From a938895e5e4f63dc6a9558158b8d0ce2f4c58eec Mon Sep 17 00:00:00 2001 From: Quinn Casey Date: Mon, 2 May 2022 08:23:04 -0700 Subject: [PATCH 1/3] Use our arm compatible tika container --- .../compose/docker-compose.postgres-tika.yml | 2 +- .../docker-compose.sqlite-tika.arm.yml | 85 ------------------- docker/compose/docker-compose.sqlite-tika.yml | 2 +- 3 files changed, 2 insertions(+), 87 deletions(-) delete mode 100644 docker/compose/docker-compose.sqlite-tika.arm.yml diff --git a/docker/compose/docker-compose.postgres-tika.yml b/docker/compose/docker-compose.postgres-tika.yml index c6a72e903..516d88b7a 100644 --- a/docker/compose/docker-compose.postgres-tika.yml +++ b/docker/compose/docker-compose.postgres-tika.yml @@ -85,7 +85,7 @@ services: - "--chromium-disable-routes=true" tika: - image: apache/tika + image: ghcr.io/paperless-ngx/tika:latest restart: unless-stopped volumes: diff --git a/docker/compose/docker-compose.sqlite-tika.arm.yml b/docker/compose/docker-compose.sqlite-tika.arm.yml deleted file mode 100644 index 16633fd1d..000000000 --- a/docker/compose/docker-compose.sqlite-tika.arm.yml +++ /dev/null @@ -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: diff --git a/docker/compose/docker-compose.sqlite-tika.yml b/docker/compose/docker-compose.sqlite-tika.yml index d9327533e..ee2aad40a 100644 --- a/docker/compose/docker-compose.sqlite-tika.yml +++ b/docker/compose/docker-compose.sqlite-tika.yml @@ -74,7 +74,7 @@ services: - "--chromium-disable-routes=true" tika: - image: apache/tika + image: ghcr.io/paperless-ngx/tika:latest restart: unless-stopped volumes: From d58b1a7de70f0972deca58aa7071e176cc241e1c Mon Sep 17 00:00:00 2001 From: Quinn Casey Date: Mon, 2 May 2022 09:02:29 -0700 Subject: [PATCH 2/3] Update Tika documentation --- docker/compose/docker-compose.postgres-tika.yml | 3 +-- docker/compose/docker-compose.sqlite-tika.yml | 4 +--- docs/configuration.rst | 4 ++-- docs/setup.rst | 4 +--- scripts/start_services.sh | 2 +- 5 files changed, 6 insertions(+), 11 deletions(-) diff --git a/docker/compose/docker-compose.postgres-tika.yml b/docker/compose/docker-compose.postgres-tika.yml index 516d88b7a..b25fdbc63 100644 --- a/docker/compose/docker-compose.postgres-tika.yml +++ b/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 -# does not support arm or arm64, however. +# Paperless supports amd64, arm and arm64 hardware. # # All compose files of paperless configure paperless in the following way: # diff --git a/docker/compose/docker-compose.sqlite-tika.yml b/docker/compose/docker-compose.sqlite-tika.yml index ee2aad40a..9017f5d20 100644 --- a/docker/compose/docker-compose.sqlite-tika.yml +++ b/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 -# does not support arm or arm64, however. -# +# 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. diff --git a/docs/configuration.rst b/docs/configuration.rst index 7849d8dad..b5668c686 100644 --- a/docs/configuration.rst +++ b/docs/configuration.rst @@ -474,7 +474,7 @@ PAPERLESS_TIKA_GOTENBERG_ENDPOINT= 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 @@ -502,7 +502,7 @@ requires are as follows: - "--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 diff --git a/docs/setup.rst b/docs/setup.rst index de694bda8..d3290b432 100644 --- a/docs/setup.rst +++ b/docs/setup.rst @@ -347,7 +347,7 @@ writing. Windows is not and will never be supported. paperless stores its data. If you like, you can point both to the same directory. * ``PAPERLESS_SECRET_KEY`` should be a random sequence of characters. It's used for authentication. Failure to do so allows third parties to forge authentication credentials. - * ``PAPERLESS_URL`` if you are behind a reverse proxy. This should point to your domain. Please see + * ``PAPERLESS_URL`` if you are behind a reverse proxy. This should point to your domain. Please see :ref:`configuration` for more information. Many more adjustments can be made to paperless, especially the OCR part. The following options are recommended @@ -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`. diff --git a/scripts/start_services.sh b/scripts/start_services.sh index 24e3233cd..fdb609e85 100755 --- a/scripts/start_services.sh +++ b/scripts/start_services.sh @@ -3,4 +3,4 @@ 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 9998:9998 -d apache/tika +docker run -p 9998:9998 -d ghcr.io/paperless-ngx/tika:latest From 939dd17910af39b88bd1e9a0a46cff0e863dfa5f Mon Sep 17 00:00:00 2001 From: Quinn Casey Date: Mon, 2 May 2022 09:16:42 -0700 Subject: [PATCH 3/3] Update Gotenberg to 7.4 --- docker/compose/docker-compose.postgres-tika.yml | 2 +- docker/compose/docker-compose.sqlite-tika.yml | 2 +- docs/configuration.rst | 2 +- docs/troubleshooting.rst | 2 +- scripts/start_services.sh | 2 +- 5 files changed, 5 insertions(+), 5 deletions(-) diff --git a/docker/compose/docker-compose.postgres-tika.yml b/docker/compose/docker-compose.postgres-tika.yml index b25fdbc63..d8f93fb79 100644 --- a/docker/compose/docker-compose.postgres-tika.yml +++ b/docker/compose/docker-compose.postgres-tika.yml @@ -77,7 +77,7 @@ services: PAPERLESS_TIKA_ENDPOINT: http://tika:9998 gotenberg: - image: gotenberg/gotenberg:7 + image: gotenberg/gotenberg:7.4 restart: unless-stopped command: - "gotenberg" diff --git a/docker/compose/docker-compose.sqlite-tika.yml b/docker/compose/docker-compose.sqlite-tika.yml index 9017f5d20..a898527da 100644 --- a/docker/compose/docker-compose.sqlite-tika.yml +++ b/docker/compose/docker-compose.sqlite-tika.yml @@ -65,7 +65,7 @@ services: PAPERLESS_TIKA_ENDPOINT: http://tika:9998 gotenberg: - image: gotenberg/gotenberg:7 + image: gotenberg/gotenberg:7.4 restart: unless-stopped command: - "gotenberg" diff --git a/docs/configuration.rst b/docs/configuration.rst index b5668c686..92cba8d72 100644 --- a/docs/configuration.rst +++ b/docs/configuration.rst @@ -495,7 +495,7 @@ requires are as follows: # ... gotenberg: - image: gotenberg/gotenberg:7 + image: gotenberg/gotenberg:7.4 restart: unless-stopped command: - "gotenberg" diff --git a/docs/troubleshooting.rst b/docs/troubleshooting.rst index 3ae4909de..b1f41f096 100644 --- a/docs/troubleshooting.rst +++ b/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" diff --git a/scripts/start_services.sh b/scripts/start_services.sh index fdb609e85..3d0addb55 100755 --- a/scripts/start_services.sh +++ b/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 ghcr.io/paperless-ngx/tika:latest