Use archivebox/sonic multi-arch container with bundled config file

docker-compose.yml

@@ -2,10 +2,9 @@
 #     curl -fsSL 'https://docker-compose.archivebox.io' > docker-compose.yml
 #     docker compose up
 #     docker compose run archivebox version
-#     echo 'https://example.com' | docker compose run -T archivebox add
+#     docker compose run -T archivebox add < urls_to_archive.txt
 #     docker compose run archivebox add --depth=1 'https://news.ycombinator.com'
 #     docker compose run archivebox config --set SAVE_ARCHIVE_DOT_ORG=False
-#     docker compose run archivebox status
 #     docker compose run archivebox help
 # Documentation:
 #     https://github.com/ArchiveBox/ArchiveBox/wiki/Docker#docker-compose
@@ -19,7 +18,7 @@ services:
             - ./data:/data
             # ./data/personas/Default/chrome_profile/Default:/data/personas/Default/chrome_profile/Default
         environment:
-            # - ADMIN_USERNAME=admin            # create an admin user on first run with the given user/pass combo
+            # - ADMIN_USERNAME=admin            # creates an admin user on first run with the given user/pass combo
             # - ADMIN_PASSWORD=SomeSecretPassword
             - CSRF_TRUSTED_ORIGINS=https://archivebox.example.com  # REQUIRED for auth, REST API, etc. to work
             - ALLOWED_HOSTS=*                   # set this to the hostname(s) from your CSRF_TRUSTED_ORIGINS
@@ -31,15 +30,16 @@ services:
             - SEARCH_BACKEND_PASSWORD=SomeSecretPassword
             # - PUID=911                        # set to your host user's UID & GID if you encounter permissions issues
             # - PGID=911                        # UID/GIDs <500 may clash with existing users and are not recommended
+            # For options below, it's better to set using `docker compose run archivebox config --set SOME_KEY=someval` instead of setting here:
             # - MEDIA_MAX_SIZE=750m             # increase this filesize limit to allow archiving larger audio/video files
             # - TIMEOUT=60                      # increase this number to 120+ seconds if you see many slow downloads timing out
             # - CHECK_SSL_VALIDITY=True         # set to False to disable strict SSL checking (allows saving URLs w/ broken certs)
             # - SAVE_ARCHIVE_DOT_ORG=True       # set to False to disable submitting all URLs to Archive.org when archiving
             # - USER_AGENT="..."                # set a custom USER_AGENT to avoid being blocked as a bot
             # ...
-            # add further configuration options from archivebox/config.py as needed (to apply them only to this container)
+            # For more info, see: https://github.com/ArchiveBox/ArchiveBox/wiki/Docker#configuration
-            # or set using `docker compose run archivebox config --set SOME_KEY=someval` (to persist config across all containers)
+            
-        # For ad-blocking during archiving, uncomment this section and pihole service section below
+        # For ad-blocking during archiving, uncomment this section and the pihole service below
         # networks:
         #   - dns
         # dns:
@@ -48,7 +48,7 @@ services:
 
     ######## Optional Addons: tweak examples below as needed for your specific use case ########
 
-    ### This optional container runs any scheduled tasks in the background, add new tasks like so:
+    ### This optional container runs scheduled jobs in the background (and retries failed ones). To add a new job:
     #   $ docker compose run archivebox schedule --add --every=day --depth=1 'https://example.com/some/rss/feed.xml'
     # then restart the scheduler container to apply any changes to the scheduled task list:
     #   $ docker compose restart archivebox_scheduler
@@ -59,9 +59,15 @@ services:
         image: archivebox/archivebox:latest
         command: schedule --foreground --update --every=day
         environment:
+            # - PUID=911                        # set to your host user's UID & GID if you encounter permissions issues
+            # - PGID=911
             - TIMEOUT=120                       # use a higher timeout than the main container to give slow tasks more time when retrying
-            # - PUID=502                        # set to your host user's UID & GID if you encounter permissions issues
+            - SEARCH_BACKEND_ENGINE=sonic       # tells ArchiveBox to use sonic container below for fast full-text search
-            # - PGID=20
+            - SEARCH_BACKEND_HOST_NAME=sonic
+            - SEARCH_BACKEND_PASSWORD=SomeSecretPassword
+            # For other config it's better to set using `docker compose run archivebox config --set SOME_KEY=someval` instead of setting here
+            # ...
+            # For more info, see: https://github.com/ArchiveBox/ArchiveBox/wiki/Docker#configuration
         volumes:
             - ./data:/data
         # cpus: 2                               # uncomment / edit these values to limit scheduler container resource consumption
@@ -75,25 +81,17 @@ services:
     # https://github.com/ArchiveBox/ArchiveBox/wiki/Setting-up-Search
 
     sonic:
-        image: valeriansaliou/sonic:latest
+        image: archivebox/sonic:latest
-        build:
-            # custom build just auto-downloads archivebox's default sonic.cfg as a convenience
-            # not needed after first run / if you have already have ./etc/sonic.cfg present
-            dockerfile_inline: |
-                FROM quay.io/curl/curl:latest AS config_downloader
-                RUN curl -fsSL 'https://raw.githubusercontent.com/ArchiveBox/ArchiveBox/stable/etc/sonic.cfg' > /tmp/sonic.cfg
-                FROM valeriansaliou/sonic:latest
-                COPY --from=config_downloader /tmp/sonic.cfg /etc/sonic.cfg
         expose:
             - 1491
         environment:
             - SEARCH_BACKEND_PASSWORD=SomeSecretPassword
         volumes:
-            #- ./sonic.cfg:/etc/sonic.cfg:ro    # use this if you prefer to download the config on the host and mount it manually
+            #- ./sonic.cfg:/etc/sonic.cfg:ro    # mount to customize: https://raw.githubusercontent.com/ArchiveBox/ArchiveBox/stable/etc/sonic.cfg
             - ./data/sonic:/var/lib/sonic/store
 
 
-    ### This container runs xvfb+noVNC so you can watch the ArchiveBox browser as it archives things,
+    ### This optional container runs xvfb+noVNC so you can watch the ArchiveBox browser as it archives things,
     # or remote control it to set up a chrome profile w/ login credentials for sites you want to archive.
     # https://github.com/ArchiveBox/ArchiveBox/wiki/Chromium-Install#setting-up-a-chromium-user-profile
     # https://github.com/ArchiveBox/ArchiveBox/wiki/Chromium-Install#docker-vnc-setup
@@ -124,7 +122,7 @@ services:
 
 
     ### Example: To run pihole in order to block ad/tracker requests during archiving,
-    # uncomment this block and set up pihole using its admin interface
+    # uncomment this optional block and set up pihole using its admin interface
 
     # pihole:
     #   image: pihole/pihole:latest
@@ -146,7 +144,7 @@ services:
 
 
     ### Example: run all your ArchiveBox traffic through a WireGuard VPN tunnel to avoid IP blocks.
-    # You can also use any other VPN that works at the docker IP level, e.g. Tailscale, OpenVPN, etc.
+    # You can also use any other VPN that works at the docker/IP level, e.g. Tailscale, OpenVPN, etc.
 
     # wireguard:
     #   image: linuxserver/wireguard:latest