--- # Source: codetrans/charts/llm-uservice/templates/configmap.yaml # Copyright (C) 2024 Intel Corporation # SPDX-License-Identifier: Apache-2.0 apiVersion: v1 kind: ConfigMap metadata: name: codetrans-llm-uservice-config labels: helm.sh/chart: llm-uservice-1.0.0 app.kubernetes.io/name: llm-uservice app.kubernetes.io/instance: codetrans app.kubernetes.io/version: "v1.0" app.kubernetes.io/managed-by: Helm data: TGI_LLM_ENDPOINT: "http://codetrans-tgi" HUGGINGFACEHUB_API_TOKEN: "insert-your-huggingface-token-here" HF_HOME: "/tmp/.cache/huggingface" http_proxy: "" https_proxy: "" no_proxy: "" LOGFLAG: "" --- # Source: codetrans/charts/tgi/templates/configmap.yaml # Copyright (C) 2024 Intel Corporation # SPDX-License-Identifier: Apache-2.0 apiVersion: v1 kind: ConfigMap metadata: name: codetrans-tgi-config labels: helm.sh/chart: tgi-1.0.0 app.kubernetes.io/name: tgi app.kubernetes.io/instance: codetrans app.kubernetes.io/version: "2.1.0" app.kubernetes.io/managed-by: Helm data: MODEL_ID: "HuggingFaceH4/mistral-7b-grok" PORT: "2080" HF_TOKEN: "insert-your-huggingface-token-here" http_proxy: "" https_proxy: "" no_proxy: "" HABANA_LOGS: "/tmp/habana_logs" NUMBA_CACHE_DIR: "/tmp" HF_HOME: "/tmp/.cache/huggingface" MAX_INPUT_LENGTH: "1024" MAX_TOTAL_TOKENS: "2048" --- # Source: codetrans/charts/llm-uservice/templates/service.yaml # Copyright (C) 2024 Intel Corporation # SPDX-License-Identifier: Apache-2.0 apiVersion: v1 kind: Service metadata: name: codetrans-llm-uservice labels: helm.sh/chart: llm-uservice-1.0.0 app.kubernetes.io/name: llm-uservice app.kubernetes.io/instance: codetrans app.kubernetes.io/version: "v1.0" app.kubernetes.io/managed-by: Helm spec: type: ClusterIP ports: - port: 9000 targetPort: 9000 protocol: TCP name: llm-uservice selector: app.kubernetes.io/name: llm-uservice app.kubernetes.io/instance: codetrans --- # Source: codetrans/charts/tgi/templates/service.yaml # Copyright (C) 2024 Intel Corporation # SPDX-License-Identifier: Apache-2.0 apiVersion: v1 kind: Service metadata: name: codetrans-tgi labels: helm.sh/chart: tgi-1.0.0 app.kubernetes.io/name: tgi app.kubernetes.io/instance: codetrans app.kubernetes.io/version: "2.1.0" app.kubernetes.io/managed-by: Helm spec: type: ClusterIP ports: - port: 80 targetPort: 2080 protocol: TCP name: tgi selector: app.kubernetes.io/name: tgi app.kubernetes.io/instance: codetrans --- # Source: codetrans/templates/service.yaml # Copyright (C) 2024 Intel Corporation # SPDX-License-Identifier: Apache-2.0 apiVersion: v1 kind: Service metadata: name: codetrans labels: helm.sh/chart: codetrans-1.0.0 app.kubernetes.io/name: codetrans app.kubernetes.io/instance: codetrans app.kubernetes.io/version: "v1.0" app.kubernetes.io/managed-by: Helm spec: type: ClusterIP ports: - port: 7777 targetPort: 7777 protocol: TCP name: codetrans selector: app.kubernetes.io/name: codetrans app.kubernetes.io/instance: codetrans --- # Source: codetrans/charts/llm-uservice/templates/deployment.yaml # Copyright (C) 2024 Intel Corporation # SPDX-License-Identifier: Apache-2.0 apiVersion: apps/v1 kind: Deployment metadata: name: codetrans-llm-uservice labels: helm.sh/chart: llm-uservice-1.0.0 app.kubernetes.io/name: llm-uservice app.kubernetes.io/instance: codetrans app.kubernetes.io/version: "v1.0" app.kubernetes.io/managed-by: Helm spec: replicas: 1 selector: matchLabels: app.kubernetes.io/name: llm-uservice app.kubernetes.io/instance: codetrans template: metadata: labels: app.kubernetes.io/name: llm-uservice app.kubernetes.io/instance: codetrans spec: securityContext: {} containers: - name: codetrans envFrom: - configMapRef: name: codetrans-llm-uservice-config securityContext: allowPrivilegeEscalation: false capabilities: drop: - ALL readOnlyRootFilesystem: false runAsNonRoot: true runAsUser: 1000 seccompProfile: type: RuntimeDefault image: "opea/llm-tgi:latest" imagePullPolicy: IfNotPresent ports: - name: llm-uservice containerPort: 9000 protocol: TCP volumeMounts: - mountPath: /tmp name: tmp livenessProbe: failureThreshold: 24 httpGet: path: v1/health_check port: llm-uservice initialDelaySeconds: 5 periodSeconds: 5 readinessProbe: httpGet: path: v1/health_check port: llm-uservice initialDelaySeconds: 5 periodSeconds: 5 startupProbe: failureThreshold: 120 httpGet: path: v1/health_check port: llm-uservice initialDelaySeconds: 5 periodSeconds: 5 resources: {} volumes: - name: tmp emptyDir: {} --- # Source: codetrans/charts/tgi/templates/deployment.yaml # Copyright (C) 2024 Intel Corporation # SPDX-License-Identifier: Apache-2.0 apiVersion: apps/v1 kind: Deployment metadata: name: codetrans-tgi labels: helm.sh/chart: tgi-1.0.0 app.kubernetes.io/name: tgi app.kubernetes.io/instance: codetrans app.kubernetes.io/version: "2.1.0" app.kubernetes.io/managed-by: Helm spec: # use explicit replica counts only of HorizontalPodAutoscaler is disabled replicas: 1 selector: matchLabels: app.kubernetes.io/name: tgi app.kubernetes.io/instance: codetrans template: metadata: labels: app.kubernetes.io/name: tgi app.kubernetes.io/instance: codetrans spec: securityContext: {} containers: - name: tgi envFrom: - configMapRef: name: codetrans-tgi-config securityContext: allowPrivilegeEscalation: false capabilities: drop: - ALL readOnlyRootFilesystem: true runAsNonRoot: true runAsUser: 1000 seccompProfile: type: RuntimeDefault image: "ghcr.io/huggingface/tgi-gaudi:2.0.1" imagePullPolicy: IfNotPresent volumeMounts: - mountPath: /data name: model-volume - mountPath: /tmp name: tmp ports: - name: http containerPort: 2080 protocol: TCP livenessProbe: failureThreshold: 24 initialDelaySeconds: 5 periodSeconds: 5 tcpSocket: port: http readinessProbe: initialDelaySeconds: 5 periodSeconds: 5 tcpSocket: port: http startupProbe: failureThreshold: 120 initialDelaySeconds: 5 periodSeconds: 5 tcpSocket: port: http resources: limits: habana.ai/gaudi: 1 volumes: - name: model-volume emptyDir: {} - name: tmp emptyDir: {} --- # Source: codetrans/templates/deployment.yaml # Copyright (C) 2024 Intel Corporation # SPDX-License-Identifier: Apache-2.0 apiVersion: apps/v1 kind: Deployment metadata: name: codetrans labels: helm.sh/chart: codetrans-1.0.0 app.kubernetes.io/name: codetrans app.kubernetes.io/instance: codetrans app.kubernetes.io/version: "v1.0" app.kubernetes.io/managed-by: Helm spec: replicas: 1 selector: matchLabels: app.kubernetes.io/name: codetrans app.kubernetes.io/instance: codetrans template: metadata: labels: app.kubernetes.io/name: codetrans app.kubernetes.io/instance: codetrans spec: securityContext: null containers: - name: codetrans env: - name: LLM_SERVICE_HOST_IP value: codetrans-llm-uservice #- name: MEGA_SERVICE_PORT # value: 7777 securityContext: allowPrivilegeEscalation: false capabilities: drop: - ALL readOnlyRootFilesystem: true runAsNonRoot: true runAsUser: 1000 seccompProfile: type: RuntimeDefault image: "opea/codetrans:latest" imagePullPolicy: IfNotPresent volumeMounts: - mountPath: /tmp name: tmp ports: - name: codetrans containerPort: 7777 protocol: TCP resources: null volumes: - name: tmp emptyDir: {} --- # Copyright (C) 2024 Intel Corporation # SPDX-License-Identifier: Apache-2.0 apiVersion: v1 kind: ConfigMap metadata: name: codetrans-nginx-config data: default.conf: | server { listen 80; listen [::]:80; location / { root /usr/share/nginx/html; index index.html index.htm; } location /v1/codetrans { proxy_pass http://codetrans:7777; proxy_set_header Host $host; proxy_set_header X-Real-IP $remote_addr; proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for; proxy_set_header X-Forwarded-Proto $scheme; } } --- # Copyright (C) 2024 Intel Corporation # SPDX-License-Identifier: Apache-2.0 apiVersion: apps/v1 kind: Deployment metadata: name: codetrans-nginx-deployment spec: replicas: 1 selector: matchLabels: app: nginx template: metadata: labels: app: nginx spec: containers: - name: nginx image: nginx:latest ports: - containerPort: 80 volumeMounts: - name: nginx-config-volume mountPath: /etc/nginx/conf.d/default.conf subPath: default.conf volumes: - name: nginx-config-volume configMap: name: codetrans-nginx-config --- kind: Service apiVersion: v1 metadata: name: nginx-svc spec: selector: app: nginx ports: - protocol: TCP port: 80 targetPort: 80 nodePort: 30789 type: NodePort