Files
stonks-oracle/infra/kube-vllm/service.yaml
T
Celes Renata af7b654fb7 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
2026-07-04 05:34:04 +00:00

30 lines
513 B
YAML

apiVersion: v1
kind: Service
metadata:
name: nuextract
namespace: vllm-service
spec:
ports:
- name: http
port: 8000
targetPort: 8000
selector:
app: vllm
type: ClusterIP
---
# External access via NodePort (like ollama's port 2701 pattern)
apiVersion: v1
kind: Service
metadata:
name: nuextract-external
namespace: vllm-service
spec:
ports:
- nodePort: 31508
name: vllm-api
port: 2701
targetPort: 8080
selector:
app: vllm-metrics
type: LoadBalancer