bentoml

import bentoml from bentoml.io import JSON from pydantic import BaseModel import os # Define a Pydantic model for input data validation class InputData(BaseModel): name: str age: int # Define a simple prediction function to be served def greeter_predict(input_data: InputData) -> dict: return {"greeting": f"Hello, {input_data.name}! You are {input_data.age} years old."} # Save a dummy 'greeter' model (in real apps, this would be a trained ML model) # This model is essentially just the greeter_predict function itself for demonstration # In a real scenario, you'd save a scikit-learn model, a PyTorch model, etc. model_tag = bentoml.models.save( name="greeter_model", obj=greeter_predict, # Saving the function directly for this simple example signatures={ "predict": {"batchable": False} } ) # Create a BentoML Service # The 'models' argument tells BentoML which models this service depends on svc = bentoml.Service( name="greeter_service", models=[model_tag] # Reference the saved model by its tag ) # Define an API endpoint using the saved model # The `input` and `output` decorators specify the data types for the API @svc.api(input=JSON(pydantic_model=InputData), output=JSON()) async def greet(input_data: InputData) -> dict: # Load the model from the BentoML model store greeter_model = await bentoml.models.get(model_tag.name) # Call the model's signature (in this case, our saved function) result = greeter_model.predict(input_data) return result # To run this service locally: # 1. Save the code above as `service.py` # 2. Run in terminal: `bentoml serve service.py:svc --reload` # 3. Access at http://localhost:3000/greet with a POST request, e.g.: # curl -X POST -H "Content-Type: application/json" \ # -d '{"name": "Alice", "age": 30}' \ # http://localhost:3000/greet