feat(hermes): add voice support with GPU-accelerated STT
- Dockerfile: add libportaudio2 system library for audio capture - Dockerfile: install sounddevice, numpy, faster-whisper for local STT - compose.yml: add ROCm environment variables for AMD GPU support Enables local faster-whisper STT with GPU acceleration via ROCm.
This commit is contained in:
Submodule assets/compose updated: fb0f2cbe84...278e4f7ffc
71
docker/hermes/Dockerfile
Normal file
71
docker/hermes/Dockerfile
Normal file
@@ -0,0 +1,71 @@
|
||||
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
|
||||
|
||||
# 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 \
|
||||
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
|
||||
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/
|
||||
|
||||
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/
|
||||
|
||||
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
|
||||
|
||||
# ---------- Source code ----------
|
||||
# .dockerignore excludes node_modules, so the installs above survive.
|
||||
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 ----------
|
||||
RUN uv venv && \
|
||||
uv pip install --no-cache-dir -e ".[all]" && \
|
||||
uv pip install --no-cache-dir sounddevice numpy faster-whisper
|
||||
|
||||
# ---------- Runtime ----------
|
||||
ENV HERMES_WEB_DIST=/opt/hermes/hermes_cli/web_dist
|
||||
ENV HERMES_HOME=/opt/data
|
||||
ENV PATH="/opt/data/.local/bin:${PATH}"
|
||||
VOLUME [ "/opt/data" ]
|
||||
ENTRYPOINT [ "/usr/bin/tini", "-g", "--", "/opt/hermes/docker/entrypoint.sh" ]
|
||||
102
docker/hermes/entrypoint.sh
Executable file
102
docker/hermes/entrypoint.sh
Executable file
@@ -0,0 +1,102 @@
|
||||
#!/bin/bash
|
||||
# Docker/Podman entrypoint: bootstrap config files into the mounted volume, then run hermes.
|
||||
set -e
|
||||
|
||||
HERMES_HOME="${HERMES_HOME:-/opt/data}"
|
||||
INSTALL_DIR="/opt/hermes"
|
||||
|
||||
# --- Privilege dropping via gosu ---
|
||||
# When started as root (the default for Docker, or fakeroot in rootless Podman),
|
||||
# optionally remap the hermes user/group to match host-side ownership, fix volume
|
||||
# permissions, then re-exec as hermes.
|
||||
if [ "$(id -u)" = "0" ]; then
|
||||
if [ -n "$HERMES_UID" ] && [ "$HERMES_UID" != "$(id -u hermes)" ]; then
|
||||
echo "Changing hermes UID to $HERMES_UID"
|
||||
usermod -u "$HERMES_UID" hermes
|
||||
fi
|
||||
|
||||
if [ -n "$HERMES_GID" ] && [ "$HERMES_GID" != "$(id -g hermes)" ]; then
|
||||
echo "Changing hermes GID to $HERMES_GID"
|
||||
# -o allows non-unique GID (e.g. macOS GID 20 "staff" may already exist
|
||||
# as "dialout" in the Debian-based container image)
|
||||
groupmod -o -g "$HERMES_GID" hermes 2>/dev/null || true
|
||||
fi
|
||||
|
||||
# Fix ownership of the data volume. When HERMES_UID remaps the hermes user,
|
||||
# files created by previous runs (under the old UID) become inaccessible.
|
||||
# Always chown -R when UID was remapped; otherwise only if top-level is wrong.
|
||||
actual_hermes_uid=$(id -u hermes)
|
||||
needs_chown=false
|
||||
if [ -n "$HERMES_UID" ] && [ "$HERMES_UID" != "10000" ]; then
|
||||
needs_chown=true
|
||||
elif [ "$(stat -c %u "$HERMES_HOME" 2>/dev/null)" != "$actual_hermes_uid" ]; then
|
||||
needs_chown=true
|
||||
fi
|
||||
if [ "$needs_chown" = true ]; then
|
||||
echo "Fixing ownership of $HERMES_HOME to hermes ($actual_hermes_uid)"
|
||||
# In rootless Podman the container's "root" is mapped to an unprivileged
|
||||
# host UID — chown will fail. That's fine: the volume is already owned
|
||||
# by the mapped user on the host side.
|
||||
chown -R hermes:hermes "$HERMES_HOME" 2>/dev/null || \
|
||||
echo "Warning: chown failed (rootless container?) — continuing anyway"
|
||||
fi
|
||||
|
||||
echo "Dropping root privileges"
|
||||
exec gosu hermes "$0" "$@"
|
||||
fi
|
||||
|
||||
# --- Running as hermes from here ---
|
||||
source "${INSTALL_DIR}/.venv/bin/activate"
|
||||
|
||||
# Create essential directory structure. Cache and platform directories
|
||||
# (cache/images, cache/audio, platforms/whatsapp, etc.) are created on
|
||||
# demand by the application — don't pre-create them here so new installs
|
||||
# get the consolidated layout from get_hermes_dir().
|
||||
# The "home/" subdirectory is a per-profile HOME for subprocesses (git,
|
||||
# ssh, gh, npm …). Without it those tools write to /root which is
|
||||
# ephemeral and shared across profiles. See issue #4426.
|
||||
mkdir -p "$HERMES_HOME"/{cron,sessions,logs,hooks,memories,skills,skins,plans,workspace,home}
|
||||
|
||||
# .env
|
||||
if [ ! -f "$HERMES_HOME/.env" ]; then
|
||||
cp "$INSTALL_DIR/.env.example" "$HERMES_HOME/.env"
|
||||
fi
|
||||
|
||||
# config.yaml
|
||||
if [ ! -f "$HERMES_HOME/config.yaml" ]; then
|
||||
cp "$INSTALL_DIR/cli-config.yaml.example" "$HERMES_HOME/config.yaml"
|
||||
fi
|
||||
|
||||
# Ensure the main config file remains accessible to the hermes runtime user
|
||||
# even if it was edited on the host after initial ownership setup.
|
||||
if [ -f "$HERMES_HOME/config.yaml" ]; then
|
||||
chown hermes:hermes "$HERMES_HOME/config.yaml"
|
||||
chmod 640 "$HERMES_HOME/config.yaml"
|
||||
fi
|
||||
|
||||
# SOUL.md
|
||||
if [ ! -f "$HERMES_HOME/SOUL.md" ]; then
|
||||
cp "$INSTALL_DIR/docker/SOUL.md" "$HERMES_HOME/SOUL.md"
|
||||
fi
|
||||
|
||||
# Sync bundled skills (manifest-based so user edits are preserved)
|
||||
if [ -d "$INSTALL_DIR/skills" ]; then
|
||||
python3 "$INSTALL_DIR/tools/skills_sync.py"
|
||||
fi
|
||||
|
||||
# Final exec: two supported invocation patterns.
|
||||
#
|
||||
# docker run <image> -> exec `hermes` with no args (legacy default)
|
||||
# docker run <image> chat -q "..." -> exec `hermes chat -q "..."` (legacy wrap)
|
||||
# docker run <image> sleep infinity -> exec `sleep infinity` directly
|
||||
# docker run <image> bash -> exec `bash` directly
|
||||
#
|
||||
# If the first positional arg resolves to an executable on PATH, we assume the
|
||||
# caller wants to run it directly (needed by the launcher which runs long-lived
|
||||
# `sleep infinity` sandbox containers — see tools/environments/docker.py).
|
||||
# Otherwise we treat the args as a hermes subcommand and wrap with `hermes`,
|
||||
# preserving the documented `docker run <image> <subcommand>` behavior.
|
||||
if [ $# -gt 0 ] && command -v "$1" >/dev/null 2>&1; then
|
||||
exec "$@"
|
||||
fi
|
||||
exec hermes "$@"
|
||||
Reference in New Issue
Block a user