SIENTIAPDE-1309: Update README with Helm instructions and refactor experiment status messages. Also, update values.yaml with new image and configurations.

This commit is contained in:
Bruno Domingues
2025-11-06 15:34:03 -03:00
parent a625ef6c19
commit c7f44a2423
9 changed files with 133 additions and 95 deletions

View File

@@ -7,18 +7,19 @@ replicaCount: 1
# This sets the container image more information can be found here: https://kubernetes.io/docs/concepts/containers/images/
image:
repository: aignosi.azurecr.io/sientia-module-courier
repository: aignosi.azurecr.io/sientia-dataops-model-manager
# This sets the pull policy for images.
pullPolicy: Always
pullPolicy: IfNotPresent
# Overrides the image tag whose default is the chart appVersion.
tag: "0.0.2"
tag: "0.0.0"
# This is for the secrets for pulling an image from a private repository more information can be found here: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
imagePullSecrets:
- name: docker-hub-secret
# This is to override the chart name.
nameOverride: "sientia-model-manager-worker"
fullnameOverride: "sientia-model-manager-worker"
nameOverride: "sientia-dataops-model-manager"
fullnameOverride: "sientia-dataops-model-manager"
namespace: sientia
# This section builds out the service account more information can be found here: https://kubernetes.io/docs/concepts/security/service-accounts/
@@ -31,7 +32,7 @@ serviceAccount:
annotations: {}
# The name of the service account to use.
# If not set and create is true, a name is generated using the fullname template
name: "sientia-model-manager-worker"
name: "sientia-dataops-model-manager"
# This is for setting Kubernetes Annotations to a Pod.
# For more information checkout: https://kubernetes.io/docs/concepts/overview/working-with-objects/annotations/
@@ -68,22 +69,21 @@ resources: {}
livenessProbe:
exec:
command:
- sh
- python3
- -c
- pgrep -f "model_manager.worker.worker"
- "import requests; requests.get('http://localhost:9090/metrics')"
initialDelaySeconds: 20
periodSeconds: 30
readinessProbe:
exec:
command:
- sh
- python3
- -c
- pgrep -f "model_manager.worker.worker"
- "import requests; requests.get('http://localhost:9090/metrics')"
initialDelaySeconds: 10
periodSeconds: 15
# This section is for setting up autoscaling more information can be found here: https://kubernetes.io/docs/concepts/workloads/autoscaling/
autoscaling:
enabled: false
@@ -105,6 +105,17 @@ volumeMounts: []
# mountPath: "/etc/foo"
# readOnly: true
# Deployment strategy configuration
# More information: https://kubernetes.io/docs/concepts/workloads/controllers/deployment/#strategy
deploymentStrategy:
type: Recreate
# rollingUpdate:
# maxSurge: 0
# maxUnavailable: 1
# Number of old ReplicaSets to retain
revisionHistoryLimit: 2
nodeSelector: {}
tolerations: []
@@ -118,7 +129,6 @@ services:
port: 9091
targetPort: 9091
name: sdk-metrics
metrics:
enabled: true
type: ClusterIP
@@ -141,48 +151,32 @@ serviceMonitor:
path: /metrics
interval: 30s
relabelings: []
additionalLabels:
release: kube-prometheus-stack
env:
# Entrypoint variables
- name: GITHUB_REPO_URL
value: "git@github.com:Aignosi/sientia-dataops-model-manager.git"
- name: GITHUB_BRANCH
value: SIENTIAPDE-1222-ajustar-a-library-para-fazer-o-download-do-courier
- name: PYTHON_APP
value: "model_manager.worker.worker"
# Application variables
- name: POSTGRES_HOST
value: "paradedb-rw.paradedb.svc.cluster.local"
- name: POSTGRES_PORT
value: "5432"
- name: POSTGRES_USER
value: "sientia"
value: "postgres"
- name: POSTGRES_PASSWORD
value: "sientia"
value: "nFqc81y6kwmr2zuAIx43DhiOosFCVPpeEfTtTWZflkNjB2j1KtEeIANkhFR9mAX3"
- name: POSTGRES_DBNAME
value: "sientia"
value: "sientia-core-mlops-bff"
- name: POSTGRES_MIN_CONNECTIONS
value: "10"
- name: POSTGRES_MAX_CONNECTIONS
value: "30"
- name: MLFLOW_HOST
value: "http://sientia-tracker-mlflow-tracking.sientia-tracker.svc.cluster.local"
- name: MLFLOW_PORT
value: "80"
- name: MLFLOW_URL
value: "http://sientia-tracker-mlflow-tracking.sientia-tracker.svc.cluster.local:80"
- name: MLFLOW_USERNAME
value: "aignosi"
- name: MLFLOW_PASSWORD
value: "1L0FP50j3ncp123"
- name: KAFKA_BOOTSTRAP_SERVERS
value: "kafka.kafka.svc.cluster.local:9092"
- name: LOG_LEVEL
value: "DEBUG"
- name: HTTP_METRICS_PORT
@@ -208,15 +202,51 @@ env:
- name: MONGODB_TTL_INDEX_HOURS
value: "1"
- name: MINIO_ENDPOINT_URL
value: "http://minio.minio.svc.cluster.local:9000"
- name: MINIO_ACCESS_KEY
value: "model-training-user"
- name: MINIO_SECRET_KEY
value: "modelTrainingUser123"
- name: MINIO_REGION
value: "us-east-1"
- name: MINIO_USE_SSL
value: "false"
- name: MINIO_MAX_RETRY_ATTEMPTS
value: "3"
- name: MINIO_RETRY_MODE
value: "adaptive"
- name: MINIO_CONNECT_TIMEOUT
value: "10"
- name: MINIO_READ_TIMEOUT
value: "60"
- name: TIMEOUT_VALIDATE_PARAMS
value: "30"
- name: TIMEOUT_TRAIN_MODEL
value: "2700"
- name: TIMEOUT_DELETE_FILE
value: "120"
- name: TIMEOUT_UPDATE_DATABASE
value: "30"
- name: EXTRA_PIP_REQUIREMENTS
value: "git+https://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@github.com/Aignosi/sientia-mlops-library.git"
- name: POD_ID
valueFrom:
fieldRef:
fieldPath: metadata.name
ssh:
enabled: true
enabled: false
secretName: git-ssh-key-sientia-model-manager-worker
sshPath: /mnt/.ssh
knownHostsPath: /mnt/known_hosts
# kubectl create secret docker-registry docker-hub-secret --namespace sientia --docker-server=http://aignosi.azurecr.io --docker-username=aignosi --docker-password=5I5zpQ6sRaHqX1hD3dr+2mo647yO3FRc359/wu6gsP+ACRDRz5mp
# helm upgrade --install sientia-model-manager-worker sientia/sientia-module -n sientia --create-namespace -f ./values.yaml --version 0.5.0
# helm upgrade --install sientia-dataops-model-manager sientia/sientia-module -n sientia --create-namespace -f ./values.yaml --version 0.5.0
# kubectl create secret generic git-ssh-key-sientia-model-manager-worker \
# --namespace sientia \