43 lines
1.9 KiB
YAML
43 lines
1.9 KiB
YAML
# ENKLY_WORKSPACE_GRPC_ADDR here means something different from the
|
|
# same-named var on the workspace Deployment: there it's "what address
|
|
# do I listen on", here it's "what address do I dial" (agent is a
|
|
# gRPC client of workspace/knowledge/billing/conversation). That's how
|
|
# docker-compose.yml defines it too — kept identical on purpose.
|
|
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata: {name: agent, namespace: enkly, labels: {app: agent}}
|
|
spec:
|
|
replicas: 1
|
|
selector: {matchLabels: {app: agent}}
|
|
template:
|
|
metadata: {labels: {app: agent}}
|
|
spec:
|
|
imagePullSecrets: [{name: enkly-registry}]
|
|
containers:
|
|
- name: agent
|
|
image: registry.enkly.org/enkly/agent:latest
|
|
ports: [{name: grpc, containerPort: 9006}]
|
|
envFrom: [{configMapRef: {name: enkly-config}}]
|
|
env:
|
|
- {name: ENKLY_WORKSPACE_GRPC_ADDR, value: "workspace:9004"}
|
|
- {name: ENKLY_KNOWLEDGE_GRPC_ADDR, value: "knowledge:9005"}
|
|
- {name: ENKLY_BILLING_GRPC_ADDR, value: "billing:9002"}
|
|
- {name: ENKLY_CONVERSATION_GRPC_ADDR, value: "conversation:9003"}
|
|
# Bearer token agent authenticates to vllm-chat/vllm-embed
|
|
# with (see services/agent/cmd/server/main.go) — without
|
|
# this, chat/tool-calling calls 401 against vLLM's --api-key.
|
|
- name: ENKLY_VLLM_API_KEY
|
|
valueFrom: {secretKeyRef: {name: enkly-secrets, key: ENKLY_VLLM_API_KEY}}
|
|
resources:
|
|
requests: {cpu: 100m, memory: 128Mi}
|
|
limits: {cpu: 1, memory: 512Mi}
|
|
readinessProbe: {grpc: {port: 9006}, initialDelaySeconds: 5, periodSeconds: 10, failureThreshold: 10}
|
|
livenessProbe: {grpc: {port: 9006}, initialDelaySeconds: 15, periodSeconds: 20, failureThreshold: 6}
|
|
---
|
|
apiVersion: v1
|
|
kind: Service
|
|
metadata: {name: agent, namespace: enkly, labels: {app: agent}}
|
|
spec:
|
|
selector: {app: agent}
|
|
ports: [{name: grpc, port: 9006, targetPort: grpc}]
|