diff --git a/active/container_bifrost/bifrost.md b/active/container_bifrost/bifrost.md new file mode 100644 index 0000000..856b056 --- /dev/null +++ b/active/container_bifrost/bifrost.md @@ -0,0 +1,208 @@ +# Podman bifrost + +- [Podman bifrost](#podman-bifrost) + - [Setup bifrost Project](#setup-bifrost-project) + - [Install bifrost](#install-bifrost) + - [Create the ai user](#create-the-ai-user) + - [Write the bifrost compose spec](#write-the-bifrost-compose-spec) + - [A Note on Volumes](#a-note-on-volumes) + - [Convert bifrost compose spec to quadlets](#convert-bifrost-compose-spec-to-quadlets) + - [Start and enable your systemd quadlet](#start-and-enable-your-systemd-quadlet) + - [Expose bifrost](#expose-bifrost) + - [Using bifrost](#using-bifrost) + - [Adding Models](#adding-models) + - [Testing Models](#testing-models) + - [Backup bifrost](#backup-bifrost) + - [Upgrade bifrost](#upgrade-bifrost) + - [Upgrade Quadlets](#upgrade-quadlets) + - [Uninstall](#uninstall) + - [Notes](#notes) + - [SELinux](#selinux) + +## Setup bifrost Project + +- [ ] Copy and rename this folder to active/container_bifrost +- [ ] Find and replace bifrost with the name of the service. +- [ ] Create the rootless user to run the podman containers +- [ ] Write the compose.yaml spec for your service +- [ ] Convert the compose.yaml spec to a quadlet +- [ ] Install the quadlet on the podman server +- [ ] Expose the quadlet service +- [ ] Install a backup service and timer + +## Install bifrost + +### Create the ai user + +```bash +# SSH into your podman server as root +useradd ai +loginctl enable-linger $(id -u ai) +systemctl --user --machine=ai@.host enable podman-restart +systemctl --user --machine=ai@.host enable --now podman.socket +mkdir -p /home/ai/.config/containers/systemd +``` + +### Write the bifrost compose spec + +Edit the compose.yaml at active/container_bifrost/compose/compose.yaml + +#### A Note on Volumes + +Named volumes are stored at `/home/bifrost/.local/share/containers/storage/volumes/`. + +### Convert bifrost compose spec to quadlets + +Run the following to convert a compose.yaml into the various `.container` files for systemd: + +```bash +# Generate the systemd service +podman run \ +--security-opt label=disable \ +--rm \ +-v $(pwd)/active/container_bifrost/compose:/compose \ +-v $(pwd)/active/container_bifrost/quadlets:/quadlets \ +quay.io/k9withabone/podlet \ +-f /quadlets \ +-i \ +--overwrite \ +compose /compose/compose.yaml + +# Copy the files to the server +export PODMAN_SERVER=ai-ai +scp -r active/container_bifrost/quadlets/. $PODMAN_SERVER:/home/ai/.config/containers/systemd/ +``` + +### Start and enable your systemd quadlet + +SSH into your podman server as root: + +```bash +systemctl --user daemon-reload +systemctl --user restart bifrost +journalctl --user -u bifrost -f +# Enable auto-update service which will pull new container images automatically every day +systemctl --user enable --now podman-auto-update.timer +``` + +### Expose bifrost + +1. If you need a domain, follow the [DDNS instructions](/active/container_ddns/ddns.md#install-a-new-ddns-service) +2. For a web service, follow the [Caddy instructions](/active/container_caddy/caddy.md#adding-a-new-caddy-record) +3. Finally, follow your OS's guide for opening ports via its firewall service. + +## Using bifrost + +### Adding Models + +```json +// qwen3.5-35b-a3b-thinking +{ + "temperature": 1, + "top_p": 0.95, + "presence_penalty": 1.5, + "extra_body": { + "top_k": 20, + "min_p": 0, + "repetition_penalty": 1, + "chat_template_kwargs": { + "enable_thinking": true + } + } +} + +// qwen3.5-35b-a3b-coding +{ + "temperature": 0.6, + "top_p": 0.95, + "presence_penalty": 0, + "extra_body": { + "top_k": 20, + "min_p": 0, + "repetition_penalty": 1, + "chat_template_kwargs": { + "enable_thinking": true + } + } +} + +// qwen3.5-35b-a3b-instruct +{ + "temperature": 0.7, + "top_p": 0.8, + "presence_penalty": 1.5, + "extra_body": { + "top_k": 20, + "min_p": 0, + "repetition_penalty": 1, + "chat_template_kwargs": { + "enable_thinking": false + } + } +} +``` + +### Testing Models + +```bash +# List models +curl -L -X GET 'https://aipi.reeseapps.com/v1/models' \ +-H 'Content-Type: application/json' \ +-H 'Authorization: Bearer sk-1234' + +curl -L -X POST 'https://aipi.reeseapps.com/v1/chat/completions' \ +-H 'Content-Type: application/json' \ +-H 'Authorization: Bearer sk-1234' \ +-d '{ + "model": "gpt-4o-mini", # 👈 REPLACE with 'public model name' for any db-model + "messages": [ + { + "content": "Hey, how's it going", + "role": "user" + } + ], +}' +``` + +## Backup bifrost + +Follow the [Borg Backup instructions](/active/systemd_borg/borg.md#set-up-a-client-for-backup) + +## Upgrade bifrost + +### Upgrade Quadlets + +Upgrades should be a repeat of [writing the compose spec](#convert-bifrost-compose-spec-to-quadlets) and [installing the quadlets](#start-and-enable-your-systemd-quadlet) + +```bash +export PODMAN_SERVER= +scp -r quadlets/. $PODMAN_SERVER$:/home/bifrost/.config/containers/systemd/ +ssh bifrost systemctl --user daemon-reload +ssh bifrost systemctl --user restart bifrost +``` + +## Uninstall + +```bash +# Stop the user's services +systemctl --user disable podman-restart +podman container stop --all +systemctl --user disable --now podman.socket +systemctl --user disable --now podman-auto-update.timer + +# Delete the user (this won't delete their home directory) +# userdel might spit out an error like: +# userdel: user bifrost is currently used by process 591255 +# kill those processes and try again +userdel bifrost +``` + +## Notes + +### SELinux + + + +:z allows a container to share a mounted volume with all other containers. + +:Z allows a container to reserve a mounted volume and prevents any other container from accessing. diff --git a/active/container_bifrost/compose/README.md b/active/container_bifrost/compose/README.md new file mode 100644 index 0000000..54893f3 --- /dev/null +++ b/active/container_bifrost/compose/README.md @@ -0,0 +1,3 @@ +# Compose + +Put your compose.yaml here. diff --git a/active/container_bifrost/compose/compose.yaml b/active/container_bifrost/compose/compose.yaml new file mode 100644 index 0000000..b6cdbf8 --- /dev/null +++ b/active/container_bifrost/compose/compose.yaml @@ -0,0 +1,32 @@ +services: + bifrost: + image: docker.io/maximhq/bifrost:latest + container_name: bifrost + ports: + - "8000:8000" + volumes: + - bifrost-data:/app/data + environment: + - APP_PORT=8000 + - APP_HOST=0.0.0.0 + - LOG_LEVEL=info + - LOG_STYLE=json + ulimits: + nofile: + soft: 65536 + hard: 65536 + healthcheck: + test: + [ + "CMD", + "wget", + "--no-verbose", + "--tries=1", + "-O", + "/dev/null", + "http://localhost:8080/health", + ] + interval: 30s + timeout: 10s + retries: 3 + restart: unless-stopped diff --git a/active/container_bifrost/quadlets/bifrost.container b/active/container_bifrost/quadlets/bifrost.container new file mode 100644 index 0000000..d998733 --- /dev/null +++ b/active/container_bifrost/quadlets/bifrost.container @@ -0,0 +1,17 @@ +[Container] +ContainerName=bifrost +Environment=APP_PORT=8000 APP_HOST=0.0.0.0 LOG_LEVEL=info LOG_STYLE=json +HealthCmd=["wget", "--no-verbose", "--tries=1", "-O", "/dev/null", "http://localhost:8080/health"] +HealthInterval=30s +HealthRetries=3 +HealthTimeout=10s +Image=docker.io/maximhq/bifrost:latest +PublishPort=8000:8000 +Ulimit=nofile=65536:65536 +Volume=bifrost-data:/app/data + +[Service] +Restart=always + +[Install] +WantedBy=default.target