Files
GenAIExamples/DocSum/kubernetes/manifests/xeon/docsum.yaml
NeuralChatBot 6a705ad3d4 Update third party images tag
Signed-off-by: NeuralChatBot <grp_neural_chat_bot@intel.com>
2024-08-29 02:45:32 +00:00

339 lines
8.6 KiB
YAML

---
# Source: docsum/charts/llm-uservice/templates/configmap.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: ConfigMap
metadata:
name: docsum-llm-uservice-config
labels:
helm.sh/chart: llm-uservice-0.8.0
app.kubernetes.io/name: llm-uservice
app.kubernetes.io/instance: docsum
app.kubernetes.io/version: "v0.8"
app.kubernetes.io/managed-by: Helm
data:
TGI_LLM_ENDPOINT: "http://docsum-tgi"
HUGGINGFACEHUB_API_TOKEN: "insert-your-huggingface-token-here"
HF_HOME: "/tmp/.cache/huggingface"
http_proxy: ""
https_proxy: ""
no_proxy: ""
LANGCHAIN_TRACING_V2: "false"
LANGCHAIN_API_KEY: insert-your-langchain-key-here
LANGCHAIN_PROJECT: "opea-llm-uservice"
---
# Source: docsum/charts/tgi/templates/configmap.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: ConfigMap
metadata:
name: docsum-tgi-config
labels:
helm.sh/chart: tgi-0.8.0
app.kubernetes.io/name: tgi
app.kubernetes.io/instance: docsum
app.kubernetes.io/version: "2.1.0"
app.kubernetes.io/managed-by: Helm
data:
MODEL_ID: "Intel/neural-chat-7b-v3-3"
PORT: "2080"
HF_TOKEN: "insert-your-huggingface-token-here"
http_proxy: ""
https_proxy: ""
no_proxy: ""
HABANA_LOGS: "/tmp/habana_logs"
NUMBA_CACHE_DIR: "/tmp"
TRANSFORMERS_CACHE: "/tmp/transformers_cache"
HF_HOME: "/tmp/.cache/huggingface"
CUDA_GRAPHS: "0"
---
# Source: docsum/charts/llm-uservice/templates/service.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: Service
metadata:
name: docsum-llm-uservice
labels:
helm.sh/chart: llm-uservice-0.8.0
app.kubernetes.io/name: llm-uservice
app.kubernetes.io/instance: docsum
app.kubernetes.io/version: "v0.8"
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: docsum
---
# Source: docsum/charts/tgi/templates/service.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: Service
metadata:
name: docsum-tgi
labels:
helm.sh/chart: tgi-0.8.0
app.kubernetes.io/name: tgi
app.kubernetes.io/instance: docsum
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: docsum
---
# Source: docsum/templates/service.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: Service
metadata:
name: docsum
labels:
helm.sh/chart: docsum-0.8.0
app.kubernetes.io/name: docsum
app.kubernetes.io/instance: docsum
app.kubernetes.io/version: "v0.8"
app.kubernetes.io/managed-by: Helm
spec:
type: ClusterIP
ports:
- port: 8888
targetPort: 8888
protocol: TCP
name: docsum
selector:
app.kubernetes.io/name: docsum
app.kubernetes.io/instance: docsum
---
# Source: docsum/charts/llm-uservice/templates/deployment.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: apps/v1
kind: Deployment
metadata:
name: docsum-llm-uservice
labels:
helm.sh/chart: llm-uservice-0.8.0
app.kubernetes.io/name: llm-uservice
app.kubernetes.io/instance: docsum
app.kubernetes.io/version: "v0.8"
app.kubernetes.io/managed-by: Helm
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: llm-uservice
app.kubernetes.io/instance: docsum
template:
metadata:
labels:
app.kubernetes.io/name: llm-uservice
app.kubernetes.io/instance: docsum
spec:
securityContext:
{}
containers:
- name: docsum
envFrom:
- configMapRef:
name: docsum-llm-uservice-config
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop:
- ALL
readOnlyRootFilesystem: false
runAsNonRoot: true
runAsUser: 1000
seccompProfile:
type: RuntimeDefault
image: "opea/llm-docsum-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: docsum/charts/tgi/templates/deployment.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: apps/v1
kind: Deployment
metadata:
name: docsum-tgi
labels:
helm.sh/chart: tgi-0.8.0
app.kubernetes.io/name: tgi
app.kubernetes.io/instance: docsum
app.kubernetes.io/version: "2.1.0"
app.kubernetes.io/managed-by: Helm
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: tgi
app.kubernetes.io/instance: docsum
template:
metadata:
labels:
app.kubernetes.io/name: tgi
app.kubernetes.io/instance: docsum
spec:
securityContext:
{}
containers:
- name: tgi
envFrom:
- configMapRef:
name: docsum-tgi-config
securityContext:
{}
image: "ghcr.io/huggingface/text-generation-inference:sha-8f99f16-intel-cpu"
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:
{}
volumes:
- name: model-volume
hostPath:
path: /mnt/opea-models
type: Directory
- name: tmp
emptyDir: {}
---
# Source: docsum/templates/deployment.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: apps/v1
kind: Deployment
metadata:
name: docsum
labels:
helm.sh/chart: docsum-0.8.0
app.kubernetes.io/name: docsum
app.kubernetes.io/instance: docsum
app.kubernetes.io/version: "v0.8"
app.kubernetes.io/managed-by: Helm
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: docsum
app.kubernetes.io/instance: docsum
template:
metadata:
labels:
app.kubernetes.io/name: docsum
app.kubernetes.io/instance: docsum
spec:
securityContext:
null
containers:
- name: docsum
env:
- name: LLM_SERVICE_HOST_IP
value: docsum-llm-uservice
#- name: MEGA_SERVICE_PORT
# value: 8888
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop:
- ALL
readOnlyRootFilesystem: true
runAsNonRoot: true
runAsUser: 1000
seccompProfile:
type: RuntimeDefault
image: "opea/docsum:latest"
imagePullPolicy: IfNotPresent
volumeMounts:
- mountPath: /tmp
name: tmp
ports:
- name: docsum
containerPort: 8888
protocol: TCP
resources:
null
volumes:
- name: tmp
emptyDir: {}