. Build the Docker Image:

Run the following command from theproject root directory:

docker build -t gemini-fullstack-langgraph -f Dockerfile.

2. Run the Production Server:

GEMINI_API_KEY=<your_gemini_api_key> LANGSMITH_API_KEY=<your_langsmith_api_key> docker-compose up

Open your browser and navigate tohttp://localhost:8123/app/ to see the application. The API will be available athttp://localhost:8123.

• React (withVite) - For the frontend user interface.
• Tailwind CSS - For styling.
• Shadcn UI - For components.
• LangGraph - For building the backend research agent.
• Google Gemini - LLM for query generation, reflection, and answer synthesis.

This project is licensed under the Apache License 2.0. See theLICENSE file for details.