From 5ed02928ecd9c5dcc4260e396aab90ed7e502eca Mon Sep 17 00:00:00 2001
From: Fizzlepoof <admin@paccoco.com>
Date: Wed, 13 May 2026 17:06:47 +0000
Subject: [PATCH] feat(paperless): add Tika and Gotenberg sidecars

Enable Paperless Office/OpenDocument ingestion by wiring internal Tika and Gotenberg services into the documents stack. Adds PAPERLESS_TIKA_* environment keys to .env.example and places both sidecars on an internal-only network with resource limits.
---
 documents/.env.example        |  3 +++
 documents/docker-compose.yaml | 25 +++++++++++++++++++++++++
 2 files changed, 28 insertions(+)

diff --git a/documents/.env.example b/documents/.env.example
index e7c4812..43edd2d 100644
--- a/documents/.env.example
+++ b/documents/.env.example
@@ -2,6 +2,9 @@ PAPERLESS_DBUSER=paperless
 PAPERLESS_DBPASS=changeme
 PAPERLESS_SECRET_KEY=generate_with_openssl_rand_hex_32
 PAPERLESS_REDIS=redis://:URL_ENCODED_REDIS_PASSWORD@shared-redis:6379
+PAPERLESS_TIKA_ENABLED=1
+PAPERLESS_TIKA_ENDPOINT=http://tika:9998
+PAPERLESS_TIKA_GOTENBERG_ENDPOINT=http://gotenberg:3000
 
 # -----------------------------
 # Karakeep
diff --git a/documents/docker-compose.yaml b/documents/docker-compose.yaml
index ab6f389..439defc 100644
--- a/documents/docker-compose.yaml
+++ b/documents/docker-compose.yaml
@@ -24,6 +24,12 @@ services:
       PAPERLESS_TIME_ZONE: America/Chicago
       PAPERLESS_OCR_LANGUAGE: eng
       PAPERLESS_URL: https://paperless.paccoco.com
+      PAPERLESS_TIKA_ENABLED: ${PAPERLESS_TIKA_ENABLED}
+      PAPERLESS_TIKA_ENDPOINT: ${PAPERLESS_TIKA_ENDPOINT}
+      PAPERLESS_TIKA_GOTENBERG_ENDPOINT: ${PAPERLESS_TIKA_GOTENBERG_ENDPOINT}
+    depends_on:
+      - tika
+      - gotenberg
     healthcheck:
       test: ["CMD-SHELL", "curl -sf http://127.0.0.1:8000/ || exit 1"]
       interval: 30s
@@ -31,9 +37,26 @@ services:
       retries: 3
       start_period: 60s
     networks:
+      - paperless-internal
       - ix-databases_shared-databases
       - pangolin
 
+  tika:
+    image: apache/tika:latest
+    container_name: paperless-tika
+    restart: unless-stopped
+    mem_limit: 512m
+    networks:
+      - paperless-internal
+
+  gotenberg:
+    image: gotenberg/gotenberg:latest
+    container_name: paperless-gotenberg
+    restart: unless-stopped
+    mem_limit: 256m
+    networks:
+      - paperless-internal
+
   karakeep:
     image: ghcr.io/karakeep-app/karakeep:${KARAKEEP_VERSION:-release}
     container_name: karakeep
@@ -95,6 +118,8 @@ services:
       - karakeep
 
 networks:
+  paperless-internal:
+    name: documents_paperless_internal
   ix-databases_shared-databases:
     external: true
   pangolin: