Gradio Client - An intro

Gradio is well-known in the Machine Learning community, and recently they expanded their Apps to automatically include a REST API - Gradio Client, it’s awesome and here’s how it works!
python
app
rest
machine-learning
Author

Hampus Londögård

Published

February 17, 2025

Gradio Client

Most people in the AI-sphere (Deep Learning, LLM’s) are aware of the Gradio project (now under the huggingface umbrella).

Gradio in short

Gradio is a simple Machine Learning App framework that provides easy components and reactivity. See for yourself:

import gradio as gr

def greet(name):
    return "Hello " + name + "!"

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

One drawback is that input, output, and function are separated which reduces type-safety and removes all intellisense. This is a big one for me and makes me highly prefer streamlit & solara. Though I can’t deny all the greatness Gradio provides to the table.

Even though Gradio is well-known some people might’ve missed that they’ve added two new projects in their fast pace!

  1. gradio_client: A client that can call any Gradio Application (!)
    1. Gradio clients are easily deployed on HuggingFace, and there exist a ton of them. All are now accessible in a REST-like interface (including the compute)!
  2. gradio_lite: A WASM version of Gradio.
    1. Very simple to embed a Gradio app inside a HTML file or JS app.
    2. They’ve implemented smooth solutions for things like Multi File, PIP Requirements and more.
    3. WASM brings Serverless deployment with Low Latency and high Privacy.

How do I use Gradio Client?

Step 1: Connect to a Client

from gradio_client import Client, handle_file

client = Client("abidlabs/whisper")

Step 2: Predict

client.predict(
    audio=handle_file("audio_sample.wav")
)

>> "This is a test of the whisper speech recognition model."

Easy right?!

If we have multiple boxes / steps in the Gradio App we can call each of the components. The client usage of any Gradio App is easily found at the bottom.

Gradio Client Button in Gradio Apps (to the left)

And that opens a new menu which shows how to use each box of the App.

The API documentation and How-To-Guide after clicking

Available Clients

Anyone can run this as it supports regular REST requests! They supply a curl sample on how to query the App. But they’ve got a Python and JS native client.

Possibilities

Gradio implemented the whole thing in a way where you don’t need to do anything at all. In turn we now get user-friendly App that is easily deployed with an automatically included REST API. It’s two birds with one stone!

Combining this “App+API” deployment with the free, or paid, HuggingFace Spaces creates a high-value package!

HuggingFace Spaces

HuggingFace (HF) Spaces is as simple deployments get:

  • Free compute1
    • ZeroGPU available using Gradio SDK
  • Natively Support streamlit, Gradio, static (webapp)
  • Support any app via Docker2

HF Spaces can deploy apps via Client, git, or Drag n’ Drop.
You get a public pretty URL huggingface.co/spaces/<USER>/<APP_NAME> to share. All in all a great tool that puts the power into developers hands!

Outro

This blog is really short and to the point. The Gradio Client is sweet and I really wanted to share the experience.
The combination of App+API written at the same time is exciting, when enhancing it with HuggingFace Spaces it all becomes magical. And Gradio’s “auto-share” when running locally that can then provide an API too is not too shabby 😉

This is it for this time,
Hampus Londögård

Footnotes

  1. Pay for GPU and/or better CPU↩︎

  2. Multiple templates to get started fast↩︎