Create an async sentiment analysis endpoint
You're building a social media analytics platform that needs to analyze reviews for sentiment. To handle high traffic efficiently, you need to implement an async endpoint. The sentiment analysis model is already loaded and available as sentiment_model.
Deze oefening maakt deel uit van de cursus
Deploying AI into Production with FastAPI
Oefeninstructies
- Create an asynchronous POST endpoint
/analyzeusing FastAPI app. - Add the keyword to call the
sentiment_modelasynchronously without blocking other operations. - Run the
sentiment_modelin a separate thread with the review's text, ensuring it doesn't block the event loop.
Praktische interactieve oefening
Probeer deze oefening eens door deze voorbeeldcode in te vullen.
from fastapi import FastAPI
from pydantic import BaseModel
app = FastAPI()
class Review(BaseModel):
text: str
# Create async endpoint at /analyze route
@app.post("____")
# Write an asynchronous function to process review's text
____ def analyze_review(review: Review):
# Run the model in a separate thread to avoid any event loop blockage
result = ____ asyncio.____(sentiment_model, ____)
return {"sentiment": result[0]["label"]}