The user asked to drop it: nobody had the Gemini CLI login or a key set up, and Exa then Wikipedia cover the voice use. webSearch is now live Chrome, Exa, Brave (opt-in), Wikipedia. Removes the CLI/REST backends, the GEMINI_* settings, the Docker login mount and checks, and updates the specs and docs/llm_contexts.md. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
81 lines
3.7 KiB
Bash
Executable File
81 lines
3.7 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Container entrypoint: render config from env, set the VNC password, ensure the
|
|
# Piper voice exists, then hand off to supervisord (which runs the desktop,
|
|
# bridge, and bot).
|
|
set -euo pipefail
|
|
|
|
# --- Defaults (override via .env / compose) ---
|
|
: "${VNC_PASSWORD:=javis123}"
|
|
: "${VNC_RESOLUTION:=1920x1080}"
|
|
: "${OLLAMA_BASE_URL:=http://ollama:11434}"
|
|
: "${OLLAMA_CHAT_MODEL:=qwen3:8b}"
|
|
# Auxiliary small-model calls (intent judge, tool router, weather place
|
|
# extraction, query decomposition). Default to a small fast model so the big
|
|
# chat model only runs for the actual spoken answer — the main per-turn latency
|
|
# win once the GPU is in use, since the 2-3 routing/extraction calls per command
|
|
# no longer pay the big model's cost. ollama-init pulls this model. Set it equal
|
|
# to OLLAMA_CHAT_MODEL to fold everything back onto one resident model.
|
|
: "${OLLAMA_INTENT_MODEL:=qwen2.5:3b}"
|
|
# Cap chat-model output tokens per turn (worst-case latency guard). Spoken
|
|
# answers are 1-2 sentences; 512 is safe headroom above tool-call JSON. 0 = off.
|
|
: "${OLLAMA_NUM_PREDICT:=512}"
|
|
: "${OLLAMA_EMBED_MODEL:=nomic-embed-text}"
|
|
: "${WHISPER_MODEL:=small}"
|
|
: "${WHISPER_DEVICE:=cuda}"
|
|
: "${WHISPER_COMPUTE_TYPE:=float16}"
|
|
: "${JARVIS_DB_PATH:=/data/jarvis.db}"
|
|
: "${BRIDGE_HOST:=127.0.0.1}"
|
|
: "${BRIDGE_PORT:=8765}"
|
|
: "${PIPER_VOICE:=en_GB-alan-medium}"
|
|
: "${PIPER_VOICE_DIR:=/opt/piper-voices}"
|
|
: "${TTS_PIPER_MODEL_PATH:=${PIPER_VOICE_DIR}/${PIPER_VOICE}.onnx}"
|
|
|
|
# Audio: shared PulseAudio socket so Chrome (playback) and the selfbot ffmpeg
|
|
# (capture of @DEFAULT_MONITOR@) reach the same headless daemon (run-pulse.sh).
|
|
: "${XDG_RUNTIME_DIR:=/run/user/0}"
|
|
: "${PULSE_SERVER:=unix:${XDG_RUNTIME_DIR}/pulse/native}"
|
|
|
|
export VNC_RESOLUTION OLLAMA_BASE_URL OLLAMA_CHAT_MODEL OLLAMA_NUM_PREDICT OLLAMA_INTENT_MODEL OLLAMA_EMBED_MODEL \
|
|
WHISPER_MODEL WHISPER_DEVICE WHISPER_COMPUTE_TYPE JARVIS_DB_PATH \
|
|
PIPER_VOICE PIPER_VOICE_DIR TTS_PIPER_MODEL_PATH BRIDGE_HOST BRIDGE_PORT \
|
|
XDG_RUNTIME_DIR PULSE_SERVER
|
|
|
|
mkdir -p /data /app/config "$(dirname "$JARVIS_DB_PATH")"
|
|
|
|
# --- VNC password file ---
|
|
mkdir -p /root/.vnc
|
|
echo "$VNC_PASSWORD" | tigervncpasswd -f > /root/.vnc/passwd
|
|
chmod 600 /root/.vnc/passwd
|
|
|
|
# --- Render jarvis brain config from template ---
|
|
envsubst < /app/docker/jarvis-config.template.json > /app/config/jarvis.json
|
|
export JARVIS_CONFIG_PATH=/app/config/jarvis.json
|
|
# Merge persistent settings from the settings UI (on the /data volume) on top of
|
|
# the env-rendered config, so changes survive container recreate.
|
|
if [ -f /data/jarvis-settings.json ]; then
|
|
python3 - <<'PY' || true
|
|
import json, os
|
|
try:
|
|
base = json.load(open("/app/config/jarvis.json"))
|
|
ov = json.load(open("/data/jarvis-settings.json"))
|
|
if isinstance(base, dict) and isinstance(ov, dict):
|
|
base.update(ov)
|
|
# A stale persisted tts_engine from an earlier voice (melo/xtts, no
|
|
# longer built into the image) would override the configured engine and
|
|
# leave the bot silent. Reset those to the env-configured engine.
|
|
if base.get("tts_engine") in ("melo", "xtts"):
|
|
base["tts_engine"] = os.environ.get("TTS_ENGINE", "edge")
|
|
print(f"[entrypoint] reset stale tts_engine -> {base['tts_engine']}")
|
|
json.dump(base, open("/app/config/jarvis.json", "w"), ensure_ascii=False, indent=2)
|
|
print("[entrypoint] merged persistent settings overrides")
|
|
except Exception as e:
|
|
print(f"[entrypoint] settings merge skipped: {e}")
|
|
PY
|
|
fi
|
|
|
|
# --- Ensure the Piper voice exists (best effort) ---
|
|
bash /app/docker/download-piper.sh || echo "[entrypoint] piper download failed; TTS may be unavailable"
|
|
|
|
echo "[entrypoint] display=$DISPLAY ollama=$OLLAMA_BASE_URL whisper=$WHISPER_MODEL/$WHISPER_DEVICE"
|
|
exec supervisord -c /app/docker/supervisord.conf
|