Training project

Model serving with FastAPI and Docker

Related course: AI Model Deployment

Problem

Deploying models means packaging inference behind an API with a repeatable container and CI story.

Architecture (high level)

FastAPI (REST/gRPC patterns) → Docker image → CI/CD for ML pipelines → basic metrics/monitoring hooks (e.g. Prometheus) per AI Model Deployment tools.

Technologies

  • Docker
  • FastAPI
  • AWS
  • Prometheus

This is a Vector Skill Academy training project completed during the course. It is not confidential client work and does not represent a live production engagement.

Back to courseAll training projects