- 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
30 lines
513 B
YAML
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
|