README.md

---
title: Recipe Oracle
emoji: 🍲
colorFrom: red
colorTo: pink
sdk: streamlit
sdk_version: "1.31.0"
app_file: app.py
pinned: false
---

# 🔮 The Recipe Oracle

Turn your fridge photos into delicious meals!  
This smart AI-powered web app uses **YOLOv8**, **NLP filtering**, and **Gemini LLM** to suggest creative recipes based on what you already have in your fridge or pantry.

---

## 📸 What It Does

- **Detects ingredients** from uploaded fridge photos (via YOLOv8)
- **Cleans & filters** the detected items (via NLP + WordNet)
- **Generates dish ideas** (via Gemini 1.5 Flash LLM)
- **Shows step-by-step recipes** with a clean Streamlit interface

---

## 🧠 Tech Stack

| Feature              | Tech Used                         |
|----------------------|------------------------------------|
| Ingredient Detection | YOLOv8 (Ultralytics)               |
| Filtering            | Python NLP + WordNet               |
| Recipe Generation    | Gemini LLM (Google Generative AI)  |
| Frontend             | Streamlit + Custom CSS             |

---

## 🛠️ How to Run Locally

```bash
# Clone the repo
git clone https://huggingface.co/spaces/ai-recipe-team/recipe-oracle
cd recipe-oracle

# (Optional) Create a virtual environment
python -m venv venv
source venv/bin/activate  # Windows: venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

# Add your Gemini API key in a .env file
echo GEMINI_API_KEY=your_key_here > .env

# Run the app
streamlit run app.py