Farfalle

Open-source AI-powered search engine.

💻 Live Demo

farfalle.dev

📖 Overview

• 🛠️ Tech Stack
• 🏃🏿‍♂️ Getting Started
• 🚀 Deploy

🛣️ Roadmap

• Add support for local LLMs
• Docker deployment setup

🛠️ Tech Stack

• Frontend: Next.js
• Backend: FastAPI
• Search API: Tavily
• Logging: Logfire
• Rate Limiting: Redis
• Components: shadcn/ui

🏃🏿‍♂️ Getting Started

Prerequisites

• Node.js
• pnpm or npm
• Python
• Poetry

Get API Keys

• Tavily
• OpenAI
• Groq

1. Clone the Repo

git clone git@github.com:rashadphz/farfalle.git

2. Install Dependencies

Frontend

cd farfalle/src/frontend
pnpm install

Backend

cd farfalle/src/backend
poetry install

3. Secrets

Create a .env file in the root of the project and add these variables:

TAVILY_API_KEY=...
OPENAI_API_KEY=...
GROQ_API_KEY=...

# Everything below is optional

# Logfire
LOGFIRE_TOKEN=

# (True | False)
RATE_LIMIT_ENABLED=

# Redis URL
REDIS_URL=

4. Run the App Locally

Frontend

cd farfalle/src/frontend
pnpm dev

Backend

cd farfalle/src/backend
poetry shell
uvicorn backend.main:app --reload

Visit http://localhost:3000 to view the app.

🚀 Deploy

Backend

After the backend is deployed, copy the web service URL to your clipboard. It should look something like: https://some-service-name.onrender.com.

Frontend

Use the copied backend URL in the NEXT_PUBLIC_API_URL environment variable when deploying with Vercel.

And you're done! 🥳