Gradio Has a Free API — Build ML Demos in 5 Lines of Python

#ai #webdev #python #machinelearning

Gradio: The Fastest Way to Share ML Models

Gradio by Hugging Face lets you build interactive ML demos with minimal code. Upload an image, get predictions. Enter text, get translations. Any model, any interface, 5 lines of code.

Why Gradio

5 lines to create a web interface for any model
Auto-generated API — every Gradio app gets a REST API
Share links — public URL in one flag
Hugging Face Spaces — free hosting
20+ input/output types — image, audio, video, text, file

The Free API

Create an Interface

import gradio as gr

def greet(name, intensity):
    return "Hello, " + name + "!" * int(intensity)

demo = gr.Interface(
    fn=greet,
    inputs=["text", gr.Slider(value=1, minimum=1, maximum=10)],
    outputs="text"
)
demo.launch()  # Starts web server + API

Auto-Generated REST API

Every Gradio app automatically gets an API:

# Call the API
curl -X POST http://localhost:7860/api/predict \
  -H "Content-Type: application/json" \
  -d "{\"data\": [\"World\", 3]}"
# Response: {"data": ["Hello, World!!!"]}

# API docs at http://localhost:7860/api/

Image Classification

import gradio as gr
from transformers import pipeline

classifier = pipeline("image-classification")

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

demo = gr.Interface(
    fn=classify,
    inputs=gr.Image(type="pil"),
    outputs=gr.Label(num_top_classes=5)
)
demo.launch(share=True)  # Gets a public URL!

Chatbot

import gradio as gr
from openai import OpenAI

client = OpenAI()

def chat(message, history):
    messages = [{"role": "system", "content": "You are helpful."}]
    for h in history:
        messages.append({"role": "user", "content": h[0]})
        messages.append({"role": "assistant", "content": h[1]})
    messages.append({"role": "user", "content": message})
    response = client.chat.completions.create(model="gpt-4o", messages=messages)
    return response.choices[0].message.content

demo = gr.ChatInterface(chat)
demo.launch()

Real-World Use Case

A researcher built a medical image classifier. Needed doctors to test it without installing Python. Gradio: 5 lines of code, deployed to Hugging Face Spaces. Doctors open a URL, upload X-rays, get predictions. 200 users in the first week.

Quick Start

pip install gradio
python -c "import gradio as gr; gr.Interface(lambda x: x, text, text).launch()"

Resources

Need data for your ML models? Check out my scraping tools on Apify or email spinov001@gmail.com for custom data pipelines.

DEV Community