apiVersion: apps/v1
kind: Deployment
metadata:
  name: ollama
  namespace: nxtgauge-ai
  labels:
    app: ollama
spec:
  replicas: 1
  selector:
    matchLabels:
      app: ollama
  template:
    metadata:
      labels:
        app: ollama
    spec:
      containers:
        - name: ollama
          image: ollama/ollama:latest
          ports:
            - containerPort: 11434
              name: http
          env:
            - name: OLLAMA_HOST
              value: "0.0.0.0:11434"
            # Keep a loaded model resident for 30 min of inactivity instead
            # of Ollama's 5-minute default — job-description/resume/cover-
            # letter traffic is bursty, and reloading a 2.5-5GB model from
            # disk on every request would add multi-second latency to each
            # first call after a gap.
            - name: OLLAMA_KEEP_ALIVE
              value: "30m"
          volumeMounts:
            - name: ollama-models
              mountPath: /root/.ollama
          resources:
            requests:
              cpu: 1000m
              memory: 3Gi
            limits:
              # qwen3:4b (~2.5GB on disk) and qwen3:8b (~5.2GB) are already
              # pulled onto the PVC, but the previous 1500Mi limit could
              # only ever load gemma3:270m — which is why every LiteLLM
              # model alias was mapped to gemma3:270m regardless of name
              # (see apps/litellm/base/configmap.yaml). Sized to comfortably
              # hold qwen3:8b plus KV cache/runtime overhead, with headroom;
              # node has 16GB total and was at ~26% memory use.
              cpu: 4000m
              memory: 8Gi
      volumes:
        - name: ollama-models
          persistentVolumeClaim:
            claimName: ollama-models