Merge pull request #866 from paperless-ngx/feature-arm-tika-consolidate

Deployment: Consolidate tika compose files

docker/compose/docker-compose.postgres-tika.yml

@@ -1,7 +1,6 @@
 # docker-compose file for running paperless from the docker container registry.
 # This file contains everything paperless needs to run.
-# Paperless supports amd64, arm and arm64 hardware. The apache/tika image
+# Paperless supports amd64, arm and arm64 hardware.
-# does not support arm or arm64, however.
 #
 # All compose files of paperless configure paperless in the following way:
 #
@@ -78,14 +77,14 @@ services:
       PAPERLESS_TIKA_ENDPOINT: http://tika:9998
 
   gotenberg:
-    image: gotenberg/gotenberg:7
+    image: gotenberg/gotenberg:7.4
     restart: unless-stopped
     command:
       - "gotenberg"
       - "--chromium-disable-routes=true"
 
   tika:
-    image: apache/tika
+    image: ghcr.io/paperless-ngx/tika:latest
     restart: unless-stopped
 
 volumes:

docker/compose/docker-compose.sqlite-tika.arm.yml

@@ -1,85 +0,0 @@
-# docker-compose file for running paperless from the docker container registry.
-# This file contains everything paperless needs to run.
-# Paperless supports amd64, arm and arm64 hardware.
-#
-# All compose files of paperless configure paperless in the following way:
-#
-# - Paperless is (re)started on system boot, if it was running before shutdown.
-# - Docker volumes for storing data are managed by Docker.
-# - Folders for importing and exporting files are created in the same directory
-#   as this file and mounted to the correct folders inside the container.
-# - Paperless listens on port 8000.
-#
-# SQLite is used as the database. The SQLite file is stored in the data volume.
-#
-# iwishiwasaneagle/apache-tika-arm docker image is used to enable arm64 arch
-# which apache/tika does not currently support.
-#
-# In addition to that, this docker-compose file adds the following optional
-# configurations:
-#
-# - Apache Tika and Gotenberg servers are started with paperless and paperless
-#   is configured to use these services. These provide support for consuming
-#   Office documents (Word, Excel, Power Point and their LibreOffice counter-
-#   parts.
-#
-# To install and update paperless with this file, do the following:
-#
-# - Copy this file as 'docker-compose.yml' and the files 'docker-compose.env'
-#   and '.env' into a folder.
-# - Run 'docker-compose pull'.
-# - Run 'docker-compose run --rm webserver createsuperuser' to create a user.
-# - Run 'docker-compose up -d'.
-#
-# For more extensive installation and update instructions, refer to the
-# documentation.
-
-version: "3.4"
-services:
-  broker:
-    image: redis:6.0
-    restart: unless-stopped
-    volumes:
-      - redisdata:/data
-
-  webserver:
-    image: ghcr.io/paperless-ngx/paperless-ngx:latest
-    restart: unless-stopped
-    depends_on:
-      - broker
-      - gotenberg
-      - tika
-    ports:
-      - 8000:8000
-    healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:8000"]
-      interval: 30s
-      timeout: 10s
-      retries: 5
-    volumes:
-      - data:/usr/src/paperless/data
-      - media:/usr/src/paperless/media
-      - ./export:/usr/src/paperless/export
-      - ./consume:/usr/src/paperless/consume
-    env_file: docker-compose.env
-    environment:
-      PAPERLESS_REDIS: redis://broker:6379
-      PAPERLESS_TIKA_ENABLED: 1
-      PAPERLESS_TIKA_GOTENBERG_ENDPOINT: http://gotenberg:3000
-      PAPERLESS_TIKA_ENDPOINT: http://tika:9998
-
-  gotenberg:
-    image: gotenberg/gotenberg:7
-    restart: unless-stopped
-    command:
-      - "gotenberg"
-      - "--chromium-disable-routes=true"
-
-  tika:
-    image: iwishiwasaneagle/apache-tika-arm@sha256:a78c25ffe57ecb1a194b2859d42a61af46e9e845191512b8f1a4bf90578ffdfd
-    restart: unless-stopped
-
-volumes:
-  data:
-  media:
-  redisdata:

docker/compose/docker-compose.sqlite-tika.yml

@@ -1,8 +1,6 @@
 # docker-compose file for running paperless from the docker container registry.
 # This file contains everything paperless needs to run.
-# Paperless supports amd64, arm and arm64 hardware. The apache/tika image
+# Paperless supports amd64, arm and arm64 hardware.
-# does not support arm or arm64, however.
-#
 # All compose files of paperless configure paperless in the following way:
 #
 # - Paperless is (re)started on system boot, if it was running before shutdown.
@@ -67,14 +65,14 @@ services:
       PAPERLESS_TIKA_ENDPOINT: http://tika:9998
 
   gotenberg:
-    image: gotenberg/gotenberg:7
+    image: gotenberg/gotenberg:7.4
     restart: unless-stopped
     command:
       - "gotenberg"
       - "--chromium-disable-routes=true"
 
   tika:
-    image: apache/tika
+    image: ghcr.io/paperless-ngx/tika:latest
     restart: unless-stopped
 
 volumes:

docs/configuration.rst

@@ -474,7 +474,7 @@ PAPERLESS_TIKA_GOTENBERG_ENDPOINT=<url>
     Defaults to "http://localhost:3000".
 
 If you run paperless on docker, you can add those services to the docker-compose
-file (see the provided ``docker-compose.tika.yml`` file for reference). The changes
+file (see the provided ``docker-compose.sqlite-tika.yml`` file for reference). The changes
 requires are as follows:
 
 .. code:: yaml
@@ -495,14 +495,14 @@ requires are as follows:
         # ...
 
         gotenberg:
-            image: gotenberg/gotenberg:7
+            image: gotenberg/gotenberg:7.4
             restart: unless-stopped
             command:
                 - "gotenberg"
                 - "--chromium-disable-routes=true"
 
         tika:
-            image: apache/tika
+            image: ghcr.io/paperless-ngx/tika:latest
             restart: unless-stopped
 
 Add the configuration variables to the environment of the webserver (alternatively

docs/setup.rst

@@ -728,8 +728,6 @@ configuring some options in paperless can help improve performance immensely:
     times. Thumbnails will be about 20% larger.
 *   If using docker, consider setting ``PAPERLESS_WEBSERVER_WORKERS`` to
     1. This will save some memory.
-*   Use the arm compatible docker-compose if you're wanting to use Tika on something like
-		a raspberry pi. The official apache/tika image does not support the arm architecture.
 
 For details, refer to :ref:`configuration`.
 

docs/troubleshooting.rst

@@ -125,7 +125,7 @@ If using docker-compose, this is achieved by the following configuration change
 .. code:: yaml
 
     gotenberg:
-        image: gotenberg/gotenberg:7
+        image: gotenberg/gotenberg:7.4
         restart: unless-stopped
         command:
             - "gotenberg"

scripts/start_services.sh

@@ -2,5 +2,5 @@
 
 docker run -p 5432:5432 -e POSTGRES_PASSWORD=password -v paperless_pgdata:/var/lib/postgresql/data -d postgres:13
 docker run -d -p 6379:6379 redis:latest
-docker run -p 3000:3000 -d gotenberg/gotenberg:7
+docker run -p 3000:3000 -d gotenberg/gotenberg:7.4
-docker run -p 9998:9998 -d apache/tika
+docker run -p 9998:9998 -d ghcr.io/paperless-ngx/tika:latest