Helm Setup

deploy/helm/.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/

deploy/helm/Chart.yaml

@@ -0,0 +1,25 @@
+apiVersion: v2
+name: llamagpt
+description: A Helm chart for Kubernetes
+icon: https://i.imgur.com/LI59cui.png
+
+# 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: "1.0.1"

deploy/helm/templates/_helpers.tpl

@@ -0,0 +1,66 @@
+{{/*
+Expand the name of the chart.
+*/}}
+{{- define "llamagpt.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 "llamagpt.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 "llamagpt.chart" -}}
+{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Common labels
+*/}}
+{{- define "llamagpt.labels" -}}
+helm.sh/chart: {{ include "llamagpt.chart" . }}
+{{ include "llamagpt.selectorLabels" . }}
+{{- if .Chart.AppVersion }}
+app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
+{{- end }}
+app.kubernetes.io/managed-by: {{ .Release.Service }}
+{{- end }}
+
+{{/*
+Selector labels
+*/}}
+{{- define "llamagpt.selectorLabels" -}}
+app.kubernetes.io/name: {{ include "llamagpt.name" . }}
+app.kubernetes.io/instance: {{ .Release.Name }}
+{{- end }}
+
+{{/*
+Create the name of the service account to use
+*/}}
+{{- define "llamagpt.serviceAccountName" -}}
+{{- if .Values.serviceAccount.create }}
+{{- default (include "llamagpt.fullname" .) .Values.serviceAccount.name }}
+{{- else }}
+{{- default "default" .Values.serviceAccount.name }}
+{{- end }}
+{{- end }}
+
+{{- define "llamagpt.api.openAi.host" -}}
+{{- default (printf "%s-api:%v" (include "llamagpt.fullname" .) .Values.api.service.port) .Values.api.openAi.host }}
+{{- end }}

deploy/helm/templates/configmap.yaml

@@ -0,0 +1,16 @@
+---
+
+kind: ConfigMap
+apiVersion: v1
+metadata:
+ name: {{ template "llamagpt.fullname" . }}-configmap
+ labels:
+ {{- include "llamagpt.labels" . | nindent 4 }}
+data:
+ DEFAULT_MODEL: {{ .Values.api.defaultModel }}
+ OPENAI_API_HOST: http://{{ template "llamagpt.api.openAi.host" . }}
+ OPENAI_API_KEY: {{ .Values.api.openAi.key }}
+ WAIT_HOSTS: {{ template "llamagpt.api.openAi.host" . }}
+ WAIT_TIMEOUT: {{ quote .Values.api.openAi.waitTimeout }}
+
+---

deploy/helm/templates/deployment.yaml

@@ -0,0 +1,66 @@
+---
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+ labels:
+ service: {{ template "llamagpt.fullname" . }}-api
+ {{- include "llamagpt.labels" . | nindent 4 }}
+ name: {{ template "llamagpt.fullname" . }}-api
+spec:
+ replicas: {{ .Values.api.replicas }}
+ selector:
+ matchLabels:
+ service: {{ template "llamagpt.fullname" . }}-api
+ template:
+ metadata:
+ labels:
+ service: {{ template "llamagpt.fullname" . }}-api
+ {{- include "llamagpt.labels" . | nindent 4 }}
+ spec:
+ containers:
+ - name: {{ template "llamagpt.fullname" . }}-api
+ image: "{{ .Values.api.image.repository }}:{{ .Values.api.image.tag }}"
+ env:
+ - name: MODEL
+ valueFrom:
+ configMapKeyRef:
+ name: {{ template "llamagpt.fullname" . }}-configmap
+ key: DEFAULT_MODEL
+ resources:
+ requests:
+ memory: {{ .Values.api.resources.memory }}
+ restartPolicy: {{ .Values.api.restartPolicy }}
+
+---
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+ labels:
+ service: {{ template "llamagpt.fullname" . }}-ui
+ {{- include "llamagpt.labels" . | nindent 4 }}
+ name: {{ template "llamagpt.fullname" . }}-ui
+spec:
+ replicas: {{ .Values.ui.replicas }}
+ selector:
+ matchLabels:
+ service: {{ template "llamagpt.fullname" . }}-ui
+ template:
+ metadata:
+ labels:
+ service: {{ template "llamagpt.fullname" . }}-ui
+ {{- include "llamagpt.labels" . | nindent 4 }}
+ spec:
+ containers:
+ - name: {{ template "llamagpt.fullname" . }}-ui
+ image: "{{ .Values.ui.image.repository }}:{{ .Values.ui.image.tag }}"
+ envFrom:
+ - configMapRef:
+ name: {{ template "llamagpt.fullname" . }}-configmap
+ ports:
+ - containerPort: {{ int .Values.ui.service.internalPort }}
+ resources: {}
+ restartPolicy: {{ .Values.ui.restartPolicy }}
+
+---

deploy/helm/templates/service.yaml

@@ -0,0 +1,40 @@
+---
+
+apiVersion: v1
+kind: Service
+metadata:
+ labels:
+ service: {{ template "llamagpt.fullname" . }}
+ {{- include "llamagpt.labels" . | nindent 4 }}
+ name: {{ template "llamagpt.fullname" . }}-api
+spec:
+ ports:
+ - name: api
+ port: {{ .Values.api.service.port }}
+ targetPort: {{ .Values.api.service.targetPort }}
+ selector:
+ service: {{ template "llamagpt.fullname" . }}-api
+status:
+ loadBalancer: {}
+
+---
+
+apiVersion: v1
+kind: Service
+metadata:
+ labels:
+ service: {{ template "llamagpt.fullname" . }}-ui
+ {{- include "llamagpt.labels" . | nindent 4 }}
+ name: {{ template "llamagpt.fullname" . }}-ui
+spec:
+ ports:
+ - name: ui
+ port: {{ .Values.ui.service.port }}
+ targetPort: {{ .Values.ui.service.targetPort }}
+ selector:
+ service: {{ template "llamagpt.fullname" . }}-ui
+ type: {{ .Values.ui.service.type }}
+status:
+ loadBalancer: {}
+
+---

deploy/helm/templates/tests/test-connection.yaml

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

deploy/helm/values.yaml

@@ -0,0 +1,37 @@
+# Default values for llamagpt.
+# This is a YAML-formatted file.
+# Declare variables to be passed into your templates.
+
+ui:
+ replicaCount: 1
+ service:
+ type: ClusterIP
+ port: 3000
+ targetPort: 3000
+ internalPort: 3000
+ image:
+ repository: ghcr.io/getumbrel/llama-gpt-ui
+ tag: 1.0.1
+ pullPolicy: IfNotPresent
+ affinity: {}
+ restartPolicy: Always
+
+api:
+ defaultModel: /models/llama-2-7b-chat.bin
+ replicaCount: 1
+ service:
+ type: ClusterIP
+ port: 8000
+ targetPort: 8000
+ image:
+ repository: ghcr.io/getumbrel/llama-gpt-api
+ tag: 1.0.1
+ pullPolicy: IfNotPresent
+ affinity: {}
+ restartPolicy: Always
+ resources:
+ memory: 5Gi
+ openAi:
+ host:
+ key: sk-XXXXXXXXXXXXXXXXXXXX
+ waitTimeout: 600