Your First /predict Endpoint
Load a model and return a prediction over HTTP.
Your First /predict Endpoint is a free MLOps Academy lesson on CoddyKit — lesson 1 of 4. You can read the complete lesson below for free — then practise it hands-on in the browser with a built-in code editor and a 24/7 AI tutor. It is part of the MLOps Academy learning path, one of 4 lessons in the course, and your progress syncs across the web and the CoddyKit app.
From Notebook to API
A model in a notebook helps only you. To serve real users, you wrap it in an API that anyone can call over the network. 🚀
Why FastAPI
FastAPI is a modern Python web framework that is fast to write, validates input for you, and auto-generates interactive docs.
Install It
You need two pieces: FastAPI itself and a server to run it. Install both with pip in one line.
pip install fastapi uvicornCreate the App
Everything starts from one app object. You create a FastAPI instance and attach routes to it.
from fastapi import FastAPI
app = FastAPI()What an Endpoint Is
An endpoint is a URL your app responds to, like /predict. Each one runs a Python function when someone calls it.
Load Your Model First
Before predicting, you load the trained model from disk. Here joblib reads a saved scikit-learn model into memory.
import joblib
model = joblib.load("model.joblib")Declare the Route
You mark a function as a POST endpoint with a decorator. POST fits prediction because you send data in the request body.
@app.post("/predict")
def predict(features: list[float]):
...Run the Prediction
Inside the function you call the model. predict expects a 2D input, so you wrap the row in a list before passing it.
pred = model.predict([features])
result = pred[0]Return JSON
Whatever your function returns, FastAPI serializes to JSON automatically. Return a plain dict and the client gets clean JSON.
return {"prediction": result}Start the Server
You launch the app with uvicorn, pointing it at the module and the app object. The reload flag restarts on code changes.
uvicorn main:app --reloadTry the Auto Docs
Visit /docs in your browser and FastAPI shows an interactive page where you can test /predict without writing any client code. 🎉
Quick Check
You want clients to send feature data to your model. Which HTTP method fits a /predict endpoint?
Recap
You wrapped a model in FastAPI: create the app, load the model, expose a POST /predict that returns JSON, and run it with uvicorn. That is a live API! 🙌
Frequently asked questions
Is the “Your First /predict Endpoint” lesson free?
Yes — the full text of “Your First /predict Endpoint” is free to read here on the web, and the MLOps Academy course includes 4 lessons in total. To practise it interactively (a built-in code editor and a 24/7 AI tutor) and unlock the rest of the MLOps Academy course, upgrade to CoddyKit PRO.
What will I learn in “Your First /predict Endpoint”?
Load a model and return a prediction over HTTP. You practise MLOps Academy with hands-on code you run directly in the browser, and a 24/7 AI tutor answers your questions as you work through the lesson.
Do I need any experience to start MLOps Academy?
No prior experience is required. MLOps Academy on CoddyKit is structured for beginners through advanced learners; this is — lesson 1 of 4, so you can start here or from the beginning and move at your own pace.
How long does the “Your First /predict Endpoint” lesson take?
Most CoddyKit lessons take about 5–10 minutes. Each one is bite-sized and interactive, so you make steady progress and pick up exactly where you left off across the web and the app.
Can I write and run code in this MLOps Academy lesson?
Yes. Every MLOps Academy lesson includes a built-in code editor, so you write and run real code right in your browser and get instant AI feedback — no local setup required.
All lessons in this course
- Your First /predict Endpoint
- Validate Requests with Pydantic
- Load the Model Once at Startup
- Add a /health Readiness Check