d22175310a
🚨 Severity: HIGH 💡 Vulnerability: User-provided IMAP `host` in `_test_imap_connection` and `pull_inbox` was not validated against private IPs, creating an SSRF risk. 🎯 Impact: Attackers could abuse the endpoints to port-scan or interact with internal/private network services. 🔧 Fix: Integrated `is_private_ip` from `app.utils.network` to block connections resolving to private, loopback, link-local, or reserved IPs. ✅ Verification: Ran `test_imap_tasks.py` and `test_api_imap_accounts.py` successfully. Checked `ruff` output and diffs. Removed all scratch files from the commit. Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>
307 lines
8.5 KiB
YAML
307 lines
8.5 KiB
YAML
# =============================================================================
|
|
# DocuElevate Helm Chart — values.yaml
|
|
#
|
|
# Override any value with:
|
|
# helm install docuelevate ./helm/docuelevate -f my-values.yaml
|
|
# helm install docuelevate ./helm/docuelevate --set key=value
|
|
# =============================================================================
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Global image settings
|
|
# ---------------------------------------------------------------------------
|
|
image:
|
|
repository: ghcr.io/christianlouis/docuelevate
|
|
# Defaults to the chart appVersion; pin to a specific digest in production.
|
|
tag: ""
|
|
pullPolicy: IfNotPresent
|
|
|
|
imagePullSecrets: []
|
|
|
|
nameOverride: ""
|
|
fullnameOverride: ""
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Shared environment — non-secret application config
|
|
# All values map 1-to-1 onto DocuElevate environment variables.
|
|
# Sensitive values (API keys, passwords) go into `secrets` below.
|
|
# ---------------------------------------------------------------------------
|
|
env:
|
|
# Required ----------------------------------------------------------------
|
|
WORKDIR: /workdir
|
|
|
|
# AI provider (openai | azure | anthropic | gemini | ollama | openrouter)
|
|
AI_PROVIDER: openai
|
|
OPENAI_MODEL: gpt-4o-mini
|
|
|
|
# Azure Document Intelligence (required when OCR_PROVIDERS includes "azure")
|
|
AZURE_REGION: eastus
|
|
AZURE_ENDPOINT: "" # e.g. https://my-resource.cognitiveservices.azure.com/
|
|
|
|
# Gotenberg PDF conversion service
|
|
GOTENBERG_URL: http://{{ include "docuelevate.fullname" . }}-gotenberg:3000
|
|
|
|
# Full-text search — uses the in-cluster Meilisearch service by default
|
|
MEILISEARCH_URL: http://{{ include "docuelevate.fullname" . }}-meilisearch:7700
|
|
MEILISEARCH_INDEX_NAME: documents
|
|
ENABLE_SEARCH: "true"
|
|
|
|
# Authentication
|
|
AUTH_ENABLED: "true"
|
|
ADMIN_USERNAME: admin
|
|
|
|
# Feature flags
|
|
ENABLE_DEDUPLICATION: "true"
|
|
ENABLE_TEXT_QUALITY_CHECK: "true"
|
|
ALLOW_FILE_DELETE: "true"
|
|
|
|
# Logging / misc
|
|
DEBUG: "false"
|
|
EXTERNAL_HOSTNAME: localhost # set to your public hostname / Ingress host
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Secrets — values are stored in a Kubernetes Secret and injected as env vars.
|
|
# In production, use an external secret manager (Vault, ESO, Sealed Secrets)
|
|
# and leave these blank, then mount the Secret yourself.
|
|
# ---------------------------------------------------------------------------
|
|
secrets:
|
|
DATABASE_URL: "" # e.g. postgresql://user:pass@postgres:5432/docuelevate
|
|
REDIS_URL: "" # leave blank to use bundled Redis
|
|
SESSION_SECRET: "" # min 32-char random string — generate with: openssl rand -hex 32
|
|
OPENAI_API_KEY: ""
|
|
AZURE_AI_KEY: ""
|
|
MEILISEARCH_API_KEY: "" # leave blank for unauthenticated (dev) Meilisearch
|
|
|
|
# Storage provider secrets (only the ones you use)
|
|
DROPBOX_APP_KEY: ""
|
|
DROPBOX_APP_SECRET: ""
|
|
DROPBOX_REFRESH_TOKEN: ""
|
|
GOOGLE_DRIVE_CREDENTIALS_JSON: ""
|
|
ONEDRIVE_CLIENT_ID: ""
|
|
ONEDRIVE_CLIENT_SECRET: ""
|
|
ONEDRIVE_REFRESH_TOKEN: ""
|
|
AWS_ACCESS_KEY_ID: ""
|
|
AWS_SECRET_ACCESS_KEY: ""
|
|
|
|
# OAuth / Authentik
|
|
AUTHENTIK_CLIENT_ID: ""
|
|
AUTHENTIK_CLIENT_SECRET: ""
|
|
AUTHENTIK_CONFIG_URL: ""
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# External services
|
|
# Set externalRedis.url (and disable bundled redis) when you have your own.
|
|
# ---------------------------------------------------------------------------
|
|
externalRedis:
|
|
# When non-empty this value is injected as REDIS_URL, overriding secrets.REDIS_URL
|
|
# and the auto-generated bundled-Redis URL.
|
|
url: ""
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# API deployment
|
|
# ---------------------------------------------------------------------------
|
|
api:
|
|
replicaCount: 2
|
|
|
|
resources:
|
|
requests:
|
|
cpu: 250m
|
|
memory: 512Mi
|
|
limits:
|
|
cpu: "1"
|
|
memory: 1Gi
|
|
|
|
# Horizontal Pod Autoscaler
|
|
autoscaling:
|
|
enabled: false
|
|
minReplicas: 2
|
|
maxReplicas: 8
|
|
targetCPUUtilizationPercentage: 70
|
|
|
|
service:
|
|
type: ClusterIP
|
|
port: 8000
|
|
|
|
# Liveness / readiness probes
|
|
livenessProbe:
|
|
httpGet:
|
|
path: /api/health
|
|
port: 8000
|
|
initialDelaySeconds: 30
|
|
periodSeconds: 20
|
|
failureThreshold: 3
|
|
|
|
readinessProbe:
|
|
httpGet:
|
|
path: /api/health
|
|
port: 8000
|
|
initialDelaySeconds: 15
|
|
periodSeconds: 10
|
|
failureThreshold: 3
|
|
|
|
podAnnotations: {}
|
|
nodeSelector: {}
|
|
tolerations: []
|
|
affinity: {}
|
|
|
|
podSecurityContext:
|
|
runAsNonRoot: true
|
|
runAsUser: 1000
|
|
fsGroup: 1000
|
|
|
|
securityContext:
|
|
allowPrivilegeEscalation: false
|
|
readOnlyRootFilesystem: false # app writes to /workdir
|
|
capabilities:
|
|
drop: ["ALL"]
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Celery worker deployment
|
|
# ---------------------------------------------------------------------------
|
|
worker:
|
|
replicaCount: 2
|
|
|
|
resources:
|
|
requests:
|
|
cpu: 500m
|
|
memory: 1Gi
|
|
limits:
|
|
cpu: "2"
|
|
memory: 4Gi
|
|
|
|
autoscaling:
|
|
enabled: false
|
|
minReplicas: 2
|
|
maxReplicas: 10
|
|
targetCPUUtilizationPercentage: 75
|
|
|
|
podAnnotations: {}
|
|
nodeSelector: {}
|
|
tolerations: []
|
|
affinity: {}
|
|
|
|
podSecurityContext:
|
|
runAsNonRoot: true
|
|
runAsUser: 1000
|
|
fsGroup: 1000
|
|
|
|
securityContext:
|
|
allowPrivilegeEscalation: false
|
|
readOnlyRootFilesystem: false
|
|
capabilities:
|
|
drop: ["ALL"]
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Shared workdir volume (api + worker mount the same PVC)
|
|
# ---------------------------------------------------------------------------
|
|
workdir:
|
|
persistence:
|
|
enabled: true
|
|
# storageClass: "" # leave blank for cluster default
|
|
accessMode: ReadWriteMany # RWX required for multiple pods
|
|
size: 20Gi
|
|
# existingClaim: ""
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Gotenberg (PDF conversion)
|
|
# ---------------------------------------------------------------------------
|
|
gotenberg:
|
|
enabled: true
|
|
image:
|
|
repository: gotenberg/gotenberg
|
|
tag: latest
|
|
pullPolicy: IfNotPresent
|
|
service:
|
|
port: 3000
|
|
resources:
|
|
requests:
|
|
cpu: 100m
|
|
memory: 256Mi
|
|
limits:
|
|
cpu: "1"
|
|
memory: 1Gi
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Meilisearch (full-text search)
|
|
# ---------------------------------------------------------------------------
|
|
meilisearch:
|
|
enabled: true
|
|
image:
|
|
repository: getmeili/meilisearch
|
|
tag: latest
|
|
pullPolicy: IfNotPresent
|
|
service:
|
|
port: 7700
|
|
env:
|
|
MEILI_NO_ANALYTICS: "true"
|
|
# MEILI_MASTER_KEY: "" # set via secrets.MEILISEARCH_API_KEY instead
|
|
persistence:
|
|
enabled: true
|
|
# storageClass: ""
|
|
accessMode: ReadWriteOnce
|
|
size: 10Gi
|
|
# existingClaim: ""
|
|
resources:
|
|
requests:
|
|
cpu: 100m
|
|
memory: 256Mi
|
|
limits:
|
|
cpu: "1"
|
|
memory: 1Gi
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Bundled Redis (from Bitnami chart)
|
|
# Disable and set externalRedis.url to use your own.
|
|
# ---------------------------------------------------------------------------
|
|
redis:
|
|
enabled: true
|
|
architecture: standalone
|
|
auth:
|
|
enabled: false
|
|
master:
|
|
persistence:
|
|
enabled: true
|
|
size: 4Gi
|
|
resources:
|
|
requests:
|
|
cpu: 100m
|
|
memory: 128Mi
|
|
limits:
|
|
cpu: 500m
|
|
memory: 512Mi
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Ingress
|
|
# ---------------------------------------------------------------------------
|
|
ingress:
|
|
enabled: false
|
|
className: "" # e.g. nginx, traefik
|
|
annotations: {}
|
|
# nginx.ingress.kubernetes.io/proxy-body-size: "1g"
|
|
# cert-manager.io/cluster-issuer: letsencrypt-prod
|
|
hosts:
|
|
- host: docuelevate.example.com
|
|
paths:
|
|
- path: /
|
|
pathType: Prefix
|
|
tls: []
|
|
# - secretName: docuelevate-tls
|
|
# hosts:
|
|
# - docuelevate.example.com
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# ServiceAccount
|
|
# ---------------------------------------------------------------------------
|
|
serviceAccount:
|
|
create: true
|
|
annotations: {}
|
|
name: ""
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Database migration job
|
|
# Runs `alembic upgrade head` before the api/worker start.
|
|
# ---------------------------------------------------------------------------
|
|
migrations:
|
|
enabled: true
|
|
# Automatically deleted after successful completion
|
|
ttlSecondsAfterFinished: 120
|