devspace.yaml

version: v2beta1

pipelines:
  # override the default `devspace deploy`
  deploy: |-
    build_images --all
    create_deployments ialacol
  # override the default `devspace dev`
  dev: |-
    start_dev ialacol
  # `devspace run-pipeline stop-dev` to stop all dev containers
  stop-dev: |-
    stop_dev --all

deployments:
  ialacol:
    helm:
      chart:
        name: ./charts/ialacol
      values:
        deployment:
          image: python:3.11-slim
          command: ["sleep", "999999"]
        tolerations:
          - key: "ai"
            operator: "Exists"
            effect: "NoSchedule"
        affinity:
          nodeAffinity:
            requiredDuringSchedulingIgnoredDuringExecution:
              nodeSelectorTerms:
              - matchExpressions:
                - key: nodegroup-ai
                  operator: In
                  values:
                  - "true"
dev:
  ialacol:
    labelSelector:
      app.kubernetes.io/name: ialacol
      app.kubernetes.io/instance: ialacol
    namespace: ${DEVSPACE_NAMESPACE}
    devImage: python:3.11-slim
    workingDir: /app
    command: ["uvicorn", "main:app", "--reload", "--host", "0.0.0.0", "--port", "8000"]
    ports:
    - port: "8000:8000"
    env:
    - name: DEFAULT_MODEL_HG_REPO_ID
      value: "TheBloke/Llama-2-13B-chat-GGML"
    - name: DEFAULT_MODEL_FILE
      value: "llama-2-13b-chat.ggmlv3.q4_0.bin"
    - name: LOGGING_LEVEL
      value: DEBUG
    sync:
      - path: ./:/app
        excludePaths:
        - requirements.txt
        printLogs: true
        uploadExcludeFile: ./.dockerignore
        downloadExcludeFile: ./.gitignore
      - path: ./requirements.txt:/app/requirements.txt
        startContainer: true
        file: true
        printLogs: true
        onUpload:
          exec:
          - command: |-
              pip install -r requirements.txt
            onChange: ["requirements.txt"]
    logs:
      enabled: true
      lastLines: 200