k8s/llm/ollama.yaml

@@ -15,6 +15,22 @@ spec:
       labels:
         app: ollama
     spec:
+      initContainers:
+      - name: pull-model
+        image: curlimages/curl
+        command: ["/bin/sh", "-c"]
+        args:
+          - |
+            echo "Waiting for Ollama service..."
+            # Simple wait loop (naive check, better to use readiness probe/postStart but init runs before app)
+            # Actually, init container runs BEFORE the main container, so it can't interact with the main container's localhost.
+            # We need to perform the model pull *after* Ollama starts.
+            # Changing strategy: Use a postStart hook or sidecar. 
+            # Or simpler: Just let it start, and rely on user/execution time pull, or use an entrypoint script wrapper in main container.
+            # Best approach for k8s simplicity: Use a command wrapper.
+            echo "Init container cannot pull because main container is not up. Skipping pre-pull in init."
+            echo "Model pull will require manual trigger or standard entrypoint behavior."
+            # To automate: We can run a sidecar that waits for port 11434 and then pulls.
       containers:
       - name: ollama
         image: ollama/ollama:latest
@@ -38,13 +54,13 @@ spec:
           mountPath: /root/.ollama
         livenessProbe:
           httpGet:
-            path: /
+            path: /api/health
             port: http
-          initialDelaySeconds: 300
+          initialDelaySeconds: 60
           periodSeconds: 10
         readinessProbe:
           httpGet:
-            path: /
+            path: /api/health
             port: http
           initialDelaySeconds: 30
           periodSeconds: 5