Switch to OpenAI provider with gpt-4o-mini model

manifests/dot-ai-stack/values.yaml

@@ -4,13 +4,10 @@ dot-ai:
 
   ai:
     provider: openai
-    model: "llama3.1:8b"  # Using local Ollama model (8b version available)
+    model: "gpt-4o-mini"  # OpenAI chat model
+    # customEndpoint disabled - using OpenAI directly
     customEndpoint:
-      enabled: true
+      enabled: false
-      baseURL: "http://ollama.ai-stack.svc.cluster.local:11434/v1"  # Point to Ollama service
-      embeddingsBaseURL: "http://ollama.ai-stack.svc.cluster.local:11434/v1"
-      embeddingsModel: "nomic-embed-text"  # Ollama embedding model
-      embeddingsDimensions: "768"  # Nomic embeddings dimension
 
   secrets:
     auth: