meshai/Dockerfile
Matt fd3f995ebb Initial commit: MeshAI - LLM-powered Meshtastic assistant
Features:
- Multi-backend LLM support (OpenAI, Anthropic, Google)
- Rolling summary memory for token optimization (~70-80% reduction)
- Per-user conversation history with SQLite persistence
- Bang commands (!help, !ping, !reset, !status, !weather)
- Meshtastic integration via serial or TCP
- Message chunking for mesh network constraints (150 char limit)
- Rate limiting to prevent network congestion
- Rich TUI configurator
- Docker support

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-15 11:53:46 -07:00

41 lines
955 B
Docker

FROM python:3.11-slim
LABEL maintainer="K7ZVX <matt@echo6.co>"
LABEL description="MeshAI - LLM-powered Meshtastic assistant"
# Install system dependencies
RUN apt-get update && apt-get install -y --no-install-recommends \
gcc \
libc6-dev \
&& rm -rf /var/lib/apt/lists/*
# Create non-root user
RUN useradd -m -s /bin/bash meshai
# Set working directory
WORKDIR /app
# Copy requirements first for layer caching
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt
# Copy application code
COPY meshai/ ./meshai/
COPY pyproject.toml .
COPY README.md .
# Install the package and fix permissions
RUN pip install --no-cache-dir -e . && \
chown -R meshai:meshai /app
# Create data directory for config and database
RUN mkdir -p /data && chown meshai:meshai /data
# Switch to non-root user
USER meshai
# Set working directory to data for config files
WORKDIR /data
# Default command
CMD ["python", "-m", "meshai"]