mlops-challenge/docker-compose.yml at main · jlsneto/mlops-challenge · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
services:
  prepare_dataset:
    profiles: ["prepare"]
    build:
      context: .
      dockerfile: Dockerfile
    image: mlops-challenge-ml:local
    platform: linux/amd64
    working_dir: /workspace
    volumes:
      - ./:/workspace
      - tfds_cache:/tfds
    environment:
      TFDS_DATA_DIR: /tfds
      WRAPT_DISABLE_EXTENSIONS: "1"
      PYTHONUNBUFFERED: "1"
    command: >
      bash -lc "python -m ml.prepare_dataset
      --output_dir ${OUTPUT_DIR:-data/processed}
      --dataset_name ${DATASET_NAME:-para_crawl/enpt}
      --max_tokens ${MAX_TOKENS:-64}
      --train_records ${TRAIN_RECORDS:-20000}
      --val_records ${VAL_RECORDS:-2000}
      --seed ${SEED:-42}"

  train:
    profiles: ["train"]
    build:
      context: .
      dockerfile: Dockerfile
    image: mlops-challenge-ml:local
    platform: linux/amd64
    working_dir: /workspace
    volumes:
      - ./:/workspace
      - tfds_cache:/tfds
    environment:
      TFDS_DATA_DIR: /tfds
      WRAPT_DISABLE_EXTENSIONS: "1"
      PYTHONUNBUFFERED: "1"
    command: >
      bash -lc "python -m ml.train
      --data_dir ${OUTPUT_DIR:-data/processed}
      --artifacts_dir ${ARTIFACTS_DIR:-artifacts}
      --epochs ${EPOCHS:-10}
      --batch_size ${BATCH_SIZE:-32}
      --threshold ${THRESHOLD:-0.30}
      --max_tokens ${MAX_TOKENS:-64}
      --git_sha ${GIT_SHA:-unknown}"

  api:
    profiles: ["api"]
    build:
      context: .
      dockerfile: Dockerfile
    image: mlops-challenge-ml:local
    platform: linux/amd64
    working_dir: /workspace
    volumes:
      - ./:/workspace
    environment:
      WRAPT_DISABLE_EXTENSIONS: "1"
      PYTHONUNBUFFERED: "1"
      ARTIFACTS_DIR: /workspace/${ARTIFACTS_DIR:-artifacts}
      DEFAULT_RUN_ID: ${DEFAULT_RUN_ID:-}
    ports:
      - "${API_PORT:-8000}:8000"
    command: >
      bash -lc "uvicorn inference_api.main:app --host 0.0.0.0 --port 8000"

  tests:
    profiles: ["tests"]
    build:
      context: .
      dockerfile: Dockerfile
    image: mlops-challenge-ml:local
    platform: linux/amd64
    working_dir: /workspace
    volumes:
      - ./:/workspace
    environment:
      WRAPT_DISABLE_EXTENSIONS: "1"
      PYTHONUNBUFFERED: "1"
    command: >
      bash -lc "pytest -q"

volumes:
  tfds_cache: