AI & ML Quick Path

Part 7: Production

Run AI and ML reliably for real users: serving models as APIs, MLOps, monitoring, cost and scale, and reference architectures that combine .NET and Python.

5 lessonsAbout 8 hours of study (estimate)0 of 5 completed in this browser

Key terms in this part (22)

From prototype to production

  1. Serving a model as an API

    Turn a saved model into a web API that loads the model once, validates input, returns a versioned answer and reports its health, in Python and in ASP.NET Core.

    Intermediate1.5 hNeeds: How an AI or ML project runs from idea to production, Classification: picking a category

  2. "MLOps: versioning, pipelines and safe releases"

    Make model training repeatable and releases safe by versioning data, code and models, recording metrics in a registry, and promoting a new model only when it passes a gate.

    Advanced1.5 hNeeds: Serving a model as an API, Measuring models honestly

  3. Monitoring models and AI apps in production

    Watch a live model or LLM app for data drift, falling quality, latency and cost, and decide when to alert, retrain or roll back.

    Advanced75 minNeeds: "MLOps: versioning, pipelines and safe releases", Evaluating AI applications

  4. Speed, cost and scaling

    Make models and LLM apps faster and cheaper with batching, caching, smaller models, quantisation and ONNX export, and know when to add more machines or GPUs.

    Advanced75 minNeeds: Serving a model as an API, Running language models on your own machine

  5. Production architecture for AI systems

    Design a complete AI system (a .NET application calling a Python model service and an LLM), with containers, secrets, fallbacks, security and a clear checklist, so you can plan any industry case.

    Expert2 hNeeds: Serving a model as an API, Monitoring models and AI apps in production, RAG: answering from your own documents, Security for AI applications

The reference architecture: .NET application with a Python model service

Many companies keep their business system in .NET and run ML models in Python. The two talk through a small, versioned contract. Details and code are in Production architecture for AI systems.

  1. ClientWeb or mobile app
  2. ASP.NET Core APISign-in, permissions, business rules, audit
  3. Python service /v1Model inference only; validated input and output
  4. Modelscikit-learn, PyTorch, ONNX or an LLM