VitePress

Appearance

FastAPI for Machine Learning ​

Deploy ML models with FastAPI.

Overview ​

FastAPI is an excellent choice for serving machine learning models due to its high performance and automatic documentation features.

Features ​

  • High performance
  • Automatic API documentation
  • Type hints for ML models
  • Async support for model inference
  • Easy integration with ML libraries

Getting Started ​

bash
pip install fastapi "uvicorn[standard]" scikit-learn numpy pandas

Basic Example ​

python
from fastapi import FastAPI
from pydantic import BaseModel
import joblib
import numpy as np

app = FastAPI(title="ML Model API")

# Load the trained model
model = joblib.load("model.pkl")

class PredictionRequest(BaseModel):
    features: list[float]

class PredictionResponse(BaseModel):
    prediction: float
    confidence: float

@app.post("/predict", response_model=PredictionResponse)
async def predict(request: PredictionRequest):
    # Convert features to numpy array
    features = np.array(request.features).reshape(1, -1)
    
    # Make prediction
    prediction = model.predict(features)[0]
    
    # Get prediction probability if available
    if hasattr(model, 'predict_proba'):
        confidence = model.predict_proba(features)[0].max()
    else:
        confidence = 1.0
    
    return PredictionResponse(
        prediction=float(prediction),
        confidence=float(confidence)
    )

@app.get("/")
async def root():
    return {"message": "ML Model API", "version": "1.0.0"}

PAPER-CODE Integration ​

PAPER-CODE provides:

  • FastAPI ML project templates
  • Model serving patterns
  • Docker configurations
  • Testing setups

Resources ​