ai-engineering-from-scratch Docker & Self-Hosted Deployment

GitHub

Learn AI Engineering! Learn it. Build it. Ship it for others.

72,243 stars Python Python 2 files · ~33,564 tokens #agents#ai#ai-agents#ai-engineering#computer-vision#course#deep-learning#dsh
RAW Compose
1. Pull Image (DOCKERHUB) docker pull qdrant/qdrant
2. Docker Run (1-Click Launch) docker run -d --name ai-engineering-from-scratch -p 8888:8888 --restart always qdrant/qdrant:v1.12.5
3. Podman Run podman run -d --name ai-engineering-from-scratch -p 8888:8888 --restart always qdrant/qdrant:v1.12.5
4. Skopeo Inspect (Zero-Pull Manifest) skopeo inspect docker://docker.io/qdrant/qdrant:v1.12.5
5. ORAS Pull (OCI Artifact) oras pull qdrant/qdrant:v1.12.5
6. Compose Deployment docker compose up -d
phases/00-setup-and-tooling/07-docker-for-ai/code/docker-compose.yml
Download .yml 
services:
  ai-dev:
    build:
      context: .
      dockerfile: Dockerfile
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    volumes:
      - ../../../:/workspace
      - ~/models:/models
      - ~/datasets:/data
    ports:
      - "8888:8888"
    stdin_open: true
    tty: true
    command: jupyter notebook --ip=0.0.0.0 --port=8888 --no-browser --allow-root

  qdrant:
    image: qdrant/qdrant:v1.12.5
    ports:
      - "6333:6333"
      - "6334:6334"
    volumes:
      - qdrant_data:/qdrant/storage

volumes:
  qdrant_data: