Copyright © 2022- basebox GmbH, all rights reserved.
Licensed to be used in conjunction with basebox, only.

RAGSRV-Support Configuration

Overview

Ragsrv-Support is a companion service for Ragsrv.

Helm Chart Configuration

Basic Settings

Parameter	Default	Description
replicaCount	1	Number of support service pod replicas
image.repository	gitea.basebox.health/basebox-distribution/ragsrv-support	Container image repository
image.pullPolicy	IfNotPresent	Image pull policy
image.tag	latest	Image tag
fullnameOverride	ragsrv-support	Override the full name of the deployment

Service Configuration

Parameter	Default	Description
service.type	ClusterIP	Kubernetes service type
service.port	8000	Service port

Health Checks

Parameter	Description
livenessProbe	Basic shell command probe (/bin/true)
readinessProbe	Basic shell command probe (/bin/true)

Environment Variables

Variable	Default	Description
API_KEY	Required	API key for authentication (should match RAGSRV)
HOST	0.0.0.0	Server host to bind to
SERVER_PORT	3001	Server port
LOG_LEVEL	trace	Logging level
API_KEY_HEADER	X-API-KEY	HTTP header name for API key
LOG_HEALTH_CHECKS	false	Log health check requests

OAuth Configuration (Optional)

Variable	Description
REQUIRE_AUTH	Enable/disable authentication
OAUTH_IDP_URL	OAuth Identity Provider URL
OAUTH_IDP_AUD	OAuth audience claim
OAUTH_JWKS_URL	JWKS endpoint for token verification

Integration Variables

Variable	Description
SUPPORT_SERVICE_URL	Self-reference URL (for internal routing)
WEBHOOK_STATE_URL	Webhook URL for state updates
OWNER_NAMESPACE_UUID	Default namespace UUID
ALLOWED_IPS	Comma-separated list of allowed IPs

GraphQL Configuration

Variable	Default	Description
GRAPHQL_ALLOW_INTROSPECTION	true	Allow GraphQL introspection
GRAPHQL_GRAPHIQL	true	Enable GraphiQL interface

Storage Configuration

Model Cache Volume

For persistent model storage:

volumes:
  - name: models-cache
    persistentVolumeClaim:
      claimName: ragsrv-support-models

volumeMounts:
  - name: models-cache
    mountPath: /models

extraObjects:
  ragsrv-support-models:
    apiVersion: v1
    kind: PersistentVolumeClaim
    metadata:
      name: ragsrv-support-models
    spec:
      accessModes:
        - ReadWriteOnce
      resources:
        requests:
          storage: 20Gi

Configuration Examples

Production Configuration

# values-production.yaml
replicaCount: 2

image:
  repository: gitea.basebox.health/basebox-distribution/ragsrv-support
  tag: "v1.2.3"
  pullPolicy: IfNotPresent

service:
  type: ClusterIP
  port: 8000

resources:
  requests:
    cpu: 4000m
    memory: 16Gi
    nvidia.com/gpu: 1
  limits:
    cpu: 8000m
    memory: 32Gi
    nvidia.com/gpu: 1

livenessProbe:
  httpGet:
    path: /health
    port: http
  initialDelaySeconds: 90
  periodSeconds: 30
  failureThreshold: 3

readinessProbe:
  httpGet:
    path: /health
    port: http
  initialDelaySeconds: 60
  periodSeconds: 10
  failureThreshold: 5

volumes:
  - name: models-cache
    persistentVolumeClaim:
      claimName: ragsrv-support-models
  - name: ragsrv-tmp
    persistentVolumeClaim:
      claimName: nfs-shared

volumeMounts:
  - name: models-cache
    mountPath: /models
  - name: ragsrv-tmp
    mountPath: /tmp/ragsrv

nodeSelector:
  nvidia.com/gpu: "true"

env:
  API_KEY: "<must-match-ragsrv-api-key>"
  LOG_LEVEL: "info"
  HOST: "0.0.0.0"
  SERVER_PORT: "8000"
  REQUIRE_AUTH: "true"
  LOG_HEALTH_CHECKS: "false"
  API_KEY_HEADER: "X-API-KEY"
  GRAPHQL_ALLOW_INTROSPECTION: "false"
  GRAPHQL_GRAPHIQL: "false"

extraObjects:
  ragsrv-support-models:
    apiVersion: v1
    kind: PersistentVolumeClaim
    metadata:
      name: ragsrv-support-models
    spec:
      accessModes:
        - ReadWriteOnce
      storageClassName: fast-ssd
      resources:
        requests:
          storage: 50Gi

Installation

# Install ragsrv-support
helm install ragsrv-support oci://hub.basebox.ai/helm/ragsrv-support \
  --values values-production.yaml \
  --namespace basebox \
  --create-namespace

# Verify
kubectl get pods -n basebox -l app.kubernetes.io/name=ragsrv-support

Integration

RAGSRV-Support must be deployed alongside RAGSRV. Ensure the API_KEY matches between both services:

# ragsrv values
env:
  API_KEY: "same-secure-key"
  SUPPORT_SERVICE_URL: "http://ragsrv-support:8000"

# ragsrv-support values
env:
  API_KEY: "same-secure-key"