Hacktoberfest 2026: the issues maintainers tagged for October, open and beginner-friendly. Browse Hacktoberfest issues

ML-024 — Dockerize ML Serving API

Open
  • Is something wrong?
#48 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
3/5
Estimated time
1-2 days
Newbie friendliness
72/100
Issue type
Feature
Clarity
Mostly clear
Activity status
Active
Tech stack
docker, fastapi, python
Domain
api, devops, machine-learning

Research direction

Start by locating the existing FastAPI serving application and its /health endpoint, then review the dependency metadata and current test, MyPy, and Ruff commands. Add the Dockerfile and .dockerignore, build with docker build -t ml-platform ., and run it with the documented port mapping. Done means the image builds, the service starts, /health responds successfully, and existing checks pass.

Written by the indexing model from the issue text.

Description

ML-024 — Dockerize ML Serving API

Goal

Package the ML Platform serving API into a Docker image so that the inference service can run consistently across local and deployment environments.

Background

The ML Platform already exposes a FastAPI-based serving layer. The next step is to package the application and its runtime dependencies into a container.

Containerization should provide a reproducible runtime and establish the foundation for future CI/CD and cloud deployment.

Requirements

The container must:

  • Use Python 3.12.
  • Install project dependencies using uv.
  • Include the ML Platform application source.
  • Start the FastAPI serving application.
  • Listen on the configured serving host and port.
  • Expose the API port to the container runtime.
  • Support the existing /health endpoint.
  • Run without requiring manual configuration inside the container.

Tasks

  • Add a Dockerfile to the repository.
  • Select an appropriate Python 3.12 base image.
  • Install uv in the build environment.
  • Copy dependency metadata before application source to support Docker layer caching.
  • Install application runtime dependencies.
  • Copy the ML Platform source into the image.
  • Configure the container working directory.
  • Define the command used to start the FastAPI application.
  • Expose the serving port.
  • Add a .dockerignore.
  • Build the image locally.
  • Run the image locally.
  • Verify the /health endpoint from outside the container.

Acceptance Criteria

  • docker build completes successfully.
  • The resulting image starts successfully.
  • The FastAPI application is reachable from the host.
  • GET /health returns a successful response.
  • The container does not depend on developer-specific absolute paths.
  • Application dependencies are installed reproducibly.
  • Existing serving functionality remains unchanged.

Verification

The image should support a workflow similar to:

docker build -t ml-platform .
docker run --rm -p 8000:8000 ml-platform

The API should then be reachable at the mapped host port.

Definition of Done

  • Dockerfile committed.
  • .dockerignore committed.
  • Image builds successfully.
  • Container starts successfully.
  • Health endpoint verified.
  • Existing tests pass.
  • MyPy passes.
  • Ruff passes.
Dominant language
Python
Stars
1
Forks
0
Avg merge
7m
Merged PRs (30d)
3

Getting set up

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from Emil57/ml-platform

All issues in Emil57/ml-platform

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.