Nutri AI — Nutrition Agent

Nutri AI is a Streamlit app that uses a LangGraph ReAct agent plus the USDA FoodData Central API to answer nutrition questions, compare foods, and visualize macro/micronutrients.

Workflow Overview

The high‑level interaction flow between the user, agent, and tools is:

Key Files

• main.py: Streamlit UI for the app.

  • Sets up the page, sidebar, and two modes: “💬 Chat with Agent” and “🔍 Quick Nutrition Lookup”.
  • Manages session state, renders the chat history, and draws nutrition charts for USDA data.

• agent.py: LangGraph ReAct agent and tools.

  • Defines tools like search_food, get_nutrition, and compare_foods that call the USDA API.
  • Builds the Groq LLM client and build_agent_executor, plus run_agent used by the Streamlit app.

Running the App

1. Install dependencies:

pip install -r requirements.txt

2. Create a local.env (or .env) file in this folder with:

USDA_API_KEY=your_usda_api_key
GROQ_API_KEY=your_groq_api_key

3. Start Streamlit:

streamlit run main.py

Then open the URL shown in your terminal (usually http://localhost:8501) to use Nutri AI.