Files
GenAIExamples/ChatQnA/kubernetes/intel/cpu/xeon/manifest/chatqna-remote-inference.yaml
sgurunat 56f770cb28 ChatQnA with Remote Inference Endpoints (Kubernetes) (#1149)
Signed-off-by: sgurunat <gurunath.s@intel.com>
Co-authored-by: chen, suyue <suyue.chen@intel.com>
2024-11-18 20:06:17 +08:00

1324 lines
35 KiB
YAML

---
# Source: chatqna/charts/data-prep/templates/configmap.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: ConfigMap
metadata:
name: chatqna-data-prep-config
labels:
helm.sh/chart: data-prep-1.0.0
app.kubernetes.io/name: data-prep
app.kubernetes.io/instance: chatqna
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
data:
TEI_ENDPOINT: "http://chatqna-tei"
EMBED_MODEL: ""
REDIS_URL: "redis://chatqna-redis-vector-db:6379"
INDEX_NAME: "rag-redis"
KEY_INDEX_NAME: "file-keys"
SEARCH_BATCH_SIZE: "10"
HUGGINGFACEHUB_API_TOKEN: "insert-your-huggingface-token-here"
HF_HOME: "/tmp/.cache/huggingface"
http_proxy: ""
https_proxy: ""
no_proxy: ""
LOGFLAG: ""
---
# Source: chatqna/charts/embedding-usvc/templates/configmap.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: ConfigMap
metadata:
name: chatqna-embedding-usvc-config
labels:
helm.sh/chart: embedding-usvc-1.0.0
app.kubernetes.io/name: embedding-usvc
app.kubernetes.io/instance: chatqna
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
data:
TEI_EMBEDDING_ENDPOINT: "http://chatqna-tei"
http_proxy: ""
https_proxy: ""
no_proxy: ""
LOGFLAG: ""
---
# Source: chatqna/charts/llm-uservice/templates/configmap.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: ConfigMap
metadata:
name: chatqna-llm-uservice-config
labels:
helm.sh/chart: llm-uservice-1.0.0
app.kubernetes.io/name: llm-uservice
app.kubernetes.io/instance: chatqna
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
data:
HUGGINGFACEHUB_API_TOKEN: "insert-your-huggingface-token-here"
HF_HOME: "/tmp/.cache/huggingface"
http_proxy: ""
https_proxy: ""
no_proxy: ""
LOGFLAG: ""
vLLM_ENDPOINT: "insert-your-remote-inference-endpoint"
LLM_MODEL: "meta-llama/Meta-Llama-3.1-8B-Instruct"
LLM_MODEL_ID: "meta-llama/Meta-Llama-3.1-8B-Instruct"
MODEL_ID: "meta-llama/Meta-Llama-3.1-8B-Instruct"
CLIENTID: ""
CLIENT_SECRET: ""
TOKEN_URL: ""
---
# Source: chatqna/charts/reranking-usvc/templates/configmap.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: ConfigMap
metadata:
name: chatqna-reranking-usvc-config
labels:
helm.sh/chart: reranking-usvc-1.0.0
app.kubernetes.io/name: reranking-usvc
app.kubernetes.io/instance: chatqna
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
data:
TEI_RERANKING_ENDPOINT: "http://chatqna-teirerank"
http_proxy: ""
https_proxy: ""
no_proxy: ""
LOGFLAG: ""
---
# Source: chatqna/charts/retriever-usvc/templates/configmap.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: ConfigMap
metadata:
name: chatqna-retriever-usvc-config
labels:
helm.sh/chart: retriever-usvc-1.0.0
app.kubernetes.io/name: retriever-usvc
app.kubernetes.io/instance: chatqna
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
data:
TEI_EMBEDDING_ENDPOINT: "http://chatqna-tei"
EMBED_MODEL: ""
REDIS_URL: "redis://chatqna-redis-vector-db:6379"
INDEX_NAME: "rag-redis"
EASYOCR_MODULE_PATH: "/tmp/.EasyOCR"
http_proxy: ""
https_proxy: ""
no_proxy: ""
HF_HOME: "/tmp/.cache/huggingface"
HUGGINGFACEHUB_API_TOKEN: "insert-your-huggingface-token-here"
LOGFLAG: ""
---
# Source: chatqna/charts/tei/templates/configmap.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: ConfigMap
metadata:
name: chatqna-tei-config
labels:
helm.sh/chart: tei-1.0.0
app.kubernetes.io/name: tei
app.kubernetes.io/instance: chatqna
app.kubernetes.io/version: "cpu-1.5"
app.kubernetes.io/managed-by: Helm
data:
MODEL_ID: "BAAI/bge-base-en-v1.5"
PORT: "2081"
http_proxy: ""
https_proxy: ""
no_proxy: ""
NUMBA_CACHE_DIR: "/tmp"
TRANSFORMERS_CACHE: "/tmp/transformers_cache"
HF_HOME: "/tmp/.cache/huggingface"
MAX_WARMUP_SEQUENCE_LENGTH: "512"
---
# Source: chatqna/charts/teirerank/templates/configmap.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: ConfigMap
metadata:
name: chatqna-teirerank-config
labels:
helm.sh/chart: teirerank-1.0.0
app.kubernetes.io/name: teirerank
app.kubernetes.io/instance: chatqna
app.kubernetes.io/version: "cpu-1.5"
app.kubernetes.io/managed-by: Helm
data:
MODEL_ID: "BAAI/bge-reranker-base"
PORT: "2082"
http_proxy: ""
https_proxy: ""
no_proxy: ""
NUMBA_CACHE_DIR: "/tmp"
TRANSFORMERS_CACHE: "/tmp/transformers_cache"
HF_HOME: "/tmp/.cache/huggingface"
---
# Source: chatqna/charts/tgi/templates/configmap.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
# Source: chatqna/templates/nginx-deployment.yaml
apiVersion: v1
data:
default.conf: |+
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
server {
listen 80;
listen [::]:80;
proxy_connect_timeout 600;
proxy_send_timeout 600;
proxy_read_timeout 600;
send_timeout 600;
client_max_body_size 10G;
location /home {
alias /usr/share/nginx/html/index.html;
}
location / {
proxy_pass http://chatqna-chatqna-ui:5173;
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;
}
location /v1/chatqna {
proxy_pass http://chatqna:8888;
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;
}
location /v1/dataprep {
proxy_pass http://chatqna-data-prep:6007;
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;
}
location /v1/dataprep/get_file {
proxy_pass http://chatqna-data-prep:6007;
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;
}
location /v1/dataprep/delete_file {
proxy_pass http://chatqna-data-prep:6007;
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;
}
}
kind: ConfigMap
metadata:
name: chatqna-nginx-config
---
# Source: chatqna/charts/chatqna-ui/templates/service.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: Service
metadata:
name: chatqna-chatqna-ui
labels:
helm.sh/chart: chatqna-ui-1.0.0
app.kubernetes.io/name: chatqna-ui
app.kubernetes.io/instance: chatqna
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
spec:
type: ClusterIP
ports:
- port: 5173
targetPort: ui
protocol: TCP
name: ui
selector:
app.kubernetes.io/name: chatqna-ui
app.kubernetes.io/instance: chatqna
---
# Source: chatqna/charts/data-prep/templates/service.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: Service
metadata:
name: chatqna-data-prep
labels:
helm.sh/chart: data-prep-1.0.0
app.kubernetes.io/name: data-prep
app.kubernetes.io/instance: chatqna
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
spec:
type: ClusterIP
ports:
- port: 6007
targetPort: 6007
protocol: TCP
name: data-prep
selector:
app.kubernetes.io/name: data-prep
app.kubernetes.io/instance: chatqna
---
# Source: chatqna/charts/embedding-usvc/templates/service.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: Service
metadata:
name: chatqna-embedding-usvc
labels:
helm.sh/chart: embedding-usvc-1.0.0
app.kubernetes.io/name: embedding-usvc
app.kubernetes.io/instance: chatqna
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
spec:
type: ClusterIP
ports:
- port: 6000
targetPort: 6000
protocol: TCP
name: embedding-usvc
selector:
app.kubernetes.io/name: embedding-usvc
app.kubernetes.io/instance: chatqna
---
# Source: chatqna/charts/llm-uservice/templates/service.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: Service
metadata:
name: chatqna-llm-uservice
labels:
helm.sh/chart: llm-uservice-1.0.0
app.kubernetes.io/name: llm-uservice
app.kubernetes.io/instance: chatqna
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: chatqna
---
# Source: chatqna/charts/redis-vector-db/templates/service.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: Service
metadata:
name: chatqna-redis-vector-db
labels:
helm.sh/chart: redis-vector-db-1.0.0
app.kubernetes.io/name: redis-vector-db
app.kubernetes.io/instance: chatqna
app.kubernetes.io/version: "7.2.0-v9"
app.kubernetes.io/managed-by: Helm
spec:
type: ClusterIP
ports:
- port: 6379
targetPort: 6379
protocol: TCP
name: redis-service
- port: 8001
targetPort: 8001
protocol: TCP
name: redis-insight
selector:
app.kubernetes.io/name: redis-vector-db
app.kubernetes.io/instance: chatqna
---
# Source: chatqna/charts/reranking-usvc/templates/service.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: Service
metadata:
name: chatqna-reranking-usvc
labels:
helm.sh/chart: reranking-usvc-1.0.0
app.kubernetes.io/name: reranking-usvc
app.kubernetes.io/instance: chatqna
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
spec:
type: ClusterIP
ports:
- port: 8000
targetPort: 8000
protocol: TCP
name: reranking-usvc
selector:
app.kubernetes.io/name: reranking-usvc
app.kubernetes.io/instance: chatqna
---
# Source: chatqna/charts/retriever-usvc/templates/service.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: Service
metadata:
name: chatqna-retriever-usvc
labels:
helm.sh/chart: retriever-usvc-1.0.0
app.kubernetes.io/name: retriever-usvc
app.kubernetes.io/instance: chatqna
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
spec:
type: ClusterIP
ports:
- port: 7000
targetPort: 7000
protocol: TCP
name: retriever-usvc
selector:
app.kubernetes.io/name: retriever-usvc
app.kubernetes.io/instance: chatqna
---
# Source: chatqna/charts/tei/templates/service.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: Service
metadata:
name: chatqna-tei
labels:
helm.sh/chart: tei-1.0.0
app.kubernetes.io/name: tei
app.kubernetes.io/instance: chatqna
app.kubernetes.io/version: "cpu-1.5"
app.kubernetes.io/managed-by: Helm
spec:
type: ClusterIP
ports:
- port: 80
targetPort: 2081
protocol: TCP
name: tei
selector:
app.kubernetes.io/name: tei
app.kubernetes.io/instance: chatqna
---
# Source: chatqna/charts/teirerank/templates/service.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: Service
metadata:
name: chatqna-teirerank
labels:
helm.sh/chart: teirerank-1.0.0
app.kubernetes.io/name: teirerank
app.kubernetes.io/instance: chatqna
app.kubernetes.io/version: "cpu-1.5"
app.kubernetes.io/managed-by: Helm
spec:
type: ClusterIP
ports:
- port: 80
targetPort: 2082
protocol: TCP
name: teirerank
selector:
app.kubernetes.io/name: teirerank
app.kubernetes.io/instance: chatqna
---
# Source: chatqna/templates/nginx-deployment.yaml
apiVersion: v1
kind: Service
metadata:
name: chatqna-nginx
spec:
ports:
- port: 80
protocol: TCP
targetPort: 80
selector:
app.kubernetes.io/name: chatqna
app.kubernetes.io/instance: chatqna
app: chatqna-nginx
type: NodePort
---
# Source: chatqna/templates/service.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: Service
metadata:
name: chatqna
labels:
helm.sh/chart: chatqna-1.0.0
app.kubernetes.io/name: chatqna
app.kubernetes.io/instance: chatqna
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
spec:
type: ClusterIP
ports:
- port: 8888
targetPort: 8888
protocol: TCP
name: chatqna
selector:
app.kubernetes.io/name: chatqna
app.kubernetes.io/instance: chatqna
app: chatqna
---
# Source: chatqna/charts/chatqna-ui/templates/deployment.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: apps/v1
kind: Deployment
metadata:
name: chatqna-chatqna-ui
labels:
helm.sh/chart: chatqna-ui-1.0.0
app.kubernetes.io/name: chatqna-ui
app.kubernetes.io/instance: chatqna
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: chatqna-ui
app.kubernetes.io/instance: chatqna
template:
metadata:
labels:
helm.sh/chart: chatqna-ui-1.0.0
app.kubernetes.io/name: chatqna-ui
app.kubernetes.io/instance: chatqna
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
spec:
securityContext:
{}
containers:
- name: chatqna-ui
securityContext:
{}
image: "opea/chatqna-ui:latest"
imagePullPolicy: Always
ports:
- name: ui
containerPort: 5173
protocol: TCP
resources:
{}
volumeMounts:
- mountPath: /tmp
name: tmp
volumes:
- name: tmp
emptyDir: {}
---
# Source: chatqna/charts/data-prep/templates/deployment.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: apps/v1
kind: Deployment
metadata:
name: chatqna-data-prep
labels:
helm.sh/chart: data-prep-1.0.0
app.kubernetes.io/name: data-prep
app.kubernetes.io/instance: chatqna
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: data-prep
app.kubernetes.io/instance: chatqna
template:
metadata:
labels:
app.kubernetes.io/name: data-prep
app.kubernetes.io/instance: chatqna
spec:
securityContext:
{}
containers:
- name: chatqna
envFrom:
- configMapRef:
name: chatqna-data-prep-config
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop:
- ALL
readOnlyRootFilesystem: false
runAsNonRoot: true
runAsUser: 1000
seccompProfile:
type: RuntimeDefault
image: "opea/dataprep-redis:latest"
imagePullPolicy: Always
ports:
- name: data-prep
containerPort: 6007
protocol: TCP
volumeMounts:
- mountPath: /tmp
name: tmp
livenessProbe:
failureThreshold: 24
httpGet:
path: v1/health_check
port: data-prep
initialDelaySeconds: 5
periodSeconds: 5
readinessProbe:
httpGet:
path: v1/health_check
port: data-prep
initialDelaySeconds: 5
periodSeconds: 5
startupProbe:
failureThreshold: 120
httpGet:
path: v1/health_check
port: data-prep
initialDelaySeconds: 5
periodSeconds: 5
resources:
{}
volumes:
- name: tmp
emptyDir: {}
---
# Source: chatqna/charts/embedding-usvc/templates/deployment.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: apps/v1
kind: Deployment
metadata:
name: chatqna-embedding-usvc
labels:
helm.sh/chart: embedding-usvc-1.0.0
app.kubernetes.io/name: embedding-usvc
app.kubernetes.io/instance: chatqna
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: embedding-usvc
app.kubernetes.io/instance: chatqna
template:
metadata:
labels:
app.kubernetes.io/name: embedding-usvc
app.kubernetes.io/instance: chatqna
spec:
securityContext:
{}
containers:
- name: chatqna
envFrom:
- configMapRef:
name: chatqna-embedding-usvc-config
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop:
- ALL
readOnlyRootFilesystem: true
runAsNonRoot: true
runAsUser: 1000
seccompProfile:
type: RuntimeDefault
image: "opea/embedding-tei:latest"
imagePullPolicy: IfNotPresent
ports:
- name: embedding-usvc
containerPort: 6000
protocol: TCP
volumeMounts:
- mountPath: /tmp
name: tmp
livenessProbe:
failureThreshold: 24
httpGet:
path: v1/health_check
port: embedding-usvc
initialDelaySeconds: 5
periodSeconds: 5
readinessProbe:
httpGet:
path: v1/health_check
port: embedding-usvc
initialDelaySeconds: 5
periodSeconds: 5
startupProbe:
failureThreshold: 120
httpGet:
path: v1/health_check
port: embedding-usvc
initialDelaySeconds: 5
periodSeconds: 5
resources:
{}
volumes:
- name: tmp
emptyDir: {}
---
# Source: chatqna/charts/llm-uservice/templates/deployment.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: apps/v1
kind: Deployment
metadata:
name: chatqna-llm-uservice
labels:
helm.sh/chart: llm-uservice-1.0.0
app.kubernetes.io/name: llm-uservice
app.kubernetes.io/instance: chatqna
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: chatqna
template:
metadata:
labels:
app.kubernetes.io/name: llm-uservice
app.kubernetes.io/instance: chatqna
spec:
securityContext:
{}
containers:
- name: chatqna
envFrom:
- configMapRef:
name: chatqna-llm-uservice-config
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop:
- ALL
readOnlyRootFilesystem: false
runAsNonRoot: true
runAsUser: 1000
seccompProfile:
type: RuntimeDefault
image: "opea/llm-vllm: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: chatqna/charts/redis-vector-db/templates/deployment.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: apps/v1
kind: Deployment
metadata:
name: chatqna-redis-vector-db
labels:
helm.sh/chart: redis-vector-db-1.0.0
app.kubernetes.io/name: redis-vector-db
app.kubernetes.io/instance: chatqna
app.kubernetes.io/version: "7.2.0-v9"
app.kubernetes.io/managed-by: Helm
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: redis-vector-db
app.kubernetes.io/instance: chatqna
template:
metadata:
labels:
app.kubernetes.io/name: redis-vector-db
app.kubernetes.io/instance: chatqna
spec:
securityContext:
{}
containers:
- name: redis-vector-db
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop:
- ALL
readOnlyRootFilesystem: true
runAsNonRoot: true
runAsUser: 1000
seccompProfile:
type: RuntimeDefault
image: "redis/redis-stack:7.2.0-v9"
imagePullPolicy: Always
volumeMounts:
- mountPath: /data
name: data-volume
- mountPath: /redisinsight
name: redisinsight-volume
- mountPath: /tmp
name: tmp
ports:
- name: redis-service
containerPort: 6379
protocol: TCP
- name: redis-insight
containerPort: 8001
protocol: TCP
startupProbe:
tcpSocket:
port: 6379 # Probe the Redis port
initialDelaySeconds: 5
periodSeconds: 5
failureThreshold: 120
resources:
{}
volumes:
- name: data-volume
emptyDir: {}
- name: redisinsight-volume
emptyDir: {}
- name: tmp
emptyDir: {}
---
# Source: chatqna/charts/reranking-usvc/templates/deployment.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: apps/v1
kind: Deployment
metadata:
name: chatqna-reranking-usvc
labels:
helm.sh/chart: reranking-usvc-1.0.0
app.kubernetes.io/name: reranking-usvc
app.kubernetes.io/instance: chatqna
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: reranking-usvc
app.kubernetes.io/instance: chatqna
template:
metadata:
labels:
app.kubernetes.io/name: reranking-usvc
app.kubernetes.io/instance: chatqna
spec:
securityContext:
{}
containers:
- name: chatqna
envFrom:
- configMapRef:
name: chatqna-reranking-usvc-config
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop:
- ALL
readOnlyRootFilesystem: true
runAsNonRoot: true
runAsUser: 1000
seccompProfile:
type: RuntimeDefault
image: "opea/reranking-tei:latest"
imagePullPolicy: IfNotPresent
ports:
- name: reranking-usvc
containerPort: 8000
protocol: TCP
volumeMounts:
- mountPath: /tmp
name: tmp
livenessProbe:
failureThreshold: 24
httpGet:
path: v1/health_check
port: reranking-usvc
initialDelaySeconds: 5
periodSeconds: 5
readinessProbe:
httpGet:
path: v1/health_check
port: reranking-usvc
initialDelaySeconds: 5
periodSeconds: 5
startupProbe:
failureThreshold: 120
httpGet:
path: v1/health_check
port: reranking-usvc
initialDelaySeconds: 5
periodSeconds: 5
resources:
{}
volumes:
- name: tmp
emptyDir: {}
---
# Source: chatqna/charts/retriever-usvc/templates/deployment.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: apps/v1
kind: Deployment
metadata:
name: chatqna-retriever-usvc
labels:
helm.sh/chart: retriever-usvc-1.0.0
app.kubernetes.io/name: retriever-usvc
app.kubernetes.io/instance: chatqna
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: retriever-usvc
app.kubernetes.io/instance: chatqna
template:
metadata:
labels:
app.kubernetes.io/name: retriever-usvc
app.kubernetes.io/instance: chatqna
spec:
securityContext:
{}
containers:
- name: chatqna
envFrom:
- configMapRef:
name: chatqna-retriever-usvc-config
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop:
- ALL
readOnlyRootFilesystem: true
runAsNonRoot: true
runAsUser: 1000
seccompProfile:
type: RuntimeDefault
image: "opea/retriever-redis:latest"
imagePullPolicy: Always
ports:
- name: retriever-usvc
containerPort: 7000
protocol: TCP
volumeMounts:
- mountPath: /tmp
name: tmp
livenessProbe:
failureThreshold: 24
httpGet:
path: v1/health_check
port: retriever-usvc
initialDelaySeconds: 5
periodSeconds: 5
readinessProbe:
httpGet:
path: v1/health_check
port: retriever-usvc
initialDelaySeconds: 5
periodSeconds: 5
startupProbe:
failureThreshold: 120
httpGet:
path: v1/health_check
port: retriever-usvc
initialDelaySeconds: 5
periodSeconds: 5
resources:
{}
volumes:
- name: tmp
emptyDir: {}
---
# Source: chatqna/charts/tei/templates/deployment.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: apps/v1
kind: Deployment
metadata:
name: chatqna-tei
labels:
helm.sh/chart: tei-1.0.0
app.kubernetes.io/name: tei
app.kubernetes.io/instance: chatqna
app.kubernetes.io/version: "cpu-1.5"
app.kubernetes.io/managed-by: Helm
spec:
# use explicit replica counts only of HorizontalPodAutoscaler is disabled
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: tei
app.kubernetes.io/instance: chatqna
template:
metadata:
labels:
app.kubernetes.io/name: tei
app.kubernetes.io/instance: chatqna
spec:
securityContext:
{}
containers:
- name: tei
envFrom:
- configMapRef:
name: chatqna-tei-config
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop:
- ALL
readOnlyRootFilesystem: true
runAsNonRoot: true
runAsUser: 1000
seccompProfile:
type: RuntimeDefault
image: "ghcr.io/huggingface/text-embeddings-inference:cpu-1.5"
imagePullPolicy: Always
args:
- "--auto-truncate"
volumeMounts:
- mountPath: /data
name: model-volume
- mountPath: /dev/shm
name: shm
- mountPath: /tmp
name: tmp
ports:
- name: http
containerPort: 2081
protocol: TCP
livenessProbe:
failureThreshold: 24
httpGet:
path: /health
port: http
initialDelaySeconds: 5
periodSeconds: 5
readinessProbe:
httpGet:
path: /health
port: http
initialDelaySeconds: 5
periodSeconds: 5
startupProbe:
failureThreshold: 120
httpGet:
path: /health
port: http
initialDelaySeconds: 5
periodSeconds: 5
resources:
{}
volumes:
- name: model-volume
emptyDir: {}
- name: shm
emptyDir:
medium: Memory
sizeLimit: 1Gi
- name: tmp
emptyDir: {}
---
# Source: chatqna/charts/teirerank/templates/deployment.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: apps/v1
kind: Deployment
metadata:
name: chatqna-teirerank
labels:
helm.sh/chart: teirerank-1.0.0
app.kubernetes.io/name: teirerank
app.kubernetes.io/instance: chatqna
app.kubernetes.io/version: "cpu-1.5"
app.kubernetes.io/managed-by: Helm
spec:
# use explicit replica counts only of HorizontalPodAutoscaler is disabled
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: teirerank
app.kubernetes.io/instance: chatqna
template:
metadata:
labels:
app.kubernetes.io/name: teirerank
app.kubernetes.io/instance: chatqna
spec:
securityContext:
{}
containers:
- name: teirerank
envFrom:
- configMapRef:
name: chatqna-teirerank-config
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop:
- ALL
readOnlyRootFilesystem: true
runAsNonRoot: true
runAsUser: 1000
seccompProfile:
type: RuntimeDefault
image: "ghcr.io/huggingface/text-embeddings-inference:cpu-1.5"
imagePullPolicy: Always
args:
- "--auto-truncate"
volumeMounts:
- mountPath: /data
name: model-volume
- mountPath: /dev/shm
name: shm
- mountPath: /tmp
name: tmp
ports:
- name: http
containerPort: 2082
protocol: TCP
livenessProbe:
failureThreshold: 24
httpGet:
path: /health
port: http
initialDelaySeconds: 5
periodSeconds: 5
readinessProbe:
httpGet:
path: /health
port: http
initialDelaySeconds: 5
periodSeconds: 5
startupProbe:
failureThreshold: 120
httpGet:
path: /health
port: http
initialDelaySeconds: 5
periodSeconds: 5
resources:
{}
volumes:
- name: model-volume
emptyDir: {}
- name: shm
emptyDir:
medium: Memory
sizeLimit: 1Gi
- name: tmp
emptyDir: {}
---
# Source: chatqna/templates/deployment.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: apps/v1
kind: Deployment
metadata:
name: chatqna
labels:
helm.sh/chart: chatqna-1.0.0
app.kubernetes.io/name: chatqna
app.kubernetes.io/instance: chatqna
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
app: chatqna
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: chatqna
app.kubernetes.io/instance: chatqna
app: chatqna
template:
metadata:
labels:
app.kubernetes.io/name: chatqna
app.kubernetes.io/instance: chatqna
app: chatqna
spec:
securityContext:
null
containers:
- name: chatqna
env:
- name: LLM_SERVICE_HOST_IP
value: chatqna-llm-uservice
- name: RERANK_SERVICE_HOST_IP
value: chatqna-reranking-usvc
- name: RETRIEVER_SERVICE_HOST_IP
value: chatqna-retriever-usvc
- name: EMBEDDING_SERVICE_HOST_IP
value: chatqna-embedding-usvc
- name: MODEL_ID
value: "meta-llama/Meta-Llama-3.1-8B-Instruct"
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop:
- ALL
readOnlyRootFilesystem: true
runAsNonRoot: true
runAsUser: 1000
seccompProfile:
type: RuntimeDefault
image: "opea/chatqna-wrapper:latest"
imagePullPolicy: IfNotPresent
volumeMounts:
- mountPath: /tmp
name: tmp
ports:
- name: chatqna
containerPort: 8888
protocol: TCP
resources:
null
volumes:
- name: tmp
emptyDir: {}
---
# Source: chatqna/templates/nginx-deployment.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
name: chatqna-nginx
labels:
helm.sh/chart: chatqna-1.0.0
app.kubernetes.io/name: chatqna
app.kubernetes.io/instance: chatqna
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
app: chatqna-nginx
spec:
selector:
matchLabels:
app.kubernetes.io/name: chatqna
app.kubernetes.io/instance: chatqna
app: chatqna-nginx
template:
metadata:
labels:
app.kubernetes.io/name: chatqna
app.kubernetes.io/instance: chatqna
app: chatqna-nginx
spec:
containers:
- image: nginx:1.27.1
imagePullPolicy: Always
name: nginx
volumeMounts:
- mountPath: /etc/nginx/conf.d
name: nginx-config-volume
securityContext: {}
volumes:
- configMap:
defaultMode: 420
name: chatqna-nginx-config
name: nginx-config-volume