Compare commits
14
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
6243ac40b7 | ||
|
|
d6fca68f33 | ||
|
|
e12327f963 | ||
|
|
b03098aa1c | ||
|
|
f61e8f1f68 | ||
|
|
7016f764e6 | ||
|
|
d826510a98 | ||
|
|
467b3441c9 | ||
|
|
7e91262257 | ||
|
|
0edd6bc73a | ||
|
|
4ad0102260 | ||
|
|
e0c08a90b3 | ||
|
|
dfbe2cc920 | ||
|
|
ae93c7ca0d |
@@ -4,6 +4,7 @@ namespace: paperless
|
||||
resources:
|
||||
- pvc.yaml
|
||||
- configmap.yaml
|
||||
- paperless-ai-config.yaml
|
||||
- redis.yaml
|
||||
- deployment.yaml
|
||||
- service.yaml
|
||||
|
||||
@@ -0,0 +1,49 @@
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: paperless-ai-env
|
||||
namespace: paperless
|
||||
data:
|
||||
paperless-ai-config.env: |
|
||||
# Paperless-NGX API configuration
|
||||
PAPERLESS_URL=http://paperless.paperless.svc.cluster.local:8000
|
||||
PAPERLESS_API_TOKEN=7b89463e04c141f4172fbcddf78d623547d327ec
|
||||
|
||||
# AI Processing settings
|
||||
ENABLE_AI_PROCESSING=yes
|
||||
AI_MODEL=reasoning
|
||||
LLM_API_URL=https://api.riotpiao.com/v1
|
||||
LLM_API_TOKEN_FILE=/app/data/llm_token.txt
|
||||
|
||||
# Auto-tagging configuration
|
||||
ENABLE_AUTO_TAGGING=yes
|
||||
ENABLE_CORRESPONDENT_EXTRACTION=yes
|
||||
ENABLE_DOCUMENT_TYPE_EXTRACTION=yes
|
||||
ENABLE_TITLE_GENERATION=yes
|
||||
|
||||
# Advanced tagging with AI
|
||||
ENABLE_INTELLIGENT_TAGGING=yes
|
||||
ENABLE_DATE_EXTRACTION=yes
|
||||
ENABLE_TIMELINE_TAGGING=yes
|
||||
AUTO_CREATE_TAGS=yes
|
||||
|
||||
# Tagging prompts for custom extraction
|
||||
CUSTOM_EXTRACTION_PROMPT=Extract document date, time period, financial year, and temporal context. Create tags like YYYY, Q1-YYYY, Last-Month, Current-Year, Historic
|
||||
TAG_EXTRACTION_MODEL=reasoning
|
||||
|
||||
# Scanning behavior
|
||||
SCAN_INTERVAL_SECONDS=60
|
||||
PROCESS_EXISTING_DOCUMENTS=no
|
||||
ADD_AI_TAG=yes
|
||||
AI_TAG_NAME=ai-processed
|
||||
|
||||
# Date/Timeline tagging configuration
|
||||
DATE_EXTRACTION_FORMAT=iso8601
|
||||
TIMELINE_TAG_GRANULARITY=year,quarter,month
|
||||
AUTO_TAG_HISTORICAL=yes
|
||||
AUTO_TAG_RECENT=yes
|
||||
|
||||
# Performance
|
||||
MAX_CONCURRENT_REQUESTS=2
|
||||
REQUEST_TIMEOUT=60
|
||||
DATE_EXTRACTION_TIMEOUT=30
|
||||
@@ -25,9 +25,15 @@ spec:
|
||||
- name: paperless-ai-data
|
||||
persistentVolumeClaim:
|
||||
claimName: paperless-ai-data
|
||||
- name: paperless-ai-env-config
|
||||
configMap:
|
||||
name: paperless-ai-env
|
||||
initContainers:
|
||||
- name: fetch-llm-token
|
||||
image: curlimages/curl:8.12.0
|
||||
securityContext:
|
||||
runAsUser: 0
|
||||
fsGroup: 0
|
||||
command:
|
||||
- sh
|
||||
- -c
|
||||
@@ -43,8 +49,8 @@ spec:
|
||||
-d "client_secret=${LLM_AUTH_CLIENT_SECRET}" \
|
||||
-d "scope=openid llm:inference" 2>/dev/null)
|
||||
|
||||
# Extract token
|
||||
TOKEN=$(echo "$TOKEN_RESPONSE" | grep -o '"access_token":"[^"]*' | cut -d'"' -f4)
|
||||
# Extract token from JSON response using sed (handles spaces after colons)
|
||||
TOKEN=$(echo "$TOKEN_RESPONSE" | sed -n 's/.*"access_token"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/p')
|
||||
|
||||
if [ -z "$TOKEN" ]; then
|
||||
echo "[error] Failed to get token. Response: $TOKEN_RESPONSE"
|
||||
@@ -52,9 +58,13 @@ spec:
|
||||
fi
|
||||
|
||||
# Store token in file for main container to read
|
||||
mkdir -p /data
|
||||
echo "$TOKEN" > /data/llm_token.txt
|
||||
echo "[init] Token fetched and stored successfully"
|
||||
# Write to both locations for compatibility
|
||||
mkdir -p /tmp/llm-token /app/data 2>/dev/null || true
|
||||
echo "$TOKEN" | tee /tmp/llm-token/llm_token.txt > /dev/null 2>&1
|
||||
echo "$TOKEN" > /app/data/llm_token.txt 2>/dev/null || true
|
||||
echo "[init] Token fetched and stored"
|
||||
[ -f /tmp/llm-token/llm_token.txt ] && echo " -> /tmp/llm-token/llm_token.txt"
|
||||
[ -f /app/data/llm_token.txt ] && echo " -> /app/data/llm_token.txt"
|
||||
env:
|
||||
- name: LLM_AUTH_CLIENT_SECRET
|
||||
valueFrom:
|
||||
@@ -63,7 +73,7 @@ spec:
|
||||
key: LLM_AUTH_CLIENT_SECRET
|
||||
volumeMounts:
|
||||
- name: paperless-ai-data
|
||||
mountPath: /data
|
||||
mountPath: /app/data
|
||||
containers:
|
||||
- name: paperless-ai
|
||||
image: clusterzx/paperless-ai:latest
|
||||
@@ -105,6 +115,9 @@ spec:
|
||||
volumeMounts:
|
||||
- name: paperless-ai-data
|
||||
mountPath: /app/data
|
||||
- name: paperless-ai-env-config
|
||||
mountPath: /app/data/.env
|
||||
subPath: paperless-ai-config.env
|
||||
resources:
|
||||
requests:
|
||||
cpu: 100m
|
||||
|
||||
@@ -73,7 +73,7 @@ grafana.ini:
|
||||
auth.generic_oauth:
|
||||
enabled: true
|
||||
name: Authentik
|
||||
allow_sign_up: true
|
||||
allow_sign_up: true # Allow sync to create/update users from OAuth claims
|
||||
client_id: grafana
|
||||
scopes: openid email profile groups
|
||||
auth_url: https://authentik.riotpiao.com/application/o/authorize/
|
||||
@@ -84,13 +84,13 @@ grafana.ini:
|
||||
# Authentik doesn't serve — request 404s with "Error getting email address"
|
||||
# and the whole OAuth login fails.
|
||||
email_attribute_path: email
|
||||
login_attribute_path: preferred_username
|
||||
login_attribute_path: preferred_username # Use preferred_username — OpenID standard claim, always present
|
||||
name_attribute_path: name
|
||||
role_attribute_path: "preferred_username == 'akadmin' && 'GrafanaAdmin' || contains(groups[*], 'homelab-admins') && 'Admin' || 'Viewer'"
|
||||
allow_assign_grafana_admin: true
|
||||
use_pkce: false
|
||||
use_refresh_token: false
|
||||
skip_org_role_sync: false
|
||||
skip_org_role_sync: false # Sync org roles from OAuth groups
|
||||
tls_skip_verify_insecure: true # Authentik uses self-signed cert; verify in prod
|
||||
|
||||
# GF_AUTH_GENERIC_OAUTH_CLIENT_SECRET is injected from the grafana-oidc K8s
|
||||
|
||||
Reference in New Issue
Block a user