🍎 Gemini Nutrition Analyzer

An AI-powered nutrition assistant that identifies food items from images and estimates calorie intake using Google’s Gemini Vision model — all through an interactive Streamlit app.

---

🚀 Overview

This project demonstrates how to integrate Google’s Gemini Vision model into a Streamlit web app to perform multimodal reasoning — combining text prompts and image understanding.
Upload a photo of food, and the app will analyze its contents and estimate calorie intake for each item.

---

🧠 Key Features

• 🖼️ Image Understanding: Processes and interprets uploaded images using Gemini Vision.
• 🍽️ Calorie Estimation: Provides estimated calorie counts for each food item detected.
• 💬 Prompt Customization: Accepts user input for custom queries or contextual instructions.
• ⚙️ Streamlit UI: Simple and lightweight frontend for easy interaction.
• ⚠️ Input Validation: Ensures both image and prompt are provided before generating a response.

---

🧩 Tech Stack

• Python 3.10+
• Streamlit
• Google Generative AI (Gemini)
• Pillow (PIL)
• dotenv

---

📦 Project Structure

📂 gemini-nutrition-analyzer
├── app.py
├── requirements.txt
├── .env
└── README.md

---

🪜 Setup Guide

1️⃣ Create and Activate Virtual Environment

Using conda:

conda create -p venv python==3.10 -y
conda activate ./venv

2️⃣ Install Dependencies

Make sure you have a requirements.txt file in your project root, then run:

pip install -r requirements.txt

3️⃣ Set Up Environment Variables

Create a .env file in your project directory and add your Google API key:

GOOGLE_API_KEY=your_google_api_key_here

4️⃣ Run the Streamlit App

Launch the app locally using:

streamlit run app.py

---

🖥️ App Interface

1. Enter a text prompt (e.g., “Identify and estimate calories in this image”).
2. Upload an image (JPEG, PNG).
3. Click “Analyze Image” to process the inputs.
4. The app validates that both a prompt and image are provided.
5. View the AI-generated calorie breakdown and total estimate.

---

🎥 Code Reference

This project was inspired by the tutorial by Krish Naik:
🔗 Complete Langchain GEN AI Crash Course With 6 End To End LLM Projects With OPENAI,LLAMA2,Gemini Pro