homelab/k8s/apps/paperless/paperless-ai.yaml

# Secret paperless-ai-config managed via SOPS (argocd/secrets/paperless-ai-secrets.enc.yaml)
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: paperless-ai
  namespace: paperless
  labels:
    app.kubernetes.io/name: paperless-ai
spec:
  replicas: 1
  selector:
    matchLabels:
      app.kubernetes.io/name: paperless-ai
  template:
    metadata:
      labels:
        app.kubernetes.io/name: paperless-ai
    spec:
      tolerations:
        - key: node-role.kubernetes.io/control-plane
          operator: Exists
          effect: NoSchedule
      volumes:
        - name: paperless-ai-data
          persistentVolumeClaim:
            claimName: paperless-ai-data
      initContainers:
        - name: fetch-llm-token
          image: curlimages/curl:8.12.0
          command:
            - sh
            - -c
            - |
              set -e
              echo "[init] Fetching JWT token from Authentik for paperless-ai-agent..."
              
              # Get JWT token via client_credentials grant
              TOKEN_RESPONSE=$(curl -s -X POST https://authentik.riotpiao.com/application/o/token/ \
                -d "grant_type=client_credentials" \
                -d "client_id=paperless-ai-agent" \
                -d "client_secret=29skAhE0tBzWn0qrPvmPTQMva0joFjcCr7msDQr_VXQ" \
                -d "scope=openid llm:inference" 2>/dev/null)
              
              # Extract token
              TOKEN=$(echo "$TOKEN_RESPONSE" | grep -o '"access_token":"[^"]*' | cut -d'"' -f4)
              
              if [ -z "$TOKEN" ]; then
                echo "[error] Failed to get token. Response: $TOKEN_RESPONSE"
                exit 1
              fi
              
              # Store token in file for main container to read
              mkdir -p /data
              echo "$TOKEN" > /data/llm_token.txt
              echo "[init] Token fetched and stored (length: ${#TOKEN})"
          volumeMounts:
            - name: paperless-ai-data
              mountPath: /data
      containers:
        - name: paperless-ai
          image: clusterzx/paperless-ai:latest
          env:
            # Paperless-ngx connection
            - name: PAPERLESS_API_URL
              value: "http://paperless.paperless.svc.cluster.local:8000"
            - name: PAPERLESS_API_TOKEN
              valueFrom:
                secretKeyRef:
                  name: paperless-ai-config
                  key: PAPERLESS_API_TOKEN
            - name: PAPERLESS_USERNAME
              value: "admin"
            # LLM API — via public gateway with JWT auth
            - name: AI_PROVIDER
              value: "custom"
            - name: CUSTOM_BASE_URL
              value: "https://api.riotpiao.com/v1"
            # Token will be read from file at runtime by the application
            # The init container fetches it and stores in /app/data/llm_token.txt
            - name: CUSTOM_API_KEY_FILE
              value: "/app/data/llm_token.txt"
            - name: CUSTOM_MODEL
              value: "qwen2.5:3b-instruct"
            # Behavior - scan for new documents and tag them
            - name: SCAN_INTERVAL
              value: "60"
            - name: PROCESS_PREDEFINED_DOCUMENTS
              value: "no"
            - name: ADD_AI_TAG
              value: "yes"
            - name: AI_TAG_NAME
              value: "ai-processed"
            - name: USE_PROMPT_TAGS
              value: "yes"
            - name: ADD_AI_DESCRIPTIONS
              value: "yes"
          volumeMounts:
            - name: paperless-ai-data
              mountPath: /app/data
          resources:
            requests:
              cpu: 100m
              memory: 512Mi
            limits:
              cpu: "1"
              memory: 2Gi