cloud-run/text-encoder.yaml

apiVersion: serving.knative.dev/v1
kind: Service
metadata:
  name: movimento-text-encoder
  annotations:
    run.googleapis.com/launch-stage: GA
spec:
  template:
    metadata:
      annotations:
        autoscaling.knative.dev/minScale: "1"
        autoscaling.knative.dev/maxScale: "1"
        run.googleapis.com/execution-environment: gen2
        run.googleapis.com/gpu-type: GPU_TYPE_PLACEHOLDER
        run.googleapis.com/gpu-zonal-redundancy-disabled: "true"
    spec:
      containerConcurrency: 1
      timeoutSeconds: 900
      containers:
        - image: REGION-docker.pkg.dev/PROJECT_ID/kimodo/kimodo:latest
          command: ["python", "-m", "kimodo.scripts.run_text_encoder_server"]
          ports:
            - containerPort: 9550
          resources:
            limits:
              cpu: "8"
              memory: 24Gi
              nvidia.com/gpu: "GPU_COUNT_PLACEHOLDER"
          env:
            - name: GRADIO_SERVER_NAME
              value: "0.0.0.0"
            - name: TEXT_ENCODER
              value: "llm2vec"
            - name: LOCAL_CACHE
              value: "true"
            - name: HF_HOME
              value: /workspace/.cache/huggingface
            - name: PYTHONUNBUFFERED
              value: "1"
            - name: HF_TOKEN
              valueFrom:
                secretKeyRef:
                  name: HF_TOKEN_SECRET_NAME
                  key: latest
            - name: HUGGING_FACE_HUB_TOKEN
              valueFrom:
                secretKeyRef:
                  name: HF_TOKEN_SECRET_NAME
                  key: latest
            - name: HF_HUB_TOKEN
              valueFrom:
                secretKeyRef:
                  name: HF_TOKEN_SECRET_NAME
                  key: latest
            - name: HUGGINGFACEHUB_API_TOKEN
              valueFrom:
                secretKeyRef:
                  name: HF_TOKEN_SECRET_NAME
                  key: latest
  traffic:
    - percent: 100
      latestRevision: true