fix: vLLM deployment — Recreate strategy, correct service port, single model name

- Strategy: Recreate (GPU can only be used by one pod at a time)
- nuextract-external targetPort: 8080 (nginx proxy port)
- served-model-name: numind/NuExtract3
- DB ai_agents updated to model=numind/NuExtract3 provider=vllm

infra/kube-vllm/deployment.yaml

@@ -7,6 +7,8 @@ metadata:
     app: vllm
 spec:
   replicas: 1
+  strategy:
+    type: Recreate
   selector:
     matchLabels:
       app: vllm