# Embeddings for the knowledge layer.
#
# Production retrieval was keyword-only: no EMBED_PROVIDER, so every chunk had
# a null embedding and a question only matched documents sharing its words.
# Ollama is what internal/knowledge/embed.go calls "the default worth reaching
# for" — real semantics, no credential, no per-token cost, and no tenant text
# leaving the cluster.
#
# Bounded on purpose. The API pods share this node, so an unbounded model
# server is a way to evict them; the limit means the kubelet kills this and
# nothing else. The request is what keeps it off the 1.2Gi node, where it
# would not fit.
apiVersion: v1
kind: PersistentVolumeClaim
metadata: { name: ollama-models, namespace: krow }
spec:
  accessModes: [ReadWriteOnce]
  resources: { requests: { storage: 4Gi } }
---
apiVersion: apps/v1
kind: Deployment
metadata: { name: ollama, namespace: krow }
spec:
  replicas: 1
  selector: { matchLabels: { app: ollama } }
  strategy: { type: Recreate }        # one volume, one writer
  template:
    metadata: { labels: { app: ollama } }
    spec:
      containers:
        - name: ollama
          image: ollama/ollama:0.33.1
          ports: [{ containerPort: 11434, name: http }]
          env:
            - { name: OLLAMA_HOST, value: "0.0.0.0:11434" }
            # One model, kept resident: reloading it per request would make
            # every retrieval pay the load cost.
            - { name: OLLAMA_KEEP_ALIVE, value: "24h" }
            - { name: OLLAMA_MAX_LOADED_MODELS, value: "1" }
          resources:
            requests: { memory: "1Gi", cpu: "250m" }
            limits:   { memory: "3Gi", cpu: "2" }
          volumeMounts: [{ name: models, mountPath: /root/.ollama }]
          readinessProbe:
            httpGet: { path: /api/version, port: http }
            initialDelaySeconds: 5
            periodSeconds: 10
          livenessProbe:
            httpGet: { path: /api/version, port: http }
            initialDelaySeconds: 30
            periodSeconds: 30
      volumes:
        - name: models
          persistentVolumeClaim: { claimName: ollama-models }
---
apiVersion: v1
kind: Service
metadata: { name: ollama, namespace: krow }
spec:
  selector: { app: ollama }
  ports: [{ port: 11434, targetPort: http, name: http }]