===== HOST ===== Hostname: nh3-ml1 Date: 2026-09-25T22:51:53+00:00 Uptime: up 18 minutes OS: Debian GNU/Linux 12 (bookworm) Kernel: 6.8.12-43-pve Arch: x86_64 ===== HARDWARE ===== CPU cores: 6 CPU model: 13th Gen Intel(R) Core(TM) i9-13900H MemTotal: 16.0 GB MemAvailable: 13.1 GB ===== GPUS ===== index, name, memory.total [MiB], memory.free [MiB], driver_version 0, NVIDIA RTX 2000E Ada Generation, 16380 MiB, 13390 MiB, 580.178.04 ===== FILESYSTEMS (df) ===== Filesystem Size Used Avail Use% Mounted on rpool/data/subvol-109-disk-0 80G 12G 69G 15% / ===== PERSISTENT MOUNTS (/etc/fstab, non-comment) ===== ===== TARGETED DATA PATHS ===== /opt (total: 3.2G) total 11 drwxr-xr-x 5 root root 5 2026-09-25 22:30 . drwxr-xr-x 17 root root 21 2026-09-25 22:33 .. drwxrwsr-x 4 root docker 4 2026-09-25 22:35 aimodels drwx--x--x 4 root root 4 2026-09-25 22:30 containerd drwxrwsr-x 4 root docker 4 2026-09-25 22:30 docker /opt/docker (total: 131K) total 2 drwxrwsr-x 4 root docker 4 2026-09-25 22:30 . drwxr-xr-x 5 root root 5 2026-09-25 22:30 .. drwxrwsr-x 5 root docker 5 2026-09-25 22:49 compose drwxrwsr-x 2 root docker 2 2026-09-25 22:30 conf /opt/docker/compose (total: 130K) total 27 drwxrwsr-x 5 root docker 5 2026-09-25 22:49 . drwxrwsr-x 4 root docker 4 2026-09-25 22:30 .. drwxr-sr-x 4 infra-ops docker 8 2026-09-25 22:43 beszel drwxr-sr-x 2 infra-ops docker 6 2026-09-25 22:49 dozzle-agent drwxr-sr-x 2 infra-ops docker 6 2026-09-25 22:35 embed-rerank /opt/docker/conf (total: 512) total 1 drwxrwsr-x 2 root docker 2 2026-09-25 22:30 . drwxrwsr-x 4 root docker 4 2026-09-25 22:30 .. /var/lib/docker (total: 8.5K) /srv (total: 512) total 9 drwxr-xr-x 2 root root 2 2025-09-07 15:14 . drwxr-xr-x 17 root root 21 2026-09-25 22:33 .. ===== DOCKER ===== Server: 29.8.1 Client: 29.8.1 ----- docker info ----- Containers: 4 (running 4, paused 0, stopped 0) Images: 4 Runtimes: map[io.containerd.runc.v2:{{runc [] map[]} map[org.opencontainers.runtime-spec.features:{"ociVersionMin":"1.0.0","ociVersionMax":"1.3.0","hooks":["prestart","createRuntime","createContainer","startContainer","poststart","poststop"],"mountOptions":["async","atime","bind","defaults","dev","diratime","dirsync","exec","iversion","lazytime","loud","mand","noatime","nodev","nodiratime","noexec","noiversion","nolazytime","nomand","norelatime","nostrictatime","nosuid","nosymfollow","private","ratime","rbind","rdev","rdiratime","relatime","remount","rexec","rnoatime","rnodev","rnodiratime","rnoexec","rnorelatime","rnostrictatime","rnosuid","rnosymfollow","ro","rprivate","rrelatime","rro","rrw","rshared","rslave","rstrictatime","rsuid","rsymfollow","runbindable","rw","shared","silent","slave","strictatime","suid","symfollow","sync","tmpcopyup","unbindable"],"linux":{"namespaces":["cgroup","ipc","mount","network","pid","time","user","uts"],"capabilities":["CAP_CHOWN","CAP_DAC_OVERRIDE","CAP_DAC_READ_SEARCH","CAP_FOWNER","CAP_FSETID","CAP_KILL","CAP_SETGID","CAP_SETUID","CAP_SETPCAP","CAP_LINUX_IMMUTABLE","CAP_NET_BIND_SERVICE","CAP_NET_BROADCAST","CAP_NET_ADMIN","CAP_NET_RAW","CAP_IPC_LOCK","CAP_IPC_OWNER","CAP_SYS_MODULE","CAP_SYS_RAWIO","CAP_SYS_CHROOT","CAP_SYS_PTRACE","CAP_SYS_PACCT","CAP_SYS_ADMIN","CAP_SYS_BOOT","CAP_SYS_NICE","CAP_SYS_RESOURCE","CAP_SYS_TIME","CAP_SYS_TTY_CONFIG","CAP_MKNOD","CAP_LEASE","CAP_AUDIT_WRITE","CAP_AUDIT_CONTROL","CAP_SETFCAP","CAP_MAC_OVERRIDE","CAP_MAC_ADMIN","CAP_SYSLOG","CAP_WAKE_ALARM","CAP_BLOCK_SUSPEND","CAP_AUDIT_READ","CAP_PERFMON","CAP_BPF","CAP_CHECKPOINT_RESTORE"],"cgroup":{"v1":true,"v2":true,"systemd":true,"systemdUser":true,"rdma":true},"seccomp":{"enabled":true,"actions":["SCMP_ACT_ALLOW","SCMP_ACT_ERRNO","SCMP_ACT_KILL","SCMP_ACT_KILL_PROCESS","SCMP_ACT_KILL_THREAD","SCMP_ACT_LOG","SCMP_ACT_NOTIFY","SCMP_ACT_TRACE","SCMP_ACT_TRAP"],"operators":["SCMP_CMP_EQ","SCMP_CMP_GE","SCMP_CMP_GT","SCMP_CMP_LE","SCMP_CMP_LT","SCMP_CMP_MASKED_EQ","SCMP_CMP_NE"],"archs":["SCMP_ARCH_AARCH64","SCMP_ARCH_ARM","SCMP_ARCH_LOONGARCH64","SCMP_ARCH_MIPS","SCMP_ARCH_MIPS64","SCMP_ARCH_MIPS64N32","SCMP_ARCH_MIPSEL","SCMP_ARCH_MIPSEL64","SCMP_ARCH_MIPSEL64N32","SCMP_ARCH_PPC","SCMP_ARCH_PPC64","SCMP_ARCH_PPC64LE","SCMP_ARCH_RISCV64","SCMP_ARCH_S390","SCMP_ARCH_S390X","SCMP_ARCH_X32","SCMP_ARCH_X86","SCMP_ARCH_X86_64"],"knownFlags":["SECCOMP_FILTER_FLAG_TSYNC","SECCOMP_FILTER_FLAG_SPEC_ALLOW","SECCOMP_FILTER_FLAG_LOG","SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV"],"supportedFlags":["SECCOMP_FILTER_FLAG_TSYNC","SECCOMP_FILTER_FLAG_SPEC_ALLOW","SECCOMP_FILTER_FLAG_LOG"]},"apparmor":{"enabled":true},"selinux":{"enabled":true},"intelRdt":{"enabled":true,"schemata":true,"monitoring":true},"memoryPolicy":{"modes":["MPOL_BIND","MPOL_DEFAULT","MPOL_INTERLEAVE","MPOL_LOCAL","MPOL_PREFERRED","MPOL_PREFERRED_MANY","MPOL_WEIGHTED_INTERLEAVE"],"flags":["MPOL_F_NUMA_BALANCING","MPOL_F_RELATIVE_NODES","MPOL_F_STATIC_NODES"]},"mountExtensions":{"idmap":{"enabled":true}},"netDevices":{"enabled":true}},"annotations":{"io.github.seccomp.libseccomp.version":"2.5.4","org.opencontainers.runc.checkpoint.enabled":"true","org.opencontainers.runc.commit":"v1.5.1-0-g8f2685a4","org.opencontainers.runc.version":"1.5.1"},"potentiallyUnsafeConfigAnnotations":["bundle","org.systemd.property.","org.criu.config"]}]} nvidia:{{nvidia-container-runtime [] map[]} map[org.opencontainers.runtime-spec.features:{"ociVersionMin":"1.0.0","ociVersionMax":"1.3.0","hooks":["prestart","createRuntime","createContainer","startContainer","poststart","poststop"],"mountOptions":["async","atime","bind","defaults","dev","diratime","dirsync","exec","iversion","lazytime","loud","mand","noatime","nodev","nodiratime","noexec","noiversion","nolazytime","nomand","norelatime","nostrictatime","nosuid","nosymfollow","private","ratime","rbind","rdev","rdiratime","relatime","remount","rexec","rnoatime","rnodev","rnodiratime","rnoexec","rnorelatime","rnostrictatime","rnosuid","rnosymfollow","ro","rprivate","rrelatime","rro","rrw","rshared","rslave","rstrictatime","rsuid","rsymfollow","runbindable","rw","shared","silent","slave","strictatime","suid","symfollow","sync","tmpcopyup","unbindable"],"linux":{"namespaces":["cgroup","ipc","mount","network","pid","time","user","uts"],"capabilities":["CAP_CHOWN","CAP_DAC_OVERRIDE","CAP_DAC_READ_SEARCH","CAP_FOWNER","CAP_FSETID","CAP_KILL","CAP_SETGID","CAP_SETUID","CAP_SETPCAP","CAP_LINUX_IMMUTABLE","CAP_NET_BIND_SERVICE","CAP_NET_BROADCAST","CAP_NET_ADMIN","CAP_NET_RAW","CAP_IPC_LOCK","CAP_IPC_OWNER","CAP_SYS_MODULE","CAP_SYS_RAWIO","CAP_SYS_CHROOT","CAP_SYS_PTRACE","CAP_SYS_PACCT","CAP_SYS_ADMIN","CAP_SYS_BOOT","CAP_SYS_NICE","CAP_SYS_RESOURCE","CAP_SYS_TIME","CAP_SYS_TTY_CONFIG","CAP_MKNOD","CAP_LEASE","CAP_AUDIT_WRITE","CAP_AUDIT_CONTROL","CAP_SETFCAP","CAP_MAC_OVERRIDE","CAP_MAC_ADMIN","CAP_SYSLOG","CAP_WAKE_ALARM","CAP_BLOCK_SUSPEND","CAP_AUDIT_READ","CAP_PERFMON","CAP_BPF","CAP_CHECKPOINT_RESTORE"],"cgroup":{"v1":true,"v2":true,"systemd":true,"systemdUser":true,"rdma":true},"seccomp":{"enabled":true,"actions":["SCMP_ACT_ALLOW","SCMP_ACT_ERRNO","SCMP_ACT_KILL","SCMP_ACT_KILL_PROCESS","SCMP_ACT_KILL_THREAD","SCMP_ACT_LOG","SCMP_ACT_NOTIFY","SCMP_ACT_TRACE","SCMP_ACT_TRAP"],"operators":["SCMP_CMP_EQ","SCMP_CMP_GE","SCMP_CMP_GT","SCMP_CMP_LE","SCMP_CMP_LT","SCMP_CMP_MASKED_EQ","SCMP_CMP_NE"],"archs":["SCMP_ARCH_AARCH64","SCMP_ARCH_ARM","SCMP_ARCH_LOONGARCH64","SCMP_ARCH_MIPS","SCMP_ARCH_MIPS64","SCMP_ARCH_MIPS64N32","SCMP_ARCH_MIPSEL","SCMP_ARCH_MIPSEL64","SCMP_ARCH_MIPSEL64N32","SCMP_ARCH_PPC","SCMP_ARCH_PPC64","SCMP_ARCH_PPC64LE","SCMP_ARCH_RISCV64","SCMP_ARCH_S390","SCMP_ARCH_S390X","SCMP_ARCH_X32","SCMP_ARCH_X86","SCMP_ARCH_X86_64"],"knownFlags":["SECCOMP_FILTER_FLAG_TSYNC","SECCOMP_FILTER_FLAG_SPEC_ALLOW","SECCOMP_FILTER_FLAG_LOG","SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV"],"supportedFlags":["SECCOMP_FILTER_FLAG_TSYNC","SECCOMP_FILTER_FLAG_SPEC_ALLOW","SECCOMP_FILTER_FLAG_LOG"]},"apparmor":{"enabled":true},"selinux":{"enabled":true},"intelRdt":{"enabled":true,"schemata":true,"monitoring":true},"memoryPolicy":{"modes":["MPOL_BIND","MPOL_DEFAULT","MPOL_INTERLEAVE","MPOL_LOCAL","MPOL_PREFERRED","MPOL_PREFERRED_MANY","MPOL_WEIGHTED_INTERLEAVE"],"flags":["MPOL_F_NUMA_BALANCING","MPOL_F_RELATIVE_NODES","MPOL_F_STATIC_NODES"]},"mountExtensions":{"idmap":{"enabled":true}},"netDevices":{"enabled":true}},"annotations":{"io.github.seccomp.libseccomp.version":"2.5.4","org.opencontainers.runc.checkpoint.enabled":"true","org.opencontainers.runc.commit":"v1.5.1-0-g8f2685a4","org.opencontainers.runc.version":"1.5.1"},"potentiallyUnsafeConfigAnnotations":["bundle","org.systemd.property.","org.criu.config"]}]} runc:{{runc [] map[]} map[org.opencontainers.runtime-spec.features:{"ociVersionMin":"1.0.0","ociVersionMax":"1.3.0","hooks":["prestart","createRuntime","createContainer","startContainer","poststart","poststop"],"mountOptions":["async","atime","bind","defaults","dev","diratime","dirsync","exec","iversion","lazytime","loud","mand","noatime","nodev","nodiratime","noexec","noiversion","nolazytime","nomand","norelatime","nostrictatime","nosuid","nosymfollow","private","ratime","rbind","rdev","rdiratime","relatime","remount","rexec","rnoatime","rnodev","rnodiratime","rnoexec","rnorelatime","rnostrictatime","rnosuid","rnosymfollow","ro","rprivate","rrelatime","rro","rrw","rshared","rslave","rstrictatime","rsuid","rsymfollow","runbindable","rw","shared","silent","slave","strictatime","suid","symfollow","sync","tmpcopyup","unbindable"],"linux":{"namespaces":["cgroup","ipc","mount","network","pid","time","user","uts"],"capabilities":["CAP_CHOWN","CAP_DAC_OVERRIDE","CAP_DAC_READ_SEARCH","CAP_FOWNER","CAP_FSETID","CAP_KILL","CAP_SETGID","CAP_SETUID","CAP_SETPCAP","CAP_LINUX_IMMUTABLE","CAP_NET_BIND_SERVICE","CAP_NET_BROADCAST","CAP_NET_ADMIN","CAP_NET_RAW","CAP_IPC_LOCK","CAP_IPC_OWNER","CAP_SYS_MODULE","CAP_SYS_RAWIO","CAP_SYS_CHROOT","CAP_SYS_PTRACE","CAP_SYS_PACCT","CAP_SYS_ADMIN","CAP_SYS_BOOT","CAP_SYS_NICE","CAP_SYS_RESOURCE","CAP_SYS_TIME","CAP_SYS_TTY_CONFIG","CAP_MKNOD","CAP_LEASE","CAP_AUDIT_WRITE","CAP_AUDIT_CONTROL","CAP_SETFCAP","CAP_MAC_OVERRIDE","CAP_MAC_ADMIN","CAP_SYSLOG","CAP_WAKE_ALARM","CAP_BLOCK_SUSPEND","CAP_AUDIT_READ","CAP_PERFMON","CAP_BPF","CAP_CHECKPOINT_RESTORE"],"cgroup":{"v1":true,"v2":true,"systemd":true,"systemdUser":true,"rdma":true},"seccomp":{"enabled":true,"actions":["SCMP_ACT_ALLOW","SCMP_ACT_ERRNO","SCMP_ACT_KILL","SCMP_ACT_KILL_PROCESS","SCMP_ACT_KILL_THREAD","SCMP_ACT_LOG","SCMP_ACT_NOTIFY","SCMP_ACT_TRACE","SCMP_ACT_TRAP"],"operators":["SCMP_CMP_EQ","SCMP_CMP_GE","SCMP_CMP_GT","SCMP_CMP_LE","SCMP_CMP_LT","SCMP_CMP_MASKED_EQ","SCMP_CMP_NE"],"archs":["SCMP_ARCH_AARCH64","SCMP_ARCH_ARM","SCMP_ARCH_LOONGARCH64","SCMP_ARCH_MIPS","SCMP_ARCH_MIPS64","SCMP_ARCH_MIPS64N32","SCMP_ARCH_MIPSEL","SCMP_ARCH_MIPSEL64","SCMP_ARCH_MIPSEL64N32","SCMP_ARCH_PPC","SCMP_ARCH_PPC64","SCMP_ARCH_PPC64LE","SCMP_ARCH_RISCV64","SCMP_ARCH_S390","SCMP_ARCH_S390X","SCMP_ARCH_X32","SCMP_ARCH_X86","SCMP_ARCH_X86_64"],"knownFlags":["SECCOMP_FILTER_FLAG_TSYNC","SECCOMP_FILTER_FLAG_SPEC_ALLOW","SECCOMP_FILTER_FLAG_LOG","SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV"],"supportedFlags":["SECCOMP_FILTER_FLAG_TSYNC","SECCOMP_FILTER_FLAG_SPEC_ALLOW","SECCOMP_FILTER_FLAG_LOG"]},"apparmor":{"enabled":true},"selinux":{"enabled":true},"intelRdt":{"enabled":true,"schemata":true,"monitoring":true},"memoryPolicy":{"modes":["MPOL_BIND","MPOL_DEFAULT","MPOL_INTERLEAVE","MPOL_LOCAL","MPOL_PREFERRED","MPOL_PREFERRED_MANY","MPOL_WEIGHTED_INTERLEAVE"],"flags":["MPOL_F_NUMA_BALANCING","MPOL_F_RELATIVE_NODES","MPOL_F_STATIC_NODES"]},"mountExtensions":{"idmap":{"enabled":true}},"netDevices":{"enabled":true}},"annotations":{"io.github.seccomp.libseccomp.version":"2.5.4","org.opencontainers.runc.checkpoint.enabled":"true","org.opencontainers.runc.commit":"v1.5.1-0-g8f2685a4","org.opencontainers.runc.version":"1.5.1"},"potentiallyUnsafeConfigAnnotations":["bundle","org.systemd.property.","org.criu.config"]}]}] Default runtime: runc Storage driver: overlayfs Root dir: /var/lib/docker Server version: 29.8.1 ----- running containers ----- NAMES IMAGE STATUS PORTS dozzle-agent amir20/dozzle:v10.4.1 Up About a minute 10.100.50.80:7007->7007/tcp, 8080/tcp beszel-agent henrygd/beszel-agent-nvidia:0.18.7 Up 7 minutes (healthy) tei-rerank ghcr.io/huggingface/text-embeddings-inference:89-1.9.4 Up 15 minutes (healthy) 0.0.0.0:8013->80/tcp, [::]:8013->80/tcp tei-embed ghcr.io/huggingface/text-embeddings-inference:89-1.9.4 Up 15 minutes (healthy) 0.0.0.0:8001->80/tcp, [::]:8001->80/tcp ----- all containers ----- NAMES IMAGE STATUS dozzle-agent amir20/dozzle:v10.4.1 Up About a minute beszel-agent henrygd/beszel-agent-nvidia:0.18.7 Up 7 minutes (healthy) tei-rerank ghcr.io/huggingface/text-embeddings-inference:89-1.9.4 Up 15 minutes (healthy) tei-embed ghcr.io/huggingface/text-embeddings-inference:89-1.9.4 Up 15 minutes (healthy) ----- networks ----- NAME DRIVER SCOPE bridge bridge local embed-rerank_default bridge local host host local none null local traefik-net bridge local ----- networks (external, non-default — worth knowing for compose external: true) ----- embed-rerank_default traefik-net ----- named volumes ----- VOLUME NAME DRIVER beszel_beszel_agent_data local dozzle-agent_dozzle_agent_data local ----- compose projects currently running ----- beszel dozzle-agent embed-rerank ===== COMPOSE FILES (/opt/docker/compose/) ===== >>> /opt/docker/compose/beszel/compose.yaml # Beszel — lightweight server/container monitoring. # # Hub: single web UI with the SQLite store. Agents: per-host metric collectors # that the hub pulls from over SSH. # # Multi-host layout via compose profiles: # COMPOSE_PROFILES=hub → hub only (ana-docker) # COMPOSE_PROFILES=hub,agent → hub + local agent on the same host # COMPOSE_PROFILES=agent → agent only (ana-ml2, nh3-docker, # esh-docker-vm, vm-esh-nas) # # The agent uses network_mode: host so it sees real host CPU/mem/net/disk # counters rather than container-scoped ones — that's why it can't share # the tnet network with the hub. # # All tunables live in .env — edit that, not this file. services: beszel: image: henrygd/beszel:${BESZEL_VERSION} container_name: beszel profiles: [hub] restart: unless-stopped ports: - "${BESZEL_PORT}:8090" volumes: - beszel_data:/beszel_data healthcheck: # Hub image is distroless — no wget/curl. Use the bundled `/beszel` # binary's built-in health subcommand (https://beszel.dev/guide/healthchecks). test: ["CMD", "/beszel", "health", "--url", "http://localhost:8090"] interval: 120s timeout: 10s retries: 3 start_period: 15s networks: - tnet labels: - homepage.group=Monitoring - homepage.name=Beszel - homepage.icon=mdi-chart-line - homepage.description=Server + container monitoring - homepage.href=http://10.250.50.70:${BESZEL_PORT} - homepage.widget.type=beszel - homepage.widget.url=http://10.250.50.70:${BESZEL_PORT} - homepage.widget.version=2 - homepage.widget.username={{HOMEPAGE_VAR_BESZEL_USERNAME}} - homepage.widget.password={{HOMEPAGE_VAR_BESZEL_PASSWORD}} beszel-agent: image: henrygd/beszel-agent:${BESZEL_VERSION} container_name: beszel-agent profiles: [agent] restart: unless-stopped network_mode: host volumes: - /var/run/docker.sock:/var/run/docker.sock:ro - beszel_agent_data:/var/lib/beszel-agent environment: # Agent auth has two modes (v0.13+ supports both side-by-side): # - KEY-mode: agent listens, hub connects inbound over SSH using KEY. # Requires BESZEL_HUB_KEY in .env. # - Token-mode: agent initiates an outbound connection to HUB_URL # using TOKEN. Easier through NAT. Requires HUB_URL + BESZEL_TOKEN. # Leave unused ones empty ("") in .env; both can be set simultaneously. - PORT=${BESZEL_AGENT_PORT:-45876} - KEY=${BESZEL_HUB_KEY:-} - HUB_URL=${HUB_URL:-} - TOKEN=${BESZEL_TOKEN:-} - EXTRA_FILESYSTEMS=${BESZEL_EXTRA_FS:-} healthcheck: # Agent image ships the `/agent` binary with a `health` subcommand. # Verifies the agent process is up — not that the hub can reach it. test: ["CMD", "/agent", "health"] interval: 120s timeout: 10s retries: 3 start_period: 15s volumes: beszel_data: beszel_agent_data: networks: tnet: name: traefik-net external: true >>> /opt/docker/compose/beszel/synology/compose.yaml services: beszel-agent: image: henrygd/beszel-agent:0.18.7 container_name: beszel-agent restart: unless-stopped network_mode: host volumes: - ./agent-data:/var/lib/beszel-agent - /var/run/docker.sock:/var/run/docker.sock:ro - /usr/share/zoneinfo:/extra-filesystems/system:ro - ./:/extra-filesystems/volume1:ro environment: PORT: '45876' KEY: 'ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIHdG5fWcEZHK45sRlx8kyvrd9agexKQv4QK9Dc07wTLt' FILESYSTEM: /extra-filesystems/system EXTRA_FILESYSTEMS: /extra-filesystems/volume1 >>> /opt/docker/compose/dozzle-agent/compose.yaml # Dozzle — container log viewer. # # Multi-host layout via compose profiles: # COMPOSE_PROFILES=hub → runs the web UI (deploy on ana-docker) # COMPOSE_PROFILES=agent → runs the remote agent (deploy on ana-ml2) # # Same compose.yaml on both servers; per-host `.env` picks the profile. # # All tunables live in .env — edit that, not this file. services: dozzle: image: amir20/dozzle:${DOZZLE_VERSION} container_name: dozzle profiles: [hub] restart: unless-stopped ports: - "${DOZZLE_PORT}:8080" volumes: - /var/run/docker.sock:/var/run/docker.sock:ro - dozzle_data:/data environment: - DOZZLE_HOSTNAME=${DOZZLE_HOSTNAME} - DOZZLE_REMOTE_AGENT=${DOZZLE_REMOTE_AGENT:-} - DOZZLE_AUTH_PROVIDER=${DOZZLE_AUTH_PROVIDER:-none} - DOZZLE_USERNAME=${DOZZLE_USERNAME:-} - DOZZLE_PASSWORD=${DOZZLE_PASSWORD:-} healthcheck: test: ["CMD", "/dozzle", "healthcheck"] interval: 30s timeout: 10s retries: 3 start_period: 15s networks: - tnet labels: - homepage.group=Monitoring - homepage.name=Dozzle - homepage.icon=mdi-text-box-search - homepage.description=Container logs (ana-docker + ana-ml2) - homepage.href=http://10.250.50.70:${DOZZLE_PORT} dozzle-agent: image: amir20/dozzle:${DOZZLE_VERSION} container_name: dozzle-agent profiles: [agent] restart: unless-stopped command: agent ports: - "${DOZZLE_AGENT_BIND:-0.0.0.0}:${DOZZLE_AGENT_PORT}:7007" volumes: - /var/run/docker.sock:/var/run/docker.sock:ro - dozzle_agent_data:/data environment: - DOZZLE_HOSTNAME=${DOZZLE_HOSTNAME} networks: - tnet volumes: dozzle_data: dozzle_agent_data: networks: tnet: name: traefik-net external: true >>> /opt/docker/compose/embed-rerank/compose.yaml # embed-rerank — THE fleet's embedding + reranking service, on esh-ml1 (CT 110 on # esh-pve, RTX 2000E Ada, 16 GB). Served by Hugging Face Text Embeddings # Inference (TEI). A second instance runs on nh3-ml1 (CT 109 on nh3-pve, the same # card) since 2026-09-25; the per-host bits are HOST_NAME / HOST_IP in .env, and # their defaults are esh-ml1's, so esh-ml1's live .env needs no change. # # Prime, 2026-09-25: "TEI is embed/reranker server for esh-ml1 and the FLEET in # general, in future." It replaced vLLM here the same day, after a side-by-side # bake-off on this card (docs/pfi/embed-rerank-tei-vs-vllm-bakeoff.md). TEI # gives the same vectors as the old vLLM seats (no re-embedding), but it is # ~1.3x slower on bulk work on this card. It is much lighter (2.6 GB VRAM for # both, 8 GB image, ~4 s restart). fv-ml1's vLLM embed/rerank seats were # retired after this went live. # # tei-embed Qwen/Qwen3-Embedding-0.6B → /v1/embeddings (OpenAI), /embed :8001 # tei-rerank BAAI/bge-reranker-v2-m3 → /rerank (body: query + texts) :8013 # # Ports kept from the vLLM era (and fv-ml1), so the embedding gateway entry did # not change address. ⚠ The RERANK gateway entry must use LiteLLM's # `huggingface/` provider: `hosted_vllm/` sends `documents` and TEI answers 422 # "missing field texts". # # ⚠ Embedding vectors are model-specific. Never change EMBED_MODEL without a # re-embedding plan for every index built on it (Worldtree, nevermore, Open WebUI). # # FAIL-CLOSED truncation (--auto-truncate false). TEI's default silently # embedded the first 16,384 tokens of a ~40k-token input and returned 200. # Turning it off requires --max-batch-tokens >= the model's max input (32,768 # for Qwen3-Embedding), or TEI refuses to start. # # NO `tnet`/traefik-net: esh-ml1 runs no traefik; consumers reach the published # ports, and in practice only the LiteLLM gateway does (verified from the seats' # logs 2026-09-25: every request matched a gateway spend-log row). # # Host setup: playbooks/pve-nvidia-host.yaml, then playbooks/gpu-lxc.yaml. # Tunables live in .env. name: embed-rerank services: tei-embed: image: ghcr.io/huggingface/text-embeddings-inference:${TEI_TAG} container_name: tei-embed restart: unless-stopped ports: - "${EMBED_PORT}:80" volumes: - /opt/aimodels/tei-cache:/data environment: - HF_TOKEN=${HF_TOKEN:-} command: - --model-id - ${EMBED_MODEL} - --served-model-name - ${EMBED_MODEL} # TEI on CUDA is float16-only; parity vs the bf16 vLLM vectors was measured. - --dtype - float16 # Default 32; vLLM had no cap and callers batch 64. - --max-client-batch-size - "${MAX_CLIENT_BATCH_SIZE}" - --auto-truncate - "false" - --max-batch-tokens - "32768" deploy: resources: reservations: devices: - driver: nvidia device_ids: ["0"] capabilities: [gpu] healthcheck: test: ["CMD", "curl", "-fsS", "http://localhost:80/health"] interval: 30s timeout: 10s retries: 3 start_period: 60s labels: - homepage.group=AI - Eval & Retrieval - homepage.name=Embed — Qwen3 0.6B (TEI, ${HOST_NAME:-esh-ml1}) - homepage.icon=mdi-vector-arrange-below - homepage.description=Fleet embeddings (qwen3-embedding) via TEI on ${HOST_NAME:-esh-ml1} - homepage.href=http://${HOST_IP:-10.0.50.80}:${EMBED_PORT}/docs tei-rerank: image: ghcr.io/huggingface/text-embeddings-inference:${TEI_TAG} container_name: tei-rerank restart: unless-stopped ports: - "${RERANK_PORT}:80" volumes: - /opt/aimodels/tei-cache:/data environment: - HF_TOKEN=${HF_TOKEN:-} command: - --model-id - ${RERANK_MODEL} - --dtype - float16 - --max-client-batch-size - "${MAX_CLIENT_BATCH_SIZE}" # Fail-closed; bge-reranker-v2-m3's max input (8,192) fits the default # max-batch-tokens (16,384). - --auto-truncate - "false" deploy: resources: reservations: devices: - driver: nvidia device_ids: ["0"] capabilities: [gpu] healthcheck: test: ["CMD", "curl", "-fsS", "http://localhost:80/health"] interval: 30s timeout: 10s retries: 3 start_period: 60s labels: - homepage.group=AI - Eval & Retrieval - homepage.name=Rerank — bge-v2-m3 (TEI, ${HOST_NAME:-esh-ml1}) - homepage.icon=mdi-sort-variant - homepage.description=Fleet reranker (reranker) via TEI on ${HOST_NAME:-esh-ml1} - homepage.href=http://${HOST_IP:-10.0.50.80}:${RERANK_PORT}/docs ===== CONFIG LAYOUT (/opt/docker/conf/ — top 200 entries) ===== /opt/docker/conf ===== LISTENING PORTS ===== *:22 *:45876 0.0.0.0:8001 0.0.0.0:8013 10.100.50.80:2375 10.100.50.80:7007 127.0.0.1:25 [::1]:25 [::]:8001 [::]:8013 ===== MODEL / HUGGINGFACE CACHES ===== ===== DOCKER-ADJACENT SYSTEMD SERVICES ===== container-getty@1.service running container-getty@2.service running containerd.service running docker.service running ===== DONE ===== Paste the above back into the chat, or pass a path as argv[1] to save.