ml-deployment

name	ml-deployment
description	Deploy ML models to production - APIs, containerization, monitoring, and MLOps
version	1.4.0
sasmp_version	1.4.0
bonded_agent	07-model-deployment
bond_type	PRIMARY_BOND
parameters	{"required":[{"name":"model","type":"object","validation":"Trained model with predict method"}],"optional":[{"name":"port","type":"integer","default":8000,"validation":"1024 <= port <= 65535"},{"name":"workers","type":"integer","default":4}]}
retry_logic	{"strategy":"exponential_backoff","max_attempts":3,"base_delay_ms":1000}
logging	{"level":"info","metrics":["latency_ms","requests_per_second","error_rate"]}

ML Deployment Skill

Take models from development to production.

Quick Start

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

app = FastAPI(title="ML Model API")
model = joblib.load('model.pkl')

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

class PredictResponse(BaseModel):
    prediction: float

@app.post("/predict", response_model=PredictResponse)
async def predict(request: PredictRequest):
    X = np.array([request.features])
    prediction = model.predict(X)[0]
    return PredictResponse(prediction=float(prediction))

@app.get("/health")
async def health():
    return {"status": "healthy"}

Key Topics

1. Model Export

import torch
import torch.onnx

# Export PyTorch to ONNX
def export_to_onnx(model, sample_input, path='model.onnx'):
    model.()
    torch.onnx.export(
        model,
        sample_input,
        path,
        export_params=,
        opset_version=,
        input_names=[],
        output_names=[],
        dynamic_axes={: {: }, : {: }}
    )


 onnxruntime  ort

session = ort.InferenceSession()
input_name = session.get_inputs()[].name
output = session.run(, {input_name: input_data})[]