35e754d6ee
Makes the all-in-one image actually run the new real-time-search features and closes review gaps: - Gemini OAuth path: install Node 22 + @google/gemini-cli (pinned 0.46.0) in the image; mount a DEDICATED host dir (~/.config/javis/gemini) holding only the OAuth creds to /root/.gemini (not the whole ~/.gemini). Verified in-container: `gemini -p ... -o json` returns a grounded answer with no API key. - Broadcast audio: add PulseAudio + a headless null-sink (run-pulse.sh, new supervisor program); export XDG_RUNTIME_DIR/PULSE_SERVER so Chrome playback and the selfbot `ffmpeg -f pulse -i @DEFAULT_MONITOR@` share one daemon. Verified: default sink virtual_speaker, monitor present, ffmpeg capture OK. - Bind the brain bridge to 127.0.0.1 only (internal, unauthenticated API). - VNC host port is overridable; this server pins VNC_PORT=5902 (.env) since the host already runs Xvnc on 5901. Verified in-container with CDI GPU passthrough: RTX 5050 visible, NVENC encoders (h264/hevc/av1) available. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
98 lines
4.0 KiB
YAML
98 lines
4.0 KiB
YAML
# ============================================================================
|
|
# Javis Bot — Docker Compose
|
|
# ollama : the LLM backend for the jarvis brain
|
|
# ollama-init : one-shot, auto-pulls the chat + embed models on startup
|
|
# javis : all-in-one container (VNC desktop + Chrome + bridge + bot)
|
|
#
|
|
# Just bring it up — everything (incl. Ollama models) comes up automatically:
|
|
# docker compose up -d --build
|
|
#
|
|
# The Discord token can be added LAST: without it the desktop, brain bridge,
|
|
# Ollama and models all run; only the bot waits. Then put DISCORD_BOT_TOKEN in
|
|
# .env and re-run `docker compose up -d`.
|
|
#
|
|
# Watch the desktop: VNC viewer -> localhost:5901 (or browser -> localhost:6080)
|
|
# ============================================================================
|
|
services:
|
|
ollama:
|
|
image: ollama/ollama:latest
|
|
restart: unless-stopped
|
|
volumes:
|
|
- ollama_models:/root/.ollama
|
|
# GPU: needs nvidia-container-toolkit on the host (CDI). Verified on the
|
|
# RTX 5050 (Blackwell sm_120) — Ollama offloads 100% to GPU.
|
|
devices:
|
|
- "nvidia.com/gpu=all"
|
|
|
|
# Auto-pull the models the brain needs, then exit. Idempotent (re-runnable).
|
|
ollama-init:
|
|
image: ollama/ollama:latest
|
|
depends_on:
|
|
- ollama
|
|
restart: "no"
|
|
environment:
|
|
OLLAMA_HOST: http://ollama:11434
|
|
CHAT_MODEL: ${OLLAMA_CHAT_MODEL:-qwen3:8b}
|
|
EMBED_MODEL: ${OLLAMA_EMBED_MODEL:-nomic-embed-text}
|
|
entrypoint: ["/bin/sh", "-c"]
|
|
command:
|
|
- |
|
|
echo "[ollama-init] waiting for ollama server...";
|
|
until ollama list >/dev/null 2>&1; do sleep 2; done;
|
|
echo "[ollama-init] pulling $$CHAT_MODEL";
|
|
ollama pull "$$CHAT_MODEL";
|
|
echo "[ollama-init] pulling $$EMBED_MODEL";
|
|
ollama pull "$$EMBED_MODEL";
|
|
echo "[ollama-init] models ready.";
|
|
|
|
javis:
|
|
build: .
|
|
restart: unless-stopped
|
|
env_file:
|
|
- path: .env
|
|
required: false
|
|
environment:
|
|
# Point the brain at the ollama service and the bot at the in-container bridge.
|
|
OLLAMA_BASE_URL: http://ollama:11434
|
|
OLLAMA_CHAT_MODEL: ${OLLAMA_CHAT_MODEL:-qwen3:8b}
|
|
OLLAMA_EMBED_MODEL: ${OLLAMA_EMBED_MODEL:-nomic-embed-text}
|
|
WHISPER_MODEL: ${WHISPER_MODEL:-small}
|
|
WHISPER_DEVICE: ${WHISPER_DEVICE:-cuda}
|
|
WHISPER_COMPUTE_TYPE: ${WHISPER_COMPUTE_TYPE:-float16}
|
|
BRIDGE_URL: http://127.0.0.1:8765
|
|
depends_on:
|
|
- ollama
|
|
# GPU: accelerates Whisper STT (and anything else CUDA) in this container.
|
|
# Verified: faster-whisper float16 works on the RTX 5050 (sm_120).
|
|
devices:
|
|
- "nvidia.com/gpu=all"
|
|
shm_size: "1gb" # Chrome needs a larger /dev/shm
|
|
ports:
|
|
# Host ports are overridable. If the HOST already runs VNC on 5901
|
|
# (see docs/vnc-xfce-setup.md), set VNC_PORT=5902 in .env — this server
|
|
# does, so .env pins VNC_PORT=5902.
|
|
- "${VNC_PORT:-5901}:5901" # VNC
|
|
- "${NOVNC_PORT:-6080}:6080" # noVNC (open in a browser)
|
|
# Brain bridge: bind to loopback only — it is an internal bot<->brain API
|
|
# with no auth and must not be reachable off-host.
|
|
- "127.0.0.1:${BRIDGE_PORT:-8765}:8765"
|
|
volumes:
|
|
- javis_data:/data # jarvis db + memory
|
|
- whisper_cache:/root/.cache/huggingface # cached Whisper models
|
|
- piper_voices:/opt/piper-voices # TTS voices
|
|
# Gemini account login for GEMINI_AUTH=oauth real-time search. Mounts a
|
|
# DEDICATED dir holding only the Gemini OAuth creds (not the whole
|
|
# ~/.gemini), so the container can refresh its token without exposing
|
|
# unrelated host state. Seed it once with the host login:
|
|
# mkdir -p ~/.config/javis/gemini
|
|
# cp ~/.gemini/oauth_creds.json ~/.config/javis/gemini/
|
|
# Override GEMINI_OAUTH_DIR to point elsewhere. Only used when
|
|
# GEMINI_AUTH=oauth.
|
|
- ${GEMINI_OAUTH_DIR:-${HOME}/.config/javis/gemini}:/root/.gemini
|
|
|
|
volumes:
|
|
ollama_models:
|
|
javis_data:
|
|
whisper_cache:
|
|
piper_voices:
|