Human-AII / Dockerfile
swayamshetkar
Backend with Llama auto-download, Dockerfile, deployment setup
5cb6ded
raw
history blame contribute delete
989 Bytes
# Use an official lightweight Python image
FROM python:3.11-slim
# System deps for llama.cpp (may require build tools)
RUN apt-get update && apt-get install -y --no-install-recommends \
build-essential \
git \
wget \
&& rm -rf /var/lib/apt/lists/*
# Set workdir
WORKDIR /app
# Copy requirement first for layer caching
COPY requirements.txt ./
# Install Python deps (prefer no cache)
RUN pip install --no-cache-dir -r requirements.txt
# Copy source
COPY . .
# Environment defaults (override in HF Space settings)
ENV HOST=0.0.0.0 \
PORT=7860 \
LOG_LEVEL=INFO \
LLAMA_MODEL_PATH=./models/meta-llama-3-8b.Q4_K_M.gguf \
LLAMA_REPO_ID=psuplj/Meta-Llama-3-8B-Q4_K_M-GGUF \
LLAMA_FILENAME=meta-llama-3-8b.Q4_K_M.gguf
# Expose port
EXPOSE 7860
# Healthcheck (simple ping)
HEALTHCHECK --interval=30s --timeout=3s --start-period=40s CMD curl -f http://localhost:7860/ || exit 1
# Entrypoint
CMD ["python", "app.py"]