first cut at redis (#2226)

* first cut at redis

* fix startup dependencies on redis

* kombu cleanup - fail silently

* mypy

* add redis_host environment override

* update REDIS_HOST env var in docker-compose.dev.yml

* update the rest of the docker files

* update contributing guide

* renaming cache to cache_volume

* add redis password to various deployments

* try setting up pr testing for helm

* fix indent

* hopefully this release version actually exists

* fix command line option to --chart-dirs

* fetch-depth 0

* edit values.yaml

* try setting ct working directory

* bypass testing only on change for now

* move files and lint them

* update helm testing

* some issues suggest using --config works

* add vespa repo

* add postgresql repo

* increase timeout

* try amd64 runner

* fix redis password reference

* add comment to helm chart testing workflow

* rename helm testing workflow to disable it

---------

Co-authored-by: Richard Kuo <rkuo@rkuo.com>
This commit is contained in:
rkuo-danswer
2024-09-06 12:21:29 -07:00
committed by GitHub
parent aeb6060854
commit 2933c3598b
43 changed files with 268 additions and 23 deletions

View File

@@ -0,0 +1,3 @@
### Helm ###
# Chart dependencies
**/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 +1,12 @@
dependencies:
- name: postgresql
repository: https://charts.bitnami.com/bitnami
version: 14.3.1
- name: vespa
repository: https://unoplat.github.io/vespa-helm-charts
version: 0.2.3
- name: nginx
repository: oci://registry-1.docker.io/bitnamicharts
version: 15.14.0
digest: sha256:ab17b5d2c3883055cb4a26bf530043521be5220c24f804e954bb428273d16ba8
generated: "2024-05-24T16:55:30.598279-07:00"

View File

@@ -0,0 +1,32 @@
apiVersion: v2
name: danswer-stack
description: A Helm chart for Kubernetes
home: https://www.danswer.ai/
sources:
- "https://github.com/danswer-ai/danswer"
type: application
version: 0.2.0
appVersion: "latest"
annotations:
category: Productivity
licenses: MIT
images: |
- name: webserver
image: docker.io/danswer/danswer-web-server:latest
- name: background
image: docker.io/danswer/danswer-backend:latest
- name: vespa
image: vespaengine/vespa:8.277.17
dependencies:
- name: postgresql
version: 14.3.1
repository: https://charts.bitnami.com/bitnami
condition: postgresql.enabled
- name: vespa
version: 0.2.3
repository: https://unoplat.github.io/vespa-helm-charts
condition: vespa.enabled
- name: nginx
version: 15.14.0
repository: oci://registry-1.docker.io/bitnamicharts
condition: nginx.enabled

View File

@@ -0,0 +1,83 @@
{{/*
Expand the name of the chart.
*/}}
{{- define "danswer-stack.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 "danswer-stack.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 "danswer-stack.chart" -}}
{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
{{- end }}
{{/*
Common labels
*/}}
{{- define "danswer-stack.labels" -}}
helm.sh/chart: {{ include "danswer-stack.chart" . }}
{{ include "danswer-stack.selectorLabels" . }}
{{- if .Chart.AppVersion }}
app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
{{- end }}
app.kubernetes.io/managed-by: {{ .Release.Service }}
{{- end }}
{{/*
Selector labels
*/}}
{{- define "danswer-stack.selectorLabels" -}}
app.kubernetes.io/name: {{ include "danswer-stack.name" . }}
app.kubernetes.io/instance: {{ .Release.Name }}
{{- end }}
{{/*
Create the name of the service account to use
*/}}
{{- define "danswer-stack.serviceAccountName" -}}
{{- if .Values.serviceAccount.create }}
{{- default (include "danswer-stack.fullname" .) .Values.serviceAccount.name }}
{{- else }}
{{- default "default" .Values.serviceAccount.name }}
{{- end }}
{{- end }}
{{/*
Set secret name
*/}}
{{- define "danswer-stack.secretName" -}}
{{- default (default "danswer-secrets" .Values.auth.secretName) .Values.auth.existingSecret }}
{{- end }}
{{/*
Create env vars from secrets
*/}}
{{- define "danswer-stack.envSecrets" -}}
{{- range $name, $key := .Values.auth.secretKeys }}
- name: {{ $name | upper | replace "-" "_" | quote }}
valueFrom:
secretKeyRef:
name: {{ include "danswer-stack.secretName" $ }}
key: {{ default $name $key }}
{{- end }}
{{- end }}

View File

@@ -0,0 +1,59 @@
apiVersion: apps/v1
kind: Deployment
metadata:
name: {{ include "danswer-stack.fullname" . }}-api-deployment
labels:
{{- include "danswer-stack.labels" . | nindent 4 }}
spec:
{{- if not .Values.api.autoscaling.enabled }}
replicas: {{ .Values.api.replicaCount }}
{{- end }}
selector:
matchLabels:
{{- include "danswer-stack.selectorLabels" . | nindent 6 }}
{{- if .Values.api.deploymentLabels }}
{{- toYaml .Values.api.deploymentLabels | nindent 6 }}
{{- end }}
template:
metadata:
{{- with .Values.api.podAnnotations }}
annotations:
{{- toYaml . | nindent 8 }}
{{- end }}
labels:
{{- include "danswer-stack.labels" . | nindent 8 }}
{{- with .Values.api.podLabels }}
{{- toYaml . | nindent 8 }}
{{- end }}
spec:
{{- with .Values.imagePullSecrets }}
imagePullSecrets:
{{- toYaml . | nindent 8 }}
{{- end }}
serviceAccountName: {{ include "danswer-stack.serviceAccountName" . }}
securityContext:
{{- toYaml .Values.api.podSecurityContext | nindent 8 }}
containers:
- name: api-server
securityContext:
{{- toYaml .Values.api.securityContext | nindent 12 }}
image: "{{ .Values.api.image.repository }}:{{ .Values.api.image.tag | default .Chart.AppVersion }}"
imagePullPolicy: {{ .Values.api.image.pullPolicy }}
command:
- "/bin/sh"
- "-c"
- |
alembic upgrade head &&
echo "Starting Danswer Api Server" &&
uvicorn danswer.main:app --host 0.0.0.0 --port 8080
ports:
- name: api-server-port
containerPort: {{ .Values.api.service.port }}
protocol: TCP
resources:
{{- toYaml .Values.api.resources | nindent 12 }}
envFrom:
- configMapRef:
name: {{ .Values.config.envConfigMapName }}
env:
{{- include "danswer-stack.envSecrets" . | nindent 12}}

View File

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

View File

@@ -0,0 +1,22 @@
apiVersion: v1
kind: Service
metadata:
# INTERNAL_URL env variable depends on this, don't change without changing INTERNAL_URL
name: {{ include "danswer-stack.fullname" . }}-api-service
labels:
{{- include "danswer-stack.labels" . | nindent 4 }}
{{- if .Values.api.deploymentLabels }}
{{- toYaml .Values.api.deploymentLabels | nindent 4 }}
{{- end }}
spec:
type: {{ .Values.api.service.type }}
ports:
- port: {{ .Values.api.service.port }}
targetPort: api-server-port
protocol: TCP
name: api-server-port
selector:
{{- include "danswer-stack.selectorLabels" . | nindent 4 }}
{{- if .Values.api.deploymentLabels }}
{{- toYaml .Values.api.deploymentLabels | nindent 4 }}
{{- end }}

View File

@@ -0,0 +1,51 @@
apiVersion: apps/v1
kind: Deployment
metadata:
name: {{ include "danswer-stack.fullname" . }}-background
labels:
{{- include "danswer-stack.labels" . | nindent 4 }}
spec:
{{- if not .Values.background.autoscaling.enabled }}
replicas: {{ .Values.background.replicaCount }}
{{- end }}
selector:
matchLabels:
{{- include "danswer-stack.selectorLabels" . | nindent 6 }}
{{- if .Values.background.deploymentLabels }}
{{- toYaml .Values.background.deploymentLabels | nindent 6 }}
{{- end }}
template:
metadata:
{{- with .Values.background.podAnnotations }}
annotations:
{{- toYaml . | nindent 8 }}
{{- end }}
labels:
{{- include "danswer-stack.labels" . | nindent 8 }}
{{- with .Values.background.podLabels }}
{{- toYaml . | nindent 8 }}
{{- end }}
spec:
{{- with .Values.imagePullSecrets }}
imagePullSecrets:
{{- toYaml . | nindent 8 }}
{{- end }}
serviceAccountName: {{ include "danswer-stack.serviceAccountName" . }}
securityContext:
{{- toYaml .Values.background.podSecurityContext | nindent 8 }}
containers:
- name: background
securityContext:
{{- toYaml .Values.background.securityContext | nindent 12 }}
image: "{{ .Values.background.image.repository }}:{{ .Values.background.image.tag | default .Chart.AppVersion }}"
imagePullPolicy: {{ .Values.background.image.pullPolicy }}
command: ["/usr/bin/supervisord"]
resources:
{{- toYaml .Values.background.resources | nindent 12 }}
envFrom:
- configMapRef:
name: {{ .Values.config.envConfigMapName }}
env:
- name: ENABLE_MULTIPASS_INDEXING
value: "{{ .Values.background.enableMiniChunk }}"
{{- include "danswer-stack.envSecrets" . | nindent 12}}

View File

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

View File

@@ -0,0 +1,15 @@
apiVersion: v1
kind: ConfigMap
metadata:
name: {{ .Values.config.envConfigMapName }}
labels:
{{- include "danswer-stack.labels" . | nindent 4 }}
data:
INTERNAL_URL: "http://{{ include "danswer-stack.fullname" . }}-api-service:{{ .Values.api.service.port | default 8080 }}"
POSTGRES_HOST: {{ .Release.Name }}-postgresql
VESPA_HOST: "document-index-service"
MODEL_SERVER_HOST: "{{ include "danswer-stack.fullname" . }}-inference-model-service"
INDEXING_MODEL_SERVER_HOST: "{{ include "danswer-stack.fullname" . }}-indexing-model-service"
{{- range $key, $value := .Values.configMap }}
{{ $key }}: "{{ $value }}"
{{- end }}

View File

@@ -0,0 +1,11 @@
{{- if not .Values.auth.existingSecret -}}
apiVersion: v1
kind: Secret
metadata:
name: {{ include "danswer-stack.secretName" . }}
type: Opaque
stringData:
{{- range $name, $value := .Values.auth.secrets }}
{{ $name }}: {{ $value | quote }}
{{- end }}
{{- end }}

View File

@@ -0,0 +1,51 @@
apiVersion: apps/v1
kind: Deployment
metadata:
name: {{ include "danswer-stack.fullname" . }}-indexing-model
labels:
{{- include "danswer-stack.labels" . | nindent 4 }}
spec:
replicas: 1
selector:
matchLabels:
{{- include "danswer-stack.selectorLabels" . | nindent 6 }}
{{- if .Values.indexCapability.deploymentLabels }}
{{- toYaml .Values.indexCapability.deploymentLabels | nindent 6 }}
{{- end }}
template:
metadata:
{{- with .Values.indexCapability.podAnnotations }}
annotations:
{{- toYaml . | nindent 8 }}
{{- end }}
labels:
{{- include "danswer-stack.labels" . | nindent 8 }}
{{- with .Values.indexCapability.podLabels }}
{{- toYaml . | nindent 8 }}
{{- end }}
spec:
containers:
- name: indexing-model-server
image: danswer/danswer-model-server:latest
imagePullPolicy: IfNotPresent
command: [ "uvicorn", "model_server.main:app", "--host", "0.0.0.0", "--port", "9000", "--limit-concurrency", "10" ]
ports:
- containerPort: 9000
envFrom:
- configMapRef:
name: {{ .Values.config.envConfigMapName }}
env:
- name: INDEXING_ONLY
value: "{{ default "True" .Values.indexCapability.indexingOnly }}"
{{- include "danswer-stack.envSecrets" . | nindent 10}}
volumeMounts:
{{- range .Values.indexCapability.volumeMounts }}
- name: {{ .name }}
mountPath: {{ .mountPath }}
{{- end }}
volumes:
{{- range .Values.indexCapability.volumes }}
- name: {{ .name }}
persistentVolumeClaim:
claimName: {{ .persistentVolumeClaim.claimName }}
{{- end }}

View File

@@ -0,0 +1,10 @@
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: {{ .Values.indexCapability.indexingModelPVC.name }}
spec:
accessModes:
- {{ .Values.indexCapability.indexingModelPVC.accessMode | quote }}
resources:
requests:
storage: {{ .Values.indexCapability.indexingModelPVC.storage | quote }}

View File

@@ -0,0 +1,18 @@
apiVersion: v1
kind: Service
metadata:
name: {{ include "danswer-stack.fullname" . }}-indexing-model-service
labels:
{{- include "danswer-stack.labels" . | nindent 4 }}
spec:
selector:
{{- include "danswer-stack.selectorLabels" . | nindent 4 }}
{{- if .Values.indexCapability.deploymentLabels }}
{{- toYaml .Values.indexCapability.deploymentLabels | nindent 4 }}
{{- end }}
ports:
- name: {{ .Values.indexCapability.service.name }}
protocol: TCP
port: {{ .Values.indexCapability.service.port }}
targetPort: {{ .Values.indexCapability.service.port }}
type: {{ .Values.indexCapability.service.type }}

View File

@@ -0,0 +1,45 @@
apiVersion: apps/v1
kind: Deployment
metadata:
name: {{ include "danswer-stack.fullname" . }}-inference-model
labels:
{{- range .Values.inferenceCapability.deployment.labels }}
{{ .key }}: {{ .value }}
{{- end }}
spec:
replicas: {{ .Values.inferenceCapability.deployment.replicas }}
selector:
matchLabels:
{{- range .Values.inferenceCapability.deployment.labels }}
{{ .key }}: {{ .value }}
{{- end }}
template:
metadata:
labels:
{{- range .Values.inferenceCapability.podLabels }}
{{ .key }}: {{ .value }}
{{- end }}
spec:
containers:
- name: {{ .Values.inferenceCapability.service.name }}
image: {{ .Values.inferenceCapability.deployment.image.repository }}:{{ .Values.inferenceCapability.deployment.image.tag }}
imagePullPolicy: {{ .Values.inferenceCapability.deployment.image.pullPolicy }}
command: {{ toYaml .Values.inferenceCapability.deployment.command | nindent 14 }}
ports:
- containerPort: {{ .Values.inferenceCapability.service.port }}
envFrom:
- configMapRef:
name: {{ .Values.config.envConfigMapName }}
env:
{{- include "danswer-stack.envSecrets" . | nindent 12}}
volumeMounts:
{{- range .Values.inferenceCapability.deployment.volumeMounts }}
- name: {{ .name }}
mountPath: {{ .mountPath }}
{{- end }}
volumes:
{{- range .Values.inferenceCapability.deployment.volumes }}
- name: {{ .name }}
persistentVolumeClaim:
claimName: {{ .persistentVolumeClaim.claimName }}
{{- end }}

View File

@@ -0,0 +1,10 @@
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: {{ .Values.inferenceCapability.pvc.name }}
spec:
accessModes:
{{- toYaml .Values.inferenceCapability.pvc.accessModes | nindent 4 }}
resources:
requests:
storage: {{ .Values.inferenceCapability.pvc.storage }}

View File

@@ -0,0 +1,15 @@
apiVersion: v1
kind: Service
metadata:
name: {{ include "danswer-stack.fullname" . }}-inference-model-service
spec:
type: {{ .Values.inferenceCapability.service.type }}
ports:
- port: {{ .Values.inferenceCapability.service.port }}
targetPort: {{ .Values.inferenceCapability.service.port }}
protocol: TCP
name: {{ .Values.inferenceCapability.service.name }}
selector:
{{- range .Values.inferenceCapability.deployment.labels }}
{{ .key }}: {{ .value }}
{{- end }}

View File

@@ -0,0 +1,44 @@
apiVersion: v1
kind: ConfigMap
metadata:
name: danswer-nginx-conf
data:
nginx.conf: |
upstream api_server {
server {{ include "danswer-stack.fullname" . }}-api-service:{{ .Values.api.service.port }} fail_timeout=0;
}
upstream web_server {
server {{ include "danswer-stack.fullname" . }}-webserver:{{ .Values.webserver.service.port }} fail_timeout=0;
}
server {
listen 1024;
server_name $$DOMAIN;
client_max_body_size 5G; # Maximum upload size
location ~ ^/api(.*)$ {
rewrite ^/api(/.*)$ $1 break;
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;
proxy_set_header X-Forwarded-Host $host;
proxy_set_header Host $host;
proxy_http_version 1.1;
proxy_buffering off;
proxy_redirect off;
proxy_pass http://api_server;
}
location / {
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;
proxy_set_header X-Forwarded-Host $host;
proxy_set_header Host $host;
proxy_http_version 1.1;
proxy_redirect off;
proxy_pass http://web_server;
}
}

View File

@@ -0,0 +1,13 @@
{{- if .Values.serviceAccount.create -}}
apiVersion: v1
kind: ServiceAccount
metadata:
name: {{ include "danswer-stack.serviceAccountName" . }}
labels:
{{- include "danswer-stack.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 "danswer-stack.fullname" . }}-test-connection"
labels:
{{- include "danswer-stack.labels" . | nindent 4 }}
annotations:
"helm.sh/hook": test
spec:
containers:
- name: wget
image: busybox
command: ['wget']
args: ['{{ include "danswer-stack.fullname" . }}:{{ .Values.webserver.service.port }}']
restartPolicy: Never

View File

@@ -0,0 +1,60 @@
apiVersion: apps/v1
kind: Deployment
metadata:
name: {{ include "danswer-stack.fullname" . }}-webserver
labels:
{{- include "danswer-stack.labels" . | nindent 4 }}
spec:
{{- if not .Values.webserver.autoscaling.enabled }}
replicas: {{ .Values.webserver.replicaCount }}
{{- end }}
selector:
matchLabels:
{{- include "danswer-stack.selectorLabels" . | nindent 6 }}
{{- if .Values.webserver.deploymentLabels }}
{{- toYaml .Values.webserver.deploymentLabels | nindent 6 }}
{{- end }}
template:
metadata:
{{- with .Values.webserver.podAnnotations }}
annotations:
{{- toYaml . | nindent 8 }}
{{- end }}
labels:
{{- include "danswer-stack.labels" . | nindent 8 }}
{{- with .Values.webserver.podLabels }}
{{- toYaml . | nindent 8 }}
{{- end }}
spec:
{{- with .Values.imagePullSecrets }}
imagePullSecrets:
{{- toYaml . | nindent 8 }}
{{- end }}
serviceAccountName: {{ include "danswer-stack.serviceAccountName" . }}
securityContext:
{{- toYaml .Values.webserver.podSecurityContext | nindent 8 }}
containers:
- name: web-server
securityContext:
{{- toYaml .Values.webserver.securityContext | nindent 12 }}
image: "{{ .Values.webserver.image.repository }}:{{ .Values.webserver.image.tag | default .Chart.AppVersion }}"
imagePullPolicy: {{ .Values.webserver.image.pullPolicy }}
ports:
- name: http
containerPort: {{ .Values.webserver.service.port }}
protocol: TCP
resources:
{{- toYaml .Values.webserver.resources | nindent 12 }}
envFrom:
- configMapRef:
name: {{ .Values.config.envConfigMapName }}
env:
{{- include "danswer-stack.envSecrets" . | nindent 12}}
{{- with .Values.webserver.volumeMounts }}
volumeMounts:
{{- toYaml . | nindent 12 }}
{{- end }}
{{- with .Values.webserver.volumes }}
volumes:
{{- toYaml . | nindent 8 }}
{{- end }}

View File

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

View File

@@ -0,0 +1,21 @@
apiVersion: v1
kind: Service
metadata:
name: {{ include "danswer-stack.fullname" . }}-webserver
labels:
{{- include "danswer-stack.labels" . | nindent 4 }}
{{- if .Values.webserver.deploymentLabels }}
{{- toYaml .Values.webserver.deploymentLabels | nindent 4 }}
{{- end }}
spec:
type: {{ .Values.webserver.service.type }}
ports:
- port: {{ .Values.webserver.service.port }}
targetPort: http
protocol: TCP
name: http
selector:
{{- include "danswer-stack.selectorLabels" . | nindent 4 }}
{{- if .Values.webserver.deploymentLabels }}
{{- toYaml .Values.webserver.deploymentLabels | nindent 4 }}
{{- end }}

View File

@@ -0,0 +1,452 @@
# Default values for danswer-stack.
# This is a YAML-formatted file.
# Declare variables to be passed into your templates.
imagePullSecrets: []
nameOverride: ""
fullnameOverride: ""
inferenceCapability:
service:
name: inference-model-server-service
type: ClusterIP
port: 9000
pvc:
name: inference-model-pvc
accessModes:
- ReadWriteOnce
storage: 3Gi
deployment:
name: inference-model-server-deployment
replicas: 1
labels:
- key: app
value: inference-model-server
image:
repository: danswer/danswer-model-server
tag: latest
pullPolicy: IfNotPresent
command: ["uvicorn", "model_server.main:app", "--host", "0.0.0.0", "--port", "9000"]
port: 9000
volumeMounts:
- name: inference-model-storage
mountPath: /root/.cache
volumes:
- name: inference-model-storage
persistentVolumeClaim:
claimName: inference-model-pvc
podLabels:
- key: app
value: inference-model-server
indexCapability:
service:
type: ClusterIP
port: 9000
name: indexing-model-server-port
deploymentLabels:
app: indexing-model-server
podLabels:
app: indexing-model-server
indexingOnly: "True"
podAnnotations: {}
volumeMounts:
- name: indexing-model-storage
mountPath: /root/.cache
volumes:
- name: indexing-model-storage
persistentVolumeClaim:
claimName: indexing-model-storage
indexingModelPVC:
name: indexing-model-storage
accessMode: "ReadWriteOnce"
storage: "3Gi"
config:
envConfigMapName: env-configmap
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: ""
postgresql:
primary:
persistence:
size: 5Gi
enabled: true
auth:
existingSecret: danswer-secrets
secretKeys:
adminPasswordKey: postgres_password # overwriting as postgres typically expects 'postgres-password'
nginx:
containerPorts:
http: 1024
extraEnvVars:
- name: DOMAIN
value: localhost
service:
ports:
http: 80
danswer: 3000
targetPort:
http: http
danswer: http
existingServerBlockConfigmap: danswer-nginx-conf
webserver:
replicaCount: 1
image:
repository: danswer/danswer-web-server
pullPolicy: IfNotPresent
# Overrides the image tag whose default is the chart appVersion.
tag: ""
deploymentLabels:
app: web-server
podAnnotations: {}
podLabels:
app: web-server
podSecurityContext: {}
# fsGroup: 2000
securityContext: {}
# capabilities:
# drop:
# - ALL
# readOnlyRootFilesystem: true
# runAsNonRoot: true
# runAsUser: 1000
service:
type: ClusterIP
port: 3000
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: {}
api:
replicaCount: 1
image:
repository: danswer/danswer-backend
pullPolicy: IfNotPresent
# Overrides the image tag whose default is the chart appVersion.
tag: ""
deploymentLabels:
app: api-server
podAnnotations: {}
podLabels:
scope: danswer-backend
app: api-server
podSecurityContext: {}
# fsGroup: 2000
securityContext: {}
# capabilities:
# drop:
# - ALL
# readOnlyRootFilesystem: true
# runAsNonRoot: true
# runAsUser: 1000
service:
type: ClusterIP
port: 8080
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:'.
# requests:
# cpu: 1000m # Requests 1 CPU core
# memory: 1Gi # Requests 1 GiB of memory
# limits:
# cpu: 2000m # Limits to 2 CPU cores
# memory: 2Gi # Limits to 2 GiB of memory
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: []
background:
replicaCount: 1
image:
repository: danswer/danswer-backend
pullPolicy: IfNotPresent
# Overrides the image tag whose default is the chart appVersion.
tag: latest
podAnnotations: {}
podLabels:
scope: danswer-backend
app: background
deploymentLabels:
app: background
podSecurityContext: {}
# fsGroup: 2000
securityContext: {}
# capabilities:
# drop:
# - ALL
# readOnlyRootFilesystem: true
# runAsNonRoot: true
# runAsUser: 1000
enableMiniChunk: "true"
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:'.
# requests:
# cpu: 1000m # Requests 1 CPU core
# memory: 1Gi # Requests 1 GiB of memory
# limits:
# cpu: 2000m # Limits to 2 CPU cores
# memory: 2Gi # Limits to 2 GiB of memory
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: []
vespa:
replicaCount: 1
image:
repository: vespa
pullPolicy: IfNotPresent
tag: "8.277.17"
podAnnotations: {}
podLabels:
app: vespa
app.kubernetes.io/instance: danswer
app.kubernetes.io/name: vespa
enabled: true
podSecurityContext: {}
# fsGroup: 2000
securityContext:
privileged: true
runAsUser: 0
# capabilities:
# drop:
# - ALL
# readOnlyRootFilesystem: true
# runAsNonRoot: true
# runAsUser: 1000
resources:
# The Vespa Helm chart specifies default resources, which are quite modest. We override
# them here to increase chances of the chart running successfully.
requests:
cpu: 1500m
memory: 4000Mi
limits:
cpu: 1500m
memory: 4000Mi
nodeSelector: {}
tolerations: []
affinity: {}
# ingress:
# enabled: false
# className: ""
# annotations: {}
# # kubernetes.io/ingress.class: nginx
# # kubernetes.io/tls-acme: "true"
# hosts:
# - host: chart-example.local
# paths:
# - path: /
# pathType: ImplementationSpecific
# tls: []
# # - secretName: chart-example-tls
# # hosts:
# # - chart-example.local
persistence:
vespa:
enabled: true
existingClaim: ""
storageClassName: ""
accessModes:
- ReadWriteOnce
size: 5Gi
auth:
# for storing smtp, oauth, slack, and other secrets
# keys are lowercased version of env vars (e.g. SMTP_USER -> smtp_user)
existingSecret: "" # danswer-secrets
# optionally override the secret keys to reference in the secret
# this is used to populate the env vars in individual deployments
# the values here reference the keys in secrets below
secretKeys:
postgres_password: "postgres_password"
smtp_pass: ""
oauth_client_id: ""
oauth_client_secret: ""
oauth_cookie_secret: ""
gen_ai_api_key: ""
danswer_bot_slack_app_token: ""
danswer_bot_slack_bot_token: ""
redis_password: "redis_password"
# will be overridden by the existingSecret if set
secretName: "danswer-secrets"
# set values as strings, they will be base64 encoded
# this is used to populate the secrets yaml
secrets:
postgres_password: "postgres"
smtp_pass: ""
oauth_client_id: ""
oauth_client_secret: ""
oauth_cookie_secret: ""
gen_ai_api_key: ""
danswer_bot_slack_app_token: ""
danswer_bot_slack_bot_token: ""
redis_password: "password"
configMap:
AUTH_TYPE: "disabled" # Change this for production uses unless Danswer is only accessible behind VPN
SESSION_EXPIRE_TIME_SECONDS: "86400" # 1 Day Default
VALID_EMAIL_DOMAINS: "" # Can be something like danswer.ai, as an extra double-check
SMTP_SERVER: "" # For sending verification emails, if unspecified then defaults to 'smtp.gmail.com'
SMTP_PORT: "" # For sending verification emails, if unspecified then defaults to '587'
SMTP_USER: "" # 'your-email@company.com'
# SMTP_PASS: "" # 'your-gmail-password'
EMAIL_FROM: "" # 'your-email@company.com' SMTP_USER missing used instead
# Gen AI Settings
GEN_AI_MAX_TOKENS: ""
QA_TIMEOUT: "60"
MAX_CHUNKS_FED_TO_CHAT: ""
DISABLE_LLM_DOC_RELEVANCE: ""
DISABLE_LLM_CHOOSE_SEARCH: ""
DISABLE_LLM_QUERY_REPHRASE: ""
# Query Options
DOC_TIME_DECAY: ""
HYBRID_ALPHA: ""
EDIT_KEYWORD_QUERY: ""
MULTILINGUAL_QUERY_EXPANSION: ""
LANGUAGE_HINT: ""
LANGUAGE_CHAT_NAMING_HINT: ""
QA_PROMPT_OVERRIDE: ""
# Internet Search Tool
BING_API_KEY: ""
# Don't change the NLP models unless you know what you're doing
DOCUMENT_ENCODER_MODEL: ""
NORMALIZE_EMBEDDINGS: ""
ASYM_QUERY_PREFIX: ""
ASYM_PASSAGE_PREFIX: ""
DISABLE_RERANK_FOR_STREAMING: ""
MODEL_SERVER_PORT: ""
MIN_THREADS_ML_MODELS: ""
# Indexing Configs
NUM_INDEXING_WORKERS: ""
DISABLE_INDEX_UPDATE_ON_SWAP: ""
DASK_JOB_CLIENT_ENABLED: ""
CONTINUE_ON_CONNECTOR_FAILURE: ""
EXPERIMENTAL_CHECKPOINTING_ENABLED: ""
CONFLUENCE_CONNECTOR_LABELS_TO_SKIP: ""
JIRA_API_VERSION: ""
GONG_CONNECTOR_START_TIME: ""
NOTION_CONNECTOR_ENABLE_RECURSIVE_PAGE_LOOKUP: ""
# DanswerBot SlackBot Configs
# DANSWER_BOT_SLACK_APP_TOKEN: ""
# DANSWER_BOT_SLACK_BOT_TOKEN: ""
DANSWER_BOT_DISABLE_DOCS_ONLY_ANSWER: ""
DANSWER_BOT_DISPLAY_ERROR_MSGS: ""
DANSWER_BOT_RESPOND_EVERY_CHANNEL: ""
DANSWER_BOT_DISABLE_COT: "" # Currently unused
NOTIFY_SLACKBOT_NO_ANSWER: ""
# Logging
# Optional Telemetry, please keep it on (nothing sensitive is collected)? <3
# https://docs.danswer.dev/more/telemetry
DISABLE_TELEMETRY: ""
LOG_LEVEL: ""
LOG_ALL_MODEL_INTERACTIONS: ""
LOG_DANSWER_MODEL_INTERACTIONS: ""
LOG_VESPA_TIMING_INFORMATION: ""
# Shared or Non-backend Related
WEB_DOMAIN: "http://localhost:3000" # for web server and api server
DOMAIN: "localhost" # for nginx