Getting Started with Gradio: Quick Start Guide

Quick Start Guide

This guide will have you running your first Gradio app in under 5 minutes. Gradio is a Python library, so you only need Python 3.8+ and pip installed on your machine.

Installation

Prerequisites

• Python 3.8 or higher
• pip (Python package manager)
• Basic familiarity with Python functions

Install Gradio

pip install gradio

That is it. One command and you are ready to build ML web apps.

Your First Gradio App

Create a file called app.py with this minimal example:

import gradio as gr

def greet(name):
    return f"Hello {name}!"

demo = gr.Interface(fn=greet, inputs="text", outputs="text")
demo.launch()

Run it:

python app.py

Open the URL shown in your terminal (typically http://127.0.0.1:7860) and you will see your first Gradio app running.

Running with Docker

If you prefer containerized deployment, use the official Docker image:

docker pull gradio/gradio:latest
# Create a directory for your app
mkdir gradio-app && cd gradio-app
# Create your app.py file
# Then run:
docker run -d --name gradio -p 7860:7860 -v $(pwd):/app gradio/gradio:latest python /app/app.py

Building a Real ML Demo

Here is a more practical example — an image classifier using a Hugging Face model:

import gradio as gr
from transformers import pipeline

classifier = pipeline("image-classification", model="google/vit-base-patch16-224")

def classify_image(image):
    results = classifier(image)
    return {r["label"]: r["score"] for r in results}

demo = gr.Interface(
    fn=classify_image,
    inputs=gr.Image(type="pil"),
    outputs=gr.Label(num_top_classes=3),
    title="Image Classifier",
    description="Upload an image to classify it with ViT"
)
demo.launch()

Sharing Your App

To share your app publicly, pass share=True:

demo.launch(share=True)

Gradio generates a public URL (valid for 72 hours) that anyone can access. No server configuration needed.

Deploying to Hugging Face Spaces

For permanent hosting with custom domain, deploy to Hugging Face Spaces:

1. Go to huggingface.co and create a Space
2. Choose the Gradio SDK
3. Push your app.py and requirements.txt to the Space's repository
4. Your app is live at your-username/your-space-name

Self-Hosting with Docker Compose

For production self-hosting, use Docker Compose:

version: "3"
services:
  gradio:
    image: gradio/gradio:latest
    restart: unless-stopped
    ports:
      - "7860:7860"
    volumes:
      - ./app:/app
    command: python /app/app.py

Next Steps

Explore the Gradio documentation for advanced components, theming, authentication, and queue configuration. Gradio also supports Gradio Blocks for more complex layouts with multiple inputs/outputs arranged in custom grids and tabs.