AI starter kit chart

.gitignore

@@ -43,3 +43,10 @@ cscope.*
 
 /bazel-*
 *.pyc
+
+# Helm chart dependecies cache
+**/Chart.lock
+**/charts/*.tgz
+
+# Helm chart output directory
+ai/ai-starter-kit/out

ai/ai-starter-kit/Makefile

@@ -0,0 +1,70 @@
+.PHONY: check_hf_token check_OCI_target package_helm lint dep_update install install_gke start uninstall push_helm
+
+check_hf_token:
+ifndef HF_TOKEN
+	$(error HF_TOKEN is not set)
+endif
+
+check_OCI_target:
+ifndef OCI_HELM_TARGET
+	$(error OCI_HELM_TARGET is not set)
+endif
+
+package_helm:
+	helm package helm-chart/ai-starter-kit/ --destination out/
+
+push_helm: check_OCI_target
+	helm push out/ai-starter-kit* oci://$$OCI_HELM_TARGET
+
+lint:
+	helm lint helm-chart/ai-starter-kit
+
+dep_update:
+	helm dependency update helm-chart/ai-starter-kit
+
+install: check_hf_token
+	helm upgrade --install ai-starter-kit helm-chart/ai-starter-kit --set huggingface.token="$$HF_TOKEN" --timeout 10m -f helm-chart/ai-starter-kit/values.yaml
+
+install_gke: check_hf_token
+	helm upgrade --install ai-starter-kit helm-chart/ai-starter-kit --set huggingface.token="$$HF_TOKEN" --timeout 10m -f helm-chart/ai-starter-kit/values-gke.yaml
+
+install_gke_gpu: check_hf_token
+	helm upgrade --install ai-starter-kit helm-chart/ai-starter-kit --set huggingface.token="$$HF_TOKEN" --timeout 10m -f helm-chart/ai-starter-kit/values-gke-gpu.yaml
+
+start:
+	mkdir -p /tmp/models-cache
+	minikube start --cpus 4 --memory 15000 --mount --mount-string="/tmp/models-cache:/tmp/models-cache"
+
+start_gpu:
+	mkdir -p $HOME/models-cache
+	minikube start --driver krunkit --cpus 4 --memory 15000 --mount --mount-string="$HOME/models-cache:$HOME/models-cache"
+
+uninstall:
+	helm uninstall ai-starter-kit
+	kubectl delete pod jupyter-user
+	kubectl delete pvc ai-starter-kit-jupyterhub-hub-db-dir
+
+destroy:
+	minikube delete
+
+validate_jupyterhub:
+	kubectl get pods; \
+    kubectl wait --for=condition=Ready pods -l 'component!=continuous-image-puller' --timeout=1800s; \
+    kubectl get pods; \
+    kubectl get services; \
+    kubectl port-forward service/ai-starter-kit-jupyterhub-proxy-public 8081:80 & \
+    PID=$$!; \
+    echo "Port-forward PID=$${PID}"; \
+    sleep 5s; \
+    python3 ./ci/test_hub.py "127.0.0.1:8081"; \
+    kill $$PID
+
+validate_ray:
+	kubectl wait --for=condition=Ready pods -l 'app.kubernetes.io/created-by=kuberay-operator' --timeout=1800s; \
+	kubectl get pods; \
+	kubectl get services; \
+	kubectl port-forward service/ai-starter-kit-kuberay-head-svc 8265:8265 & \
+	PID=$$!; \
+	sleep 10s; \
+	ray job submit --address=http://127.0.0.1:8265 -- python -c "import ray; ray.init(); print(ray.cluster_resources())"; \
+	kill $$PID

ai/ai-starter-kit/helm-chart/ai-starter-kit/.helmignore

@@ -0,0 +1,23 @@
+# Patterns to ignore when building packages.
+# This supports shell glob matching, relative path matching, and
+# negation (prefixed with !). Only one pattern per line.
+.DS_Store
+# Common VCS dirs
+.git/
+.gitignore
+.bzr/
+.bzrignore
+.hg/
+.hgignore
+.svn/
+# Common backup files
+*.swp
+*.bak
+*.tmp
+*.orig
+*~
+# Various IDEs
+.project
+.idea/
+*.tmproj
+.vscode/

ai/ai-starter-kit/helm-chart/ai-starter-kit/Chart.yaml

@@ -0,0 +1,45 @@
+apiVersion: v2
+name: ai-starter-kit
+description: A Helm chart for Kubernetes
+
+# A chart can be either an 'application' or a 'library' chart.
+#
+# Application charts are a collection of templates that can be packaged into versioned archives
+# to be deployed.
+#
+# Library charts provide useful utilities or functions for the chart developer. They're included as
+# a dependency of application charts to inject those utilities and functions into the rendering
+# pipeline. Library charts do not define any templates and therefore cannot be deployed.
+type: application
+
+# This is the chart version. This version number should be incremented each time you make changes
+# to the chart and its templates, including the app version.
+# Versions are expected to follow Semantic Versioning (https://semver.org/)
+version: 0.1.0
+
+# This is the version number of the application being deployed. This version number should be
+# incremented each time you make changes to the application. Versions are not expected to
+# follow Semantic Versioning. They should reflect the version the application is using.
+# It is recommended to use it with quotes.
+appVersion: "0.1.0"
+
+
+dependencies:
+  - name: kuberay-operator
+    condition: ray-cluster.enabled
+    version: "1.3.0"
+    repository: "https://ray-project.github.io/kuberay-helm"
+  - condition: ray-cluster.enabled
+    name: ray-cluster
+    version: "1.3.0"
+    repository: "https://ray-project.github.io/kuberay-helm"
+  - name: jupyterhub
+    version: "4.2.0"
+    repository: "https://hub.jupyter.org/helm-chart/"
+  - name: mlflow
+    version: "0.12.0"
+    repository: "https://community-charts.github.io/helm-charts"
+  - name: ollama
+    condition: ollama.enabled
+    version: "1.27.0"
+    repository: "https://helm.otwld.com"