Merge pull request #1602 from ShaunMaher/add_helm_chart

Add a Helm chart for deploying LiteLLM Proxy
This commit is contained in:
Ishaan Jaff 2024-02-05 08:12:58 -08:00 committed by GitHub
commit 109ccf4cef
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
22 changed files with 1190 additions and 1 deletions

View file

@ -0,0 +1,77 @@
name: Helm OCI Chart Releaser
description: Push Helm charts to OCI-based (Docker) registries
author: sergeyshaykhullin
branding:
color: yellow
icon: upload-cloud
inputs:
name:
required: true
description: Chart name
repository:
required: true
description: Chart repository name
tag:
required: true
description: Chart version
app_version:
required: true
description: App version
path:
required: false
description: Chart path (Default 'charts/{name}')
registry:
required: true
description: OCI registry
registry_username:
required: true
description: OCI registry username
registry_password:
required: true
description: OCI registry password
update_dependencies:
required: false
default: 'false'
description: Update chart dependencies before packaging (Default 'false')
outputs:
image:
value: ${{ steps.output.outputs.image }}
description: Chart image (Default '{registry}/{repository}/{image}:{tag}')
runs:
using: composite
steps:
- name: Helm | Login
shell: bash
run: echo ${{ inputs.registry_password }} | helm registry login -u ${{ inputs.registry_username }} --password-stdin ${{ inputs.registry }}
env:
HELM_EXPERIMENTAL_OCI: '1'
- name: Helm | Dependency
if: inputs.update_dependencies == 'true'
shell: bash
run: helm dependency update ${{ inputs.path == null && format('{0}/{1}', 'charts', inputs.name) || inputs.path }}
env:
HELM_EXPERIMENTAL_OCI: '1'
- name: Helm | Package
shell: bash
run: helm package ${{ inputs.path == null && format('{0}/{1}', 'charts', inputs.name) || inputs.path }} --version ${{ inputs.tag }} --app-version ${{ inputs.app_version }}
env:
HELM_EXPERIMENTAL_OCI: '1'
- name: Helm | Push
shell: bash
run: helm push ${{ inputs.name }}-${{ inputs.tag }}.tgz oci://${{ inputs.registry }}/${{ inputs.repository }}
env:
HELM_EXPERIMENTAL_OCI: '1'
- name: Helm | Logout
shell: bash
run: helm registry logout ${{ inputs.registry }}
env:
HELM_EXPERIMENTAL_OCI: '1'
- name: Helm | Output
id: output
shell: bash
run: echo "image=${{ inputs.registry }}/${{ inputs.repository }}/${{ inputs.name }}:${{ inputs.tag }}" >> $GITHUB_OUTPUT

64
.github/workflows/ghcr_helm_deploy.yml vendored Normal file
View file

@ -0,0 +1,64 @@
# this workflow is triggered by an API call when there is a new PyPI release of LiteLLM
name: Build, Publish LiteLLM Helm Chart. New Release
on:
workflow_dispatch:
inputs:
chartVersion:
description: "Update the helm chart's version to this"
# Defines two custom environment variables for the workflow. Used for the Container registry domain, and a name for the Docker image that this workflow builds.
env:
REGISTRY: ghcr.io
IMAGE_NAME: ${{ github.repository }}
REPO_OWNER: ${{github.repository_owner}}
# There is a single job in this workflow. It's configured to run on the latest available version of Ubuntu.
jobs:
build-and-push-helm-chart:
runs-on: ubuntu-latest
steps:
- name: Checkout repository
uses: actions/checkout@v4
- name: Log in to the Container registry
uses: docker/login-action@65b78e6e13532edd9afa3aa52ac7964289d1a9c1
with:
registry: ${{ env.REGISTRY }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: lowercase github.repository_owner
run: |
echo "REPO_OWNER=`echo ${{github.repository_owner}} | tr '[:upper:]' '[:lower:]'`" >>${GITHUB_ENV}
- name: Get LiteLLM Latest Tag
id: current_app_tag
uses: WyriHaximus/github-action-get-previous-tag@v1.3.0
- name: Get last published chart version
id: current_version
shell: bash
run: helm show chart oci://${{ env.REGISTRY }}/${{ env.REPO_OWNER }}/litellm-helm | grep '^version:' | awk 'BEGIN{FS=":"}{print "current-version="$2}' | tr -d " " | tee -a $GITHUB_OUTPUT
env:
HELM_EXPERIMENTAL_OCI: '1'
# Automatically update the helm chart version one "patch" level
- name: Bump release version
id: bump_version
uses: christian-draeger/increment-semantic-version@1.1.0
with:
current-version: ${{ steps.current_version.outputs.current-version || '0.1.0' }}
version-fragment: 'bug'
- uses: ./.github/actions/helm-oci-chart-releaser
with:
name: litellm-helm
repository: ${{ env.REPO_OWNER }}
tag: ${{ github.event.inputs.chartVersion || steps.bump_version.outputs.next-version || '0.1.0' }}
app_version: ${{ steps.current_app_tag.outputs.tag || 'latest' }}
path: deploy/charts/litellm-helm
registry: ${{ env.REGISTRY }}
registry_username: ${{ github.actor }}
registry_password: ${{ secrets.GITHUB_TOKEN }}
update_dependencies: true

5
.gitignore vendored
View file

@ -39,4 +39,7 @@ ui/litellm-dashboard/.next
ui/litellm-dashboard/node_modules
ui/litellm-dashboard/next-env.d.ts
ui/litellm-dashboard/package.json
ui/litellm-dashboard/package-lock.json
ui/litellm-dashboard/package-lock.json
deploy/charts/litellm-helm/*.tgz
deploy/charts/litellm-helm/charts/*
deploy/charts/*.tgz

View file

@ -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/

View file

@ -0,0 +1,6 @@
dependencies:
- name: postgresql
repository: oci://registry-1.docker.io/bitnamicharts
version: 13.3.1
digest: sha256:f5c129150f0d38dd06752ab37f3c8e143d7c14d30379af058767bcd9f4ba83dd
generated: "2024-01-19T11:32:56.694808861+11:00"

View file

@ -0,0 +1,34 @@
apiVersion: v2
# We can't call ourselves just "litellm" because then we couldn't publish to the
# same OCI repository as the "litellm" OCI image
name: litellm-helm
description: Call all LLM APIs using the OpenAI format
# 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: v1.18.9
dependencies:
- name: "postgresql"
version: ">=13.3.0"
repository: oci://registry-1.docker.io/bitnamicharts
condition: db.deployStandalone

View file

@ -0,0 +1,107 @@
# Helm Chart for LiteLLM
## Prerequisites
- Kubernetes 1.23+
- Helm 3.8.0+
If `db.deployStandalone` is used:
- PV provisioner support in the underlying infrastructure
If `db.useStackgresOperator` is used (not yet implemented):
- The Stackgres Operator must already be installed in the Kubernetes Cluster. This chart will **not** install the operator if it is missing.
## Parameters
### LiteLLM Proxy Deployment Settings
| Name | Description | Value |
| ---------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
| `replicaCount` | The number of LiteLLM Proxy pods to be deployed | `1` |
| `masterkey` | The Master API Key for LiteLLM. If not specified, a random key is generated. | N/A |
| `environmentSecrets` | An optional array of Secret object names. The keys and values in these secrets will be presented to the LiteLLM proxy pod as environment variables. See below for an example Secret object. | `[]` |
| `image.repository` | LiteLLM Proxy image repository | `ghcr.io/berriai/litellm` |
| `image.pullPolicy` | LiteLLM Proxy image pull policy | `IfNotPresent` |
| `image.tag` | Overrides the image tag whose default the latest version of LiteLLM at the time this chart was published. | `""` |
| `image.dbReadyImage` | On Pod startup, an initContainer is used to make sure the Postgres database is available before attempting to start LiteLLM. This field specifies the image to use as that initContainer. | `docker.io/bitnami/postgresql` |
| `image.dbReadyTag` | Tag for the above image. If not specified, "latest" is used. | `""` |
| `imagePullSecrets` | Registry credentials for the LiteLLM and initContainer images. | `[]` |
| `serviceAccount.create` | Whether or not to create a Kubernetes Service Account for this deployment. The default is `false` because LiteLLM has no need to access the Kubernetes API. | `false` |
| `service.type` | Kubernetes Service type (e.g. `LoadBalancer`, `ClusterIP`, etc.) | `ClusterIP` |
| `service.port` | TCP port that the Kubernetes Service will listen on. Also the TCP port within the Pod that the proxy will listen on. | `8000` |
| `ingress.*` | See [values.yaml](./values.yaml) for example settings | N/A |
| `proxy_config.*` | See [values.yaml](./values.yaml) for default settings. See [example_config_yaml](../../../litellm/proxy/example_config_yaml/) for configuration examples. | N/A |
#### Example `environmentSecrets` Secret
```
apiVersion: v1
kind: Secret
metadata:
name: litellm-envsecrets
data:
AZURE_OPENAI_API_KEY: TXlTZWN1cmVLM3k=
type: Opaque
```
### LiteLLM Admin UI Settings
| Name | Description | Value |
| ---------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
| `ui.enabled` | Should the LiteLLM Admin UI be deployed | `true` |
| `ui.replicaCount` | The number of LiteLLM Admin UI pods to be deployed | `1` |
| `ui.image.repository` | LiteLLM Admin UI image repository | `ghcr.io/berriai/litellm` |
| `ui.image.pullPolicy` | LiteLLM Admin UI image pull policy | `IfNotPresent` |
| `ui.image.tag` | Overrides the image tag whose default the latest version of LiteLLM at the time this chart was published. | `""` |
| `ui.imagePullSecrets` | Registry credentials for the above images. | `[]` |
| `ui.service.type` | Kubernetes Service type (e.g. `LoadBalancer`, `ClusterIP`, etc.) | `ClusterIP` |
| `ui.service.port` | TCP port that the Kubernetes Service will listen on. Also the TCP port within the Pod that the web server will listen on. | `8000` |
| `ui.ingress.*` | See [values.yaml](./values.yaml) for example settings | N/A |
### Database Settings
| Name | Description | Value |
| ---------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
| `db.useExisting` | Use an existing Postgres database. A Kubernetes Secret object must exist that contains credentials for connecting to the database. An example secret object definition is provided below. | `false` |
| `db.endpoint` | If `db.useExisting` is `true`, this is the IP, Hostname or Service Name of the Postgres server to connect to. | `localhost` |
| `db.database` | If `db.useExisting` is `true`, the name of the existing database to connect to. | `litellm` |
| `db.secret.name` | If `db.useExisting` is `true`, the name of the Kubernetes Secret that contains credentials. | `postgres` |
| `db.secret.usernameKey` | If `db.useExisting` is `true`, the name of the key within the Kubernetes Secret that holds the username for authenticating with the Postgres instance. | `username` |
| `db.secret.passwordKey` | If `db.useExisting` is `true`, the name of the key within the Kubernetes Secret that holds the password associates with the above user. | `password` |
| `db.useStackgresOperator` | Not yet implemented. | `false` |
| `db.deployStandalone` | Deploy a standalone, single instance deployment of Postgres, using the Bitnami postgresql chart. This is useful for getting started but doesn't provide HA or (by default) data backups. | `true` |
| `postgresql.*` | If `db.deployStandalone` is `true`, configuration passed to the Bitnami postgresql chart. See the [Bitnami Documentation](https://github.com/bitnami/charts/tree/main/bitnami/postgresql) for full configuration details. See [values.yaml](./values.yaml) for the default configuration. | See [values.yaml](./values.yaml) |
| `postgresql.auth.*` | If `db.deployStandalone` is `true`, care should be taken to ensure the default `password` and `postgres-password` values are **NOT** used. | `NoTaGrEaTpAsSwOrD` |
#### Example Postgres `db.useExisting` Secret
```yaml
apiVersion: v1
kind: Secret
metadata:
name: postgres
data:
# Password for the "postgres" user
postgres-password: <some secure password, base64 encoded>
username: litellm
password: <some secure password, base64 encoded>
type: Opaque
```
## Accessing the Admin UI
When browsing to the URL published per the settings in `ui.ingress.*`, you will
be prompted for **Admin Configuration**. The **Proxy Endpoint** is the internal
(from the `litellm-ui` pod's perspective) URL published by the `litellm-proxy`
Kubernetes Service. If the deployment uses the default settings for this
service, the **Proxy Endpoint** should be set to `http://litellm-proxy:8000`.
The **Proxy Key** is the value specified for `masterkey` or, if a `masterkey`
was not provided to the helm command line, the `masterkey` is a randomly
generated string stored in the `litellm-masterkey` Kubernetes Secret.
```bash
kubectl -n litellm get secret litellm-masterkey -o jsonpath="{.data.masterkey}"
```
## Admin UI Limitations
At the time of writing, the Admin UI is unable to add models. This is because
it would need to update the `config.yaml` file which is a exposed ConfigMap, and
therefore, read-only. This is a limitation of this helm chart, not the Admin UI
itself.

View file

@ -0,0 +1,22 @@
1. Get the application URL by running these commands:
{{- if .Values.ingress.enabled }}
{{- range $host := .Values.ingress.hosts }}
{{- range .paths }}
http{{ if $.Values.ingress.tls }}s{{ end }}://{{ $host.host }}{{ .path }}
{{- end }}
{{- end }}
{{- else if contains "NodePort" .Values.service.type }}
export NODE_PORT=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ include "litellm.fullname" . }})
export NODE_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}")
echo http://$NODE_IP:$NODE_PORT
{{- else if contains "LoadBalancer" .Values.service.type }}
NOTE: It may take a few minutes for the LoadBalancer IP to be available.
You can watch the status of by running 'kubectl get --namespace {{ .Release.Namespace }} svc -w {{ include "litellm.fullname" . }}'
export SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ include "litellm.fullname" . }} --template "{{"{{ range (index .status.loadBalancer.ingress 0) }}{{.}}{{ end }}"}}")
echo http://$SERVICE_IP:{{ .Values.service.port }}
{{- else if contains "ClusterIP" .Values.service.type }}
export POD_NAME=$(kubectl get pods --namespace {{ .Release.Namespace }} -l "app.kubernetes.io/name={{ include "litellm.name" . }},app.kubernetes.io/instance={{ .Release.Name }}" -o jsonpath="{.items[0].metadata.name}")
export CONTAINER_PORT=$(kubectl get pod --namespace {{ .Release.Namespace }} $POD_NAME -o jsonpath="{.spec.containers[0].ports[0].containerPort}")
echo "Visit http://127.0.0.1:8080 to use your application"
kubectl --namespace {{ .Release.Namespace }} port-forward $POD_NAME 8080:$CONTAINER_PORT
{{- end }}

View file

@ -0,0 +1,74 @@
{{/*
Expand the name of the chart.
*/}}
{{- define "litellm.name" -}}
{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }}
{{- end }}
{{/*
Create a default fully qualified app name.
We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec).
If release name contains chart name it will be used as a full name.
*/}}
{{- define "litellm.fullname" -}}
{{- if .Values.fullnameOverride }}
{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }}
{{- else }}
{{- $name := default .Chart.Name .Values.nameOverride }}
{{- if contains $name .Release.Name }}
{{- .Release.Name | trunc 63 | trimSuffix "-" }}
{{- else }}
{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }}
{{- end }}
{{- end }}
{{- end }}
{{/*
Create chart name and version as used by the chart label.
*/}}
{{- define "litellm.chart" -}}
{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
{{- end }}
{{/*
Common labels
*/}}
{{- define "litellm.labels" -}}
helm.sh/chart: {{ include "litellm.chart" . }}
{{ include "litellm.selectorLabels" . }}
{{- if .Chart.AppVersion }}
app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
{{- end }}
app.kubernetes.io/managed-by: {{ .Release.Service }}
{{- end }}
{{- define "litellm.ui.labels" -}}
helm.sh/chart: {{ include "litellm.chart" . }}
{{ include "litellm.ui.selectorLabels" . }}
{{- if .Chart.AppVersion }}
app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
{{- end }}
app.kubernetes.io/managed-by: {{ .Release.Service }}
{{- end }}
{{/*
Selector labels
*/}}
{{- define "litellm.selectorLabels" -}}
app.kubernetes.io/name: {{ include "litellm.name" . }}
app.kubernetes.io/instance: {{ .Release.Name }}
{{- end }}
{{- define "litellm.ui.selectorLabels" -}}
app.kubernetes.io/name: {{ include "litellm.name" . }}-ui
app.kubernetes.io/instance: {{ .Release.Name }}
{{- end }}
{{/*
Create the name of the service account to use
*/}}
{{- define "litellm.serviceAccountName" -}}
{{- if .Values.serviceAccount.create }}
{{- default (include "litellm.fullname" .) .Values.serviceAccount.name }}
{{- else }}
{{- default "default" .Values.serviceAccount.name }}
{{- end }}
{{- end }}

View file

@ -0,0 +1,7 @@
apiVersion: v1
kind: ConfigMap
metadata:
name: {{ include "litellm.fullname" . }}-config
data:
config.yaml: |
{{ .Values.proxy_config | toYaml | indent 6 }}

View file

@ -0,0 +1,230 @@
apiVersion: apps/v1
kind: Deployment
metadata:
name: {{ include "litellm.fullname" . }}-proxy
labels:
{{- include "litellm.labels" . | nindent 4 }}
spec:
{{- if not .Values.autoscaling.enabled }}
replicas: {{ .Values.replicaCount }}
{{- end }}
selector:
matchLabels:
{{- include "litellm.selectorLabels" . | nindent 6 }}
template:
metadata:
{{- with .Values.podAnnotations }}
annotations:
{{- toYaml . | nindent 8 }}
{{- end }}
labels:
{{- include "litellm.labels" . | nindent 8 }}
{{- with .Values.podLabels }}
{{- toYaml . | nindent 8 }}
{{- end }}
spec:
{{- with .Values.imagePullSecrets }}
imagePullSecrets:
{{- toYaml . | nindent 8 }}
{{- end }}
serviceAccountName: {{ include "litellm.serviceAccountName" . }}
securityContext:
{{- toYaml .Values.podSecurityContext | nindent 8 }}
initContainers:
- name: db-ready
securityContext:
{{- toYaml .Values.securityContext | nindent 12 }}
image: "docker.io/bitnami/postgresql:16.1.0-debian-11-r20"
imagePullPolicy: {{ .Values.image.pullPolicy }}
env:
{{- if .Values.db.deployStandalone }}
- name: DATABASE_USERNAME
valueFrom:
secretKeyRef:
name: {{ include "litellm.name" . }}-dbcredentials
key: username
- name: PGPASSWORD
valueFrom:
secretKeyRef:
name: {{ include "litellm.name" . }}-dbcredentials
key: password
- name: DATABASE_HOST
value: {{ .Release.Name }}-postgresql
- name: DATABASE_NAME
value: litellm
{{- else if .Values.db.useExisting }}
- name: DATABASE_USERNAME
valueFrom:
secretKeyRef:
name: {{ .Values.db.secret.name }}
key: {{ .Values.db.secret.usernameKey }}
- name: PGPASSWORD
valueFrom:
secretKeyRef:
name: {{ .Values.db.secret.name }}
key: {{ .Values.db.secret.passwordKey }}
- name: DATABASE_HOST
value: {{ .Values.db.endpoint }}
- name: DATABASE_NAME
value: litellm
{{- end }}
command:
- sh
- -c
- |
# Maximum wait time will be (limit * 2) seconds.
limit=60
current=0
ret=1
while [ $current -lt $limit ] && [ $ret -ne 0 ]; do
echo "Waiting for database to be ready $current"
psql -U $(DATABASE_USERNAME) -h $(DATABASE_HOST) -l
ret=$?
current=$(( $current + 1 ))
sleep 2
done
if [ $ret -eq 0 ]; then
echo "Database is ready"
else
echo "Database failed to become ready before we gave up waiting."
fi
{{ if .Values.securityContext.readOnlyRootFilesystem }}
volumeMounts:
- name: tmp
mountPath: /tmp
{{ end }}
containers:
- name: {{ include "litellm.name" . }}
securityContext:
{{- toYaml .Values.securityContext | nindent 12 }}
image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default (printf "main-%s" .Chart.AppVersion) }}"
imagePullPolicy: {{ .Values.image.pullPolicy }}
env:
- name: HOST
value: "0.0.0.0"
- name: PORT
value: {{ .Values.service.port | quote}}
{{- if .Values.db.deployStandalone }}
- name: DATABASE_USERNAME
valueFrom:
secretKeyRef:
name: {{ include "litellm.name" . }}-dbcredentials
key: username
- name: DATABASE_PASSWORD
valueFrom:
secretKeyRef:
name: {{ include "litellm.name" . }}-dbcredentials
key: password
- name: DATABASE_HOST
value: {{ .Release.Name }}-postgresql
- name: DATABASE_NAME
value: litellm
{{- else if .Values.db.useExisting }}
- name: DATABASE_USERNAME
valueFrom:
secretKeyRef:
name: {{ .Values.db.secret.name }}
key: {{ .Values.db.secret.usernameKey }}
- name: DATABASE_PASSWORD
valueFrom:
secretKeyRef:
name: {{ .Values.db.secret.name }}
key: {{ .Values.db.secret.passwordKey }}
- name: DATABASE_HOST
value: {{ .Values.db.endpoint }}
- name: DATABASE_NAME
value: {{ .Values.db.database }}
{{- end }}
- name: DATABASE_URL
value: "postgresql://$(DATABASE_USERNAME):$(DATABASE_PASSWORD)@$(DATABASE_HOST)/$(DATABASE_NAME)"
- name: PROXY_MASTER_KEY
valueFrom:
secretKeyRef:
name: {{ include "litellm.name" . }}-masterkey
key: masterkey
envFrom:
{{- range .Values.environmentSecrets }}
- secretRef:
name: {{ . }}
{{- end }}
args:
- --config
- /etc/litellm/config.yaml
# command:
# - bash
# - -c
# - |
# ls -la /etc/litellm/; cat /etc/litellm/config.yaml; export
# find / 2>/dev/null | grep -v -e '^/proc' -e '^/sys' -e '^/dev' >/tmp/before.list
# prisma generate
# find / 2>/dev/null | grep -v -e '^/proc' -e '^/sys' -e '^/dev' >/tmp/after.list
# diff -ruN /tmp/before.list /tmp/after.list
# sleep 3600
ports:
- name: http
containerPort: {{ .Values.service.port }}
protocol: TCP
livenessProbe:
httpGet:
path: /health/liveliness
port: http
readinessProbe:
httpGet:
path: /health/readiness
port: http
# Give the container time to start up. Up to 5 minutes (10 * 30 seconds)
startupProbe:
httpGet:
path: /health/readiness
port: http
failureThreshold: 30
periodSeconds: 10
resources:
{{- toYaml .Values.resources | nindent 12 }}
volumeMounts:
- name: litellm-config
mountPath: /etc/litellm/
{{ if .Values.securityContext.readOnlyRootFilesystem }}
- name: tmp
mountPath: /tmp
- name: cache
mountPath: /.cache
- name: npm
mountPath: /.npm
{{- end }}
{{- with .Values.volumeMounts }}
{{- toYaml . | nindent 12 }}
{{- end }}
volumes:
{{ if .Values.securityContext.readOnlyRootFilesystem }}
- name: tmp
emptyDir:
sizeLimit: 500Mi
- name: cache
emptyDir:
sizeLimit: 500Mi
- name: npm
emptyDir:
sizeLimit: 500Mi
{{- end }}
- name: litellm-config
configMap:
name: {{ include "litellm.fullname" . }}-config
items:
- key: "config.yaml"
path: "config.yaml"
{{- with .Values.volumes }}
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.nodeSelector }}
nodeSelector:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.affinity }}
affinity:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.tolerations }}
tolerations:
{{- toYaml . | nindent 8 }}
{{- end }}

View file

@ -0,0 +1,89 @@
{{- if .Values.ui.enabled -}}
apiVersion: apps/v1
kind: Deployment
metadata:
name: {{ include "litellm.fullname" . }}-ui
labels:
{{- include "litellm.labels" . | nindent 4 }}
spec:
{{- if not .Values.ui.autoscaling.enabled }}
replicas: {{ .Values.ui.replicaCount }}
{{- end }}
selector:
matchLabels:
{{- include "litellm.ui.selectorLabels" . | nindent 6 }}
template:
metadata:
{{- with .Values.podAnnotations }}
annotations:
{{- toYaml . | nindent 8 }}
{{- end }}
labels:
{{- include "litellm.ui.labels" . | nindent 8 }}
{{- with .Values.ui.podLabels }}
{{- toYaml . | nindent 8 }}
{{- end }}
spec:
{{- with .Values.imagePullSecrets }}
imagePullSecrets:
{{- toYaml . | nindent 8 }}
{{- end }}
serviceAccountName: {{ include "litellm.serviceAccountName" . }}
securityContext:
{{- toYaml .Values.ui.podSecurityContext | nindent 8 }}
containers:
- name: {{ include "litellm.name" . }}-ui
securityContext:
{{- toYaml .Values.ui.securityContext | nindent 12 }}
image: "{{ .Values.ui.image.repository }}:{{ .Values.ui.image.tag | default (printf "main-%s" .Chart.AppVersion) }}"
imagePullPolicy: {{ .Values.ui.image.pullPolicy }}
env:
- name: BASE_URL
value: {{ (index .Values.ui.ingress.hosts 0).host | default "example.com" }}
ports:
- name: http
containerPort: {{ .Values.ui.service.port }}
protocol: TCP
livenessProbe:
httpGet:
path: /
port: http
readinessProbe:
httpGet:
path: /
port: http
# Give the container time to start up. Up to 5 minutes (10 * 30 seconds)
startupProbe:
httpGet:
path: /
port: http
failureThreshold: 30
periodSeconds: 10
resources:
{{- toYaml .Values.ui.resources | nindent 12 }}
volumeMounts:
- name: tmp
mountPath: /tmp
{{- with .Values.ui.volumeMounts }}
{{- toYaml . | nindent 12 }}
{{- end }}
volumes:
- name: tmp
emptyDir:
sizeLimit: 500Mi
{{- with .Values.ui.volumes }}
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.ui.nodeSelector }}
nodeSelector:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.ui.affinity }}
affinity:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.ui.tolerations }}
tolerations:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- end -}}

View file

@ -0,0 +1,32 @@
{{- if .Values.autoscaling.enabled }}
apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
name: {{ include "litellm.fullname" . }}
labels:
{{- include "litellm.labels" . | nindent 4 }}
spec:
scaleTargetRef:
apiVersion: apps/v1
kind: Deployment
name: {{ include "litellm.fullname" . }}
minReplicas: {{ .Values.autoscaling.minReplicas }}
maxReplicas: {{ .Values.autoscaling.maxReplicas }}
metrics:
{{- if .Values.autoscaling.targetCPUUtilizationPercentage }}
- type: Resource
resource:
name: cpu
target:
type: Utilization
averageUtilization: {{ .Values.autoscaling.targetCPUUtilizationPercentage }}
{{- end }}
{{- if .Values.autoscaling.targetMemoryUtilizationPercentage }}
- type: Resource
resource:
name: memory
target:
type: Utilization
averageUtilization: {{ .Values.autoscaling.targetMemoryUtilizationPercentage }}
{{- end }}
{{- end }}

View file

@ -0,0 +1,61 @@
{{- if .Values.ingress.enabled -}}
{{- $fullName := (printf "%s%s" (include "litellm.fullname" .) "-proxy") -}}
{{- $svcPort := .Values.service.port -}}
{{- if and .Values.ingress.className (not (semverCompare ">=1.18-0" .Capabilities.KubeVersion.GitVersion)) }}
{{- if not (hasKey .Values.ingress.annotations "kubernetes.io/ingress.class") }}
{{- $_ := set .Values.ingress.annotations "kubernetes.io/ingress.class" .Values.ingress.className}}
{{- end }}
{{- end }}
{{- if semverCompare ">=1.19-0" .Capabilities.KubeVersion.GitVersion -}}
apiVersion: networking.k8s.io/v1
{{- else if semverCompare ">=1.14-0" .Capabilities.KubeVersion.GitVersion -}}
apiVersion: networking.k8s.io/v1beta1
{{- else -}}
apiVersion: extensions/v1beta1
{{- end }}
kind: Ingress
metadata:
name: {{ $fullName }}
labels:
{{- include "litellm.labels" . | nindent 4 }}
{{- with .Values.ingress.annotations }}
annotations:
{{- toYaml . | nindent 4 }}
{{- end }}
spec:
{{- if and .Values.ingress.className (semverCompare ">=1.18-0" .Capabilities.KubeVersion.GitVersion) }}
ingressClassName: {{ .Values.ingress.className }}
{{- end }}
{{- if .Values.ingress.tls }}
tls:
{{- range .Values.ingress.tls }}
- hosts:
{{- range .hosts }}
- {{ . | quote }}
{{- end }}
secretName: {{ .secretName }}
{{- end }}
{{- end }}
rules:
{{- range .Values.ingress.hosts }}
- host: {{ .host | quote }}
http:
paths:
{{- range .paths }}
- path: {{ .path }}
{{- if and .pathType (semverCompare ">=1.18-0" $.Capabilities.KubeVersion.GitVersion) }}
pathType: {{ .pathType }}
{{- end }}
backend:
{{- if semverCompare ">=1.19-0" $.Capabilities.KubeVersion.GitVersion }}
service:
name: {{ $fullName }}
port:
number: {{ $svcPort }}
{{- else }}
serviceName: {{ $fullName }}
servicePort: {{ $svcPort }}
{{- end }}
{{- end }}
{{- end }}
{{- end }}

View file

@ -0,0 +1,61 @@
{{- if .Values.ui.ingress.enabled -}}
{{- $fullName := (printf "%s%s" (include "litellm.fullname" .) "-ui") -}}
{{- $svcPort := .Values.ui.service.port -}}
{{- if and .Values.ui.ingress.className (not (semverCompare ">=1.18-0" .Capabilities.KubeVersion.GitVersion)) }}
{{- if not (hasKey .Values.ui.ingress.annotations "kubernetes.io/ingress.class") }}
{{- $_ := set .Values.ui.ingress.annotations "kubernetes.io/ingress.class" .Values.ui.ingress.className}}
{{- end }}
{{- end }}
{{- if semverCompare ">=1.19-0" .Capabilities.KubeVersion.GitVersion -}}
apiVersion: networking.k8s.io/v1
{{- else if semverCompare ">=1.14-0" .Capabilities.KubeVersion.GitVersion -}}
apiVersion: networking.k8s.io/v1beta1
{{- else -}}
apiVersion: extensions/v1beta1
{{- end }}
kind: Ingress
metadata:
name: {{ $fullName }}
labels:
{{- include "litellm.ui.labels" . | nindent 4 }}
{{- with .Values.ui.ingress.annotations }}
annotations:
{{- toYaml . | nindent 4 }}
{{- end }}
spec:
{{- if and .Values.ui.ingress.className (semverCompare ">=1.18-0" .Capabilities.KubeVersion.GitVersion) }}
ingressClassName: {{ .Values.ui.ingress.className }}
{{- end }}
{{- if .Values.ui.ingress.tls }}
tls:
{{- range .Values.ui.ingress.tls }}
- hosts:
{{- range .hosts }}
- {{ . | quote }}
{{- end }}
secretName: {{ .secretName }}
{{- end }}
{{- end }}
rules:
{{- range .Values.ui.ingress.hosts }}
- host: {{ .host | quote }}
http:
paths:
{{- range .paths }}
- path: {{ .path }}
{{- if and .pathType (semverCompare ">=1.18-0" $.Capabilities.KubeVersion.GitVersion) }}
pathType: {{ .pathType }}
{{- end }}
backend:
{{- if semverCompare ">=1.19-0" $.Capabilities.KubeVersion.GitVersion }}
service:
name: {{ $fullName }}
port:
number: {{ $svcPort }}
{{- else }}
serviceName: {{ $fullName }}
servicePort: {{ $svcPort }}
{{- end }}
{{- end }}
{{- end }}
{{- end }}

View file

@ -0,0 +1,12 @@
{{- if .Values.db.deployStandalone -}}
apiVersion: v1
kind: Secret
metadata:
name: {{ include "litellm.name" . }}-dbcredentials
data:
# Password for the "postgres" user
postgres-password: {{ ( index .Values.postgresql.auth "postgres-password") | default "litellm" | b64enc }}
username: {{ .Values.postgresql.auth.username | default "litellm" | b64enc }}
password: {{ .Values.postgresql.auth.password | default "litellm" | b64enc }}
type: Opaque
{{- end -}}

View file

@ -0,0 +1,8 @@
{{ $masterkey := (.Values.masterkey | default (randAlphaNum 17)) }}
apiVersion: v1
kind: Secret
metadata:
name: {{ include "litellm.name" . }}-masterkey
data:
masterkey: {{ $masterkey | b64enc }}
type: Opaque

View file

@ -0,0 +1,15 @@
apiVersion: v1
kind: Service
metadata:
name: {{ include "litellm.fullname" . }}-proxy
labels:
{{- include "litellm.labels" . | nindent 4 }}
spec:
type: {{ .Values.service.type }}
ports:
- port: {{ .Values.service.port }}
targetPort: http
protocol: TCP
name: http
selector:
{{- include "litellm.selectorLabels" . | nindent 4 }}

View file

@ -0,0 +1,17 @@
{{- if .Values.ui.enabled -}}
apiVersion: v1
kind: Service
metadata:
name: {{ include "litellm.fullname" . }}-ui
labels:
{{- include "litellm.labels" . | nindent 4 }}
spec:
type: {{ .Values.ui.service.type }}
ports:
- port: {{ .Values.ui.service.port }}
targetPort: http
protocol: TCP
name: http
selector:
{{- include "litellm.ui.selectorLabels" . | nindent 4 }}
{{ end -}}

View file

@ -0,0 +1,13 @@
{{- if .Values.serviceAccount.create -}}
apiVersion: v1
kind: ServiceAccount
metadata:
name: {{ include "litellm.serviceAccountName" . }}
labels:
{{- include "litellm.labels" . | nindent 4 }}
{{- with .Values.serviceAccount.annotations }}
annotations:
{{- toYaml . | nindent 4 }}
{{- end }}
automountServiceAccountToken: {{ .Values.serviceAccount.automount }}
{{- end }}

View file

@ -0,0 +1,15 @@
apiVersion: v1
kind: Pod
metadata:
name: "{{ include "litellm.fullname" . }}-test-connection"
labels:
{{- include "litellm.labels" . | nindent 4 }}
annotations:
"helm.sh/hook": test
spec:
containers:
- name: wget
image: busybox
command: ['wget']
args: ['{{ include "litellm.fullname" . }}:{{ .Values.service.port }}']
restartPolicy: Never

View file

@ -0,0 +1,219 @@
# Default values for litellm.
# This is a YAML-formatted file.
# Declare variables to be passed into your templates.
replicaCount: 1
image:
repository: ghcr.io/berriai/litellm
pullPolicy: IfNotPresent
# Overrides the image tag whose default is the chart appVersion.
# tag: "main-latest"
tag: ""
# Image and tag used for the init container to check and wait for the
# readiness of the postgres database.
dbReadyImage: docker.io/bitnami/postgresql
dbReadyTag: ""
imagePullSecrets: []
nameOverride: "litellm"
fullnameOverride: ""
serviceAccount:
# Specifies whether a service account should be created
create: false
# Automatically mount a ServiceAccount's API credentials?
automount: true
# Annotations to add to the service account
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: ""
podAnnotations: {}
podLabels: {}
# At the time of writing, the litellm docker image requires write access to the
# filesystem on startup so that prisma can install some dependencies.
podSecurityContext: {}
securityContext: {}
# capabilities:
# drop:
# - ALL
# readOnlyRootFilesystem: false
# runAsNonRoot: true
# runAsUser: 1000
# A list of Kubernetes Secret objects that will be exported to the LiteLLM proxy
# pod as environment variables. These secrets can then be referenced in the
# configuration file (or "litellm" ConfigMap) with `os.environ/<Env Var Name>`
environmentSecrets: []
# - litellm-envsecrets
service:
type: ClusterIP
port: 8000
ingress:
enabled: true
className: "nginx"
annotations: {}
# kubernetes.io/ingress.class: nginx
# kubernetes.io/tls-acme: "true"
hosts:
- host: api.example.local
paths:
- path: /
pathType: ImplementationSpecific
tls: []
# - secretName: chart-example-tls
# hosts:
# - chart-example.local
# The elements within proxy_config are rendered as config.yaml for the proxy
# Examples: https://github.com/BerriAI/litellm/tree/main/litellm/proxy/example_config_yaml
# Reference: https://docs.litellm.ai/docs/proxy/configs
proxy_config:
model_list:
# At least one model must exist for the proxy to start.
- model_name: gpt-3.5-turbo
litellm_params:
model: gpt-3.5-turbo
api_key: eXaMpLeOnLy
general_settings:
master_key: os.environ/PROXY_MASTER_KEY
resources: {}
# We usually recommend not to specify default resources and to leave this as a conscious
# choice for the user. This also increases chances charts run on environments with little
# resources, such as Minikube. If you do want to specify resources, uncomment the following
# lines, adjust them as necessary, and remove the curly braces after 'resources:'.
# limits:
# cpu: 100m
# memory: 128Mi
# requests:
# cpu: 100m
# memory: 128Mi
autoscaling:
enabled: false
minReplicas: 1
maxReplicas: 100
targetCPUUtilizationPercentage: 80
# targetMemoryUtilizationPercentage: 80
# Additional volumes on the output Deployment definition.
volumes: []
# - name: foo
# secret:
# secretName: mysecret
# optional: false
# Additional volumeMounts on the output Deployment definition.
volumeMounts: []
# - name: foo
# mountPath: "/etc/foo"
# readOnly: true
nodeSelector: {}
tolerations: []
affinity: {}
db:
# Use an existing postgres server/cluster
useExisting: false
# How to connect to the existing postgres server/cluster
endpoint: localhost
database: litellm
secret:
name: postgres
usernameKey: username
passwordKey: password
# Use the Stackgres Helm chart to deploy an instance of a Stackgres cluster.
# The Stackgres Operator must already be installed within the target
# Kubernetes cluster.
# TODO: Stackgres deployment currently unsupported
useStackgresOperator: false
# Use the Postgres Helm chart to create a single node, stand alone postgres
# instance. See the "postgresql" top level key for additional configuration.
deployStandalone: true
# Settings for Bitnami postgresql chart (if db.deployStandalone is true, ignored
# otherwise)
postgresql:
architecture: standalone
auth:
username: litellm
database: litellm
# You should override these on the helm command line with
# `--set postgresql.auth.postgres-password=<some good password>,postgresql.auth.password=<some good password>`
password: NoTaGrEaTpAsSwOrD
postgres-password: NoTaGrEaTpAsSwOrD
# A secret is created by this chart (litellm-helm) with the credentials that
# the new Postgres instance should use.
existingSecret: litellm-dbcredentials
secretKeys:
userPasswordKey: password
ui:
enabled: true
replicaCount: 1
autoscaling:
enabled: false
image:
repository: ghcr.io/berriai/litellm-ui
pullPolicy: IfNotPresent
# Overrides the image tag whose default is the chart appVersion.
# tag: "main-latest"
# TODO: Switch to BerryAI repo and tags if/when they provide a ui image
# https://github.com/BerriAI/litellm/pull/1505
tag: ""
service:
type: ClusterIP
port: 8501
ingress:
enabled: true
className: "nginx"
annotations: {}
hosts:
- host: ui.example.local
paths:
- path: /
pathType: ImplementationSpecific
tls: []
podAnnotations: {}
podLabels: {}
podSecurityContext:
fsGroup: 1000
securityContext:
capabilities:
drop:
- ALL
readOnlyRootFilesystem: true
runAsNonRoot: true
runAsUser: 1000
resources: {}
volumes: []
volumeMounts: []
nodeSelector: {}
tolerations: []
affinity: {}