FoodSpotHub

FoodSpotHub is a modern web application designed to help you discover the best food spots near your location. It features a Next.js frontend with dynamic routing and components, backed by a FastAPI backend that uses Google's Gemini LLM and Maps API to provide personalized food recommendations.

Features

• AI-Powered Recommendations: Get tailored food spot suggestions based on your location and queries using CrewAI and Gemini 1.5 Flash.
• Location-Aware: Automatically fetches your geolocation to find the best spots around you.
• Modern UI: Built with Next.js and Tailwind CSS for a sleek, responsive experience.

Tech Stack

• Frontend: Next.js (React), Tailwind CSS, Lucide React
• Backend: Python, FastAPI, CrewAI, Langchain, Google Generative AI
• APIs: Google Maps API (Places)

Getting Started

Prerequisites

• Node.js (v18+)
• Python (v3.12+)
• API Keys:
  • GOOGLE_MAPS_API_KEY
  • GEMINI_API_KEY

Backend Setup

1. Navigate to the backend directory:

   cd backend

2. Create and activate a virtual environment (recommended):

   python -m venv venv
   source venv/bin/activate  # On Windows: venv\Scripts\activate

3. Install dependencies:

   pip install -r requirements.txt

4. Create a .env file in the backend directory and add your keys:

   GOOGLE_MAPS_API_KEY=your_google_maps_key
   GEMINI_API_KEY=your_gemini_key
   

5. Start the FastAPI server:

   python main.py

   The backend will run on http://127.0.0.1:8000.

Frontend Setup

1. From the project root, navigate to the frontend code (or stay in root if that's where package.json is located):

   npm install

2. Configure your environment variables in .env.local if necessary.
3. Start the Next.js development server:

   npm run dev

4. Open http://localhost:3000 in your browser.

How it Works

1. The Next.js frontend requests the user's location via the browser's Geolocation API.
2. It sends the coordinates to the Next.js API route (/api/ai-recommendations), which acts as a proxy.
3. The request is forwarded to the FastAPI backend (/api/recommendations).
4. CrewAI kicks off an agentic workflow:
   • A custom tool fetches nearby restaurants using the Google Maps API.
   • The Gemini model analyzes the data and formats a curated JSON list of recommendations.
5. The frontend receives the data and renders it beautifully using FoodSpotCard components.