Building a Machine Learning API with FastAPI

FastAPI is a modern, fast (high-performance), web framework for building APIs with Python 3.7+ based on standard Python type hints. It’s fast to code and fast to run. In this article, we’ll take a look at how to build a Machine Learning API with FastAPI.

Step 1: Setting up FastAPI

First, you need to install FastAPI by running the following command:


pip install fastapi


Next, create a new file for your FastAPI application. For example, create a file called app.py:


touch app.py


Step 2: Create a FastAPI Application

Inside your app.py file, import FastAPI and create an instance of the FastAPI class:


from fastapi import FastAPI

app = FastAPI()


Step 3: Create Machine Learning Endpoints

Now, you can create endpoints for your machine learning API. For example, let’s create a simple endpoint that takes a list of numbers and returns their sum:


@app.get("/sum/")
def sum_numbers(numbers: List[int]):
return {"result": sum(numbers)}


Step 4: Start the FastAPI Application

Finally, start the FastAPI application by running the following command:


uvicorn app:app --reload


Your FastAPI application should now be running on http://127.0.0.1:8000.

Conclusion

FastAPI is a powerful and easy-to-use tool for building machine learning APIs. With its support for type hints and automatic documentation generation, it makes the process of building and deploying APIs a breeze. Give FastAPI a try for your next machine learning project!