server/Dockerfile

# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
#
# This source code is licensed under the BSD-style license found in the
# LICENSE file in the root directory of this source tree.

ARG BASE_IMAGE=ghcr.io/meta-pytorch/openenv-base:latest
FROM ${BASE_IMAGE} AS builder

WORKDIR /app


COPY . /app/env

WORKDIR /app/env

RUN if ! command -v uv >/dev/null 2>&1; then \
        curl -LsSf https://astral.sh/uv/install.sh | sh && \
        mv /root/.local/bin/uv /usr/local/bin/uv && \
        mv /root/.local/bin/uvx /usr/local/bin/uvx; \
    fi

RUN apt-get update && apt-get install -y --no-install-recommends \
    git \
    && rm -rf /var/lib/apt/lists/*

RUN --mount=type=cache,target=/root/.cache/uv \
    if [ -f uv.lock ]; then \
        uv sync --frozen --no-install-project --no-editable; \
    else \
        uv sync --no-install-project --no-editable; \
    fi

RUN --mount=type=cache,target=/root/.cache/uv \
    if [ -f uv.lock ]; then \
        uv sync --frozen --no-editable; \
    else \
        uv sync --no-editable; \
    fi

# Pre-download GPT-2 tokenizer to avoid permission issues at runtime.
# HF_HOME must match the runtime value so the cache is copied to the right place.
RUN HF_HOME=/.cache /app/env/.venv/bin/python -c "from transformers import GPT2Tokenizer; GPT2Tokenizer.from_pretrained('gpt2')"

# Final runtime stage
FROM ${BASE_IMAGE}

WORKDIR /app

COPY --from=builder /app/env/.venv /app/.venv
COPY --from=builder /app/env /app/env
COPY --from=builder /.cache /.cache

ENV PATH="/app/.venv/bin:$PATH"
ENV PYTHONPATH="/app/env:$PYTHONPATH"
ENV HF_HOME=/.cache
ENV TRANSFORMERS_CACHE=/.cache
ENV TOKENIZER_NAME=gpt2
ENV SYSTEM_PROMPT="You are a helpful AI assistant."
ENV ENABLE_WEB_INTERFACE=true

HEALTHCHECK --interval=30s --timeout=3s --start-period=5s --retries=3 \
    CMD python -c "import urllib.request; urllib.request.urlopen('http://localhost:8000/health')" || exit 1

CMD ["sh", "-c", "cd /app/env && uvicorn server.app:app --host 0.0.0.0 --port 8000"]