wrolpi/pi-gen
Roland 318b835faf
ai: package llama-server for all three deployments, with idle unload
install_llama_cpp.sh builds llama-server from the SHA-pinned v0.3.0
source tarball (single source of truth: on-device upgrade, Pi image,
Live ISO, and the new docker/llm container all call it; version-marker
makes re-runs no-ops).  start_llama_server.sh refuses to start unless
ai.yaml enables AI and the active model file exists — which also covers
unmounted media.  wrolpi-llm.service is installed but deliberately
never enabled at boot: the Controller starts it on demand (registered
in managed_services; the llm compose service follows the samba
pattern), and the API's perpetual idle-unload worker asks the
Controller to stop it after the configured idle minutes.  llama-server
is localhost-only natively, internal-network-only in docker, and never
proxied by Caddy.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-09-13 20:10:16 -06:00
..
stage2/04-wrolpi ai: package llama-server for all three deployments, with idle unload 2026-09-13 20:10:16 -06:00
build.sh Debian 13 (trixie) rebase: docker, debian-live-config, and pi-gen builds. 2026-07-13 15:43:08 -06:00
config.txt Debian 13 (trixie) rebase: docker, debian-live-config, and pi-gen builds. 2026-07-13 15:43:08 -06:00
README.md Remove stale Postgres references after SQLite cutover. 2026-07-18 13:28:54 -06:00

Pi-Gen

This directory exists to facilitate the creation of WROLPI Raspberry Pi OS images.

See https://github.com/RPI-Distro/pi-gen

Generate 64bit Raspberry Pi WROLPi image

  1. (Optional) Place any default map assets under pi-gen/stage2/04-wrolpi/files/ if the image should ship with preloaded map data. Maps use PMTiles files served from /media/wrolpi/map/.

  2. Run the build (or, with a specific git branch)

    • Build release branch (default)

      sudo ./build.sh
      
    • Build specific branch

      sudo ./build.sh -b master
      
  3. The images are now in the pi-gen directory.