Compare commits

...

10 Commits

4 changed files with 192 additions and 41 deletions

View File

@@ -1,71 +1,66 @@
FROM ghcr.io/astral-sh/uv:0.11.6-python3.13-trixie@sha256:b3c543b6c4f23a5f2df22866bd7857e5d304b67a564f4feab6ac22044dde719b AS uv_source
FROM tianon/gosu:1.19-trixie@sha256:3b176695959c71e123eb390d427efc665eeb561b1540e82679c15e992006b8b9 AS gosu_source
FROM debian:13.4
# 1. On récupère la version la plus récente d'UV
FROM ghcr.io/astral-sh/uv:latest AS uv_source
# 2. Image de base stable
FROM debian:stable-slim
# Disable Python stdout buffering to ensure logs are printed immediately
ENV PYTHONUNBUFFERED=1
# Store Playwright browsers outside the volume mount so the build-time
# install survives the /opt/data volume overlay at runtime.
ENV PLAYWRIGHT_BROWSERS_PATH=/opt/hermes/.playwright
# Install system dependencies in one layer, clear APT cache
# tini reaps orphaned zombie processes (MCP stdio subprocesses, git, bun, etc.)
# that would otherwise accumulate when hermes runs as PID 1. See #15012.
RUN apt-get update && \
apt-get install -y --no-install-recommends \
build-essential nodejs npm python3 ripgrep ffmpeg gcc python3-dev libffi-dev procps git openssh-client docker-cli tini \
build-essential python3 ripgrep ffmpeg gcc python3-dev libffi-dev procps git openssh-client docker-cli tini \
curl poppler-utils imagemagick \
chromium xvfb fonts-noto-color-emoji fonts-unifont fonts-liberation fonts-ipafont-gothic fonts-wqy-zenhei fonts-tlwg-loma-otf fonts-freefont-ttf \
libasound2t64 libatk-bridge2.0-0t64 libatk1.0-0t64 libatspi2.0-0t64 libcairo2 libcups2t64 libdbus-1-3 libdrm2 libgbm1 libglib2.0-0t64 libnspr4 libnss3 libpango-1.0-0 libx11-6 libxcb1 libxcomposite1 libxdamage1 libxext6 libxfixes3 libxkbcommon0 libxrandr2 \
texlive-latex-base texlive-latex-extra texlive-fonts-recommended texlive-xetex texlive-science \
qemu-user-static binfmt-support qemu-user-binfmt \
emacs-nox \
libportaudio2 && \
rm -rf /var/lib/apt/lists/*
# Non-root user for runtime; UID can be overridden via HERMES_UID at runtime
# Création de l'utilisateur 'hermes' directement avec les bons accès
RUN useradd -u 10000 -m -d /opt/data hermes
COPY --chmod=0755 --from=gosu_source /gosu /usr/local/bin/
COPY --chmod=0755 --from=uv_source /usr/local/bin/uv /usr/local/bin/uvx /usr/local/bin/
# Copie d'uv (dernière version)
COPY --chmod=0755 --from=uv_source /uv /usr/local/bin/
WORKDIR /opt/hermes
# ---------- Layer-cached dependency install ----------
# Copy only package manifests first so npm install + Playwright are cached
# unless the lockfiles themselves change.
COPY package.json package-lock.json ./
COPY web/package.json web/package-lock.json web/
# On donne la propriété du dossier de travail à l'utilisateur hermes
RUN chown hermes:hermes /opt/hermes
RUN npm install --prefer-offline --no-audit && \
npx playwright install --with-deps chromium --only-shell && \
(cd web && npm install --prefer-offline --no-audit) && \
npm cache clean --force
# ---------- Hermes venv ----------
# Passer immédiatement sous l'utilisateur hermes pour tout le reste du build
USER hermes
# ---------- Source code ----------
# .dockerignore excludes node_modules, so the installs above survive.
# On copie tout le projet d'un coup sans assumer la présence de fichiers de lock spécifiques
COPY --chown=hermes:hermes . .
# Build web dashboard (Vite outputs to hermes_cli/web_dist/)
RUN cd web && npm run build
# ---------- Permissions ----------
# Make install dir world-readable so any HERMES_UID can read it at runtime.
# The venv needs to be traversable too.
USER root
RUN chmod -R a+rX /opt/hermes
# Start as root so the entrypoint can usermod/groupmod + gosu.
# If HERMES_UID is unset, the entrypoint drops to the default hermes user (10000).
# ---------- Python virtualenv ----------
# ---------- Python virtualenv avec Piper TTS ----------
RUN uv venv && \
uv pip install --no-cache-dir -e ".[all]" && \
uv pip install --no-cache-dir sounddevice numpy faster-whisper
uv pip install --no-cache-dir piper-tts sounddevice numpy faster-whisper
# ---------- Télécharger la voix Piper Ryan ----------
RUN mkdir -p /opt/hermes/.venv/share/piper/voices && \
/opt/hermes/.venv/bin/python3 -c "
import urllib.request
base = '/opt/hermes/.venv/share/piper/voices'
url = 'https://huggingface.co/rhasspy/piper-voices/resolve/main/en/en_US/ryan/high/en_US-ryan-high.onnx'
urllib.request.urlretrieve(url + '?download=true', base + '/en_US-ryan-high.onnx')
urllib.request.urlretrieve(url + '.onnx.json?download=true', base + '/en_US-ryan-high.onnx.json')
"
# ---------- Patch tts_tool.py: remplacer Coqui par Piper, supprimer Edge ----------
COPY ai/patch_tts_tool.py /tmp/patch_tts_tool.py
RUN /opt/hermes/.venv/bin/python3 /tmp/patch_tts_tool.py && rm /tmp/patch_tts_tool.py
# ---------- Runtime ----------
ENV HERMES_WEB_DIST=/opt/hermes/hermes_cli/web_dist
ENV HERMES_HOME=/opt/data
ENV PATH="/opt/data/.local/bin:${PATH}"
VOLUME [ "/opt/data" ]
# Le conteneur tourne de manière ultra-sécurisée sous l'utilisateur hermes dès le départ
ENTRYPOINT [ "/usr/bin/tini", "-g", "--", "/opt/hermes/docker/entrypoint.sh" ]

View File

@@ -39,6 +39,12 @@ services:
- API_SERVER_KEY=hermes_local_key
- GATEWAY_ALLOW_ALL_USERS=true
- OPENROUTER_API_KEY=${OPENROUTER_API_KEY}
# ROCm for GPU-accelerated faster-whisper STT
- HSA_OVERRIDE_GFX_VERSION=9.0.6
- HCC_AMDGPU_TARGET=gfx906
- HIP_VISIBLE_DEVICES=0,1
- ROCR_VISIBLE_DEVICES=0,1
- HSA_ENABLE_SDMA=0
volumes:
- /mnt/HoardingCow_docker_data/Hermes/data:/opt/data
devices:

147
ai/patch_tts_tool.py Normal file
View File

@@ -0,0 +1,147 @@
#!/usr/bin/env python3
"""Patch Hermes TTS tool to add Piper provider and remove Edge TTS fallback."""
import sys
tts_path = '/opt/hermes/.venv/lib/python3.13/site-packages/tools/tts_tool.py'
with open(tts_path) as f:
code = f.read()
# Replace the Coqui provider block with Piper
old_coqui = ' elif provider == "coqui":'
new_piper = ''' elif provider == "piper":
logger.info("Generating speech with Piper TTS (local, CPU)...")
import subprocess
piper_binary = "/opt/hermes/.venv/bin/piper"
piper_config = tts_config.get("piper", {})
voice = piper_config.get("voice", "en_US-lessac-medium")
model_dir = piper_config.get("model_dir", "/opt/hermes/.venv/share/piper/voices")
model_path = os.path.join(model_dir, f"{voice}.onnx")
if not os.path.exists(model_path):
raise FileNotFoundError(f"Piper voice model not found: {model_path}")
cmd = [piper_binary, "--model", model_path, "--output-raw"]
proc = subprocess.Popen(cmd, stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
raw_audio, stderr = proc.communicate(input=text.encode(), timeout=60)
if proc.returncode != 0:
raise RuntimeError(f"Piper TTS failed: {stderr.decode()[:200]}")
ffmpeg_cmd = ["ffmpeg", "-f", "s16le", "-ar", "22050", "-ac", "1", "-i", "-", "-y", file_str]
subprocess.run(ffmpeg_cmd, input=raw_audio, capture_output=True, timeout=30)
logger.info("Piper TTS audio saved: %s", file_str)'''
if old_coqui in code:
code = code.replace(old_coqui, new_piper)
print("Coqui -> Piper replaced")
else:
# Fresh Hermes install - add Piper after the last provider (kittentts)
if 'provider == "piper"' in code:
print("Piper already present, skipping coqui replacement")
else:
print("Stock Hermes - adding Piper provider after kittentts...")
marker = ' elif provider == "kittentts":'
if marker in code:
# Find the end of the kittentts block and insert Piper before else
lines = code.split('\n')
kit_idx = None
for i, line in enumerate(lines):
if line.strip().startswith('elif provider == "kittentts":'):
kit_idx = i
break
if kit_idx is not None:
# Find the next blank line + else block
for i in range(kit_idx, len(lines)):
if lines[i].strip() == 'else:':
# Insert Piper block before this line
indent = ' '
piper_lines = new_piper.split('\n')
insert = piper_lines + ['']
lines[i:i] = insert
code = '\n'.join(lines)
print("Piper provider added after kittentts")
break
# Replace the Edge fallback with Piper fallback
old_edge = ''' else:
# Default: Edge TTS (free), with NeuTTS as local fallback
edge_available = True
try:
_import_edge_tts()
except ImportError:
edge_available = False
if edge_available:
logger.info("Generating speech with Edge TTS...")
try:
import concurrent.futures
with concurrent.futures.ThreadPoolExecutor(max_workers=1) as pool:
pool.submit(
lambda: asyncio.run(_generate_edge_tts(text, file_str, tts_config))
).result(timeout=60)
except RuntimeError:
asyncio.run(_generate_edge_tts(text, file_str, tts_config))
elif _check_neutts_available():
logger.info("Edge TTS not available, falling back to NeuTTS (local)...")
provider = "neutts"
_generate_neutts(text, file_str, tts_config)
else:
return json.dumps({
"success": False,
"error": "No TTS provider available. Install edge-tts (pip install edge-tts) "
"or set up NeuTTS for local synthesis."
}, ensure_ascii=False)'''
new_piper_fallback = ''' else:
# Default: Piper TTS (local, CPU, no cloud)
piper_available = False
try:
piper_binary = "/opt/hermes/.venv/bin/piper"
piper_config = tts_config.get("piper", {})
voice = piper_config.get("voice", "en_US-lessac-medium")
model_dir = piper_config.get("model_dir", "/opt/hermes/.venv/share/piper/voices")
model_path = os.path.join(model_dir, f"{voice}.onnx")
if os.path.exists(model_path):
piper_available = True
except Exception:
pass
if piper_available:
logger.info("Generating speech with Piper TTS (local, CPU)...")
import subprocess
piper_binary = "/opt/hermes/.venv/bin/piper"
piper_config = tts_config.get("piper", {})
voice = piper_config.get("voice", "en_US-lessac-medium")
model_dir = piper_config.get("model_dir", "/opt/hermes/.venv/share/piper/voices")
model_path = os.path.join(model_dir, f"{voice}.onnx")
cmd = [piper_binary, "--model", model_path, "--output-raw"]
proc = subprocess.Popen(cmd, stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
raw_audio, stderr = proc.communicate(input=text.encode(), timeout=60)
if proc.returncode != 0:
raise RuntimeError(f"Piper TTS failed: {stderr.decode()[:200]}")
ffmpeg_cmd = ["ffmpeg", "-f", "s16le", "-ar", "22050", "-ac", "1", "-i", "-", "-y", file_str]
subprocess.run(ffmpeg_cmd, input=raw_audio, capture_output=True, timeout=30)
logger.info("Piper TTS audio saved: %s", file_str)
else:
return json.dumps({
"success": False,
"error": "No TTS provider available. Install Piper TTS (pip install piper-tts) "
"and download a voice model."
}, ensure_ascii=False)'''
if old_edge in code:
code = code.replace(old_edge, new_piper_fallback)
print("Edge fallback replaced with Piper")
else:
print("Edge fallback NOT found, checking if already Piper...")
if 'Default: Piper TTS' in code:
print("Piper fallback already present, skipping")
else:
print("ERROR: Could not find Edge fallback")
# Debug: show what the else block looks like
import re
match = re.search(r' else:\n # Default:', code)
if match:
print("Found else block at", match.start())
sys.exit(1)
with open(tts_path, 'w') as f:
f.write(code)
print("tts_tool.py patched successfully")

View File

@@ -13,17 +13,20 @@ services:
- "--certificatesresolvers.njalla.acme.storage=/letsencrypt/acme.json"
- "--certificatesresolvers.njalla.acme.httpchallenge.entrypoint=web"
- "--log.level=DEBUG"
- "--log.level=INFO"
- "--log.filepath=/var/log/traefik/traefik.log"
- "--accesslog.filepath=/var/log/traefik/access.log"
- "--providers.docker=true"
- "--providers.docker.exposedByDefault=false"
ports:
- "80:80"
- "443:443"
environment:
- NJALLA_TOKEN=${NJALLA_TOKEN}
- NJALLA_TOKEN=***
volumes:
- /var/run/docker.sock:/var/run/docker.sock:ro
- /mnt/HoardingCow_docker_data/Traefik:/letsencrypt
- /var/log/traefik:/var/log/traefik
restart: unless-stopped
networks:
- traefik_backend