mirror of
https://github.com/BerriAI/litellm.git
synced 2026-08-28 05:25:59 +00:00
33eda22386
The componentized images exec uvicorn directly, so ddtrace-run never wraps the interpreter. USE_DDTRACE is not inert there; the proxy lifespan still runs patch_all and litellm's own manual spans still emit. What never gets installed is ddtrace's ASGI TraceMiddleware: starlette builds its middleware stack lazily on the first __call__, which is the lifespan scope, so patching from inside the lifespan body is already too late and no root request span is ever created. Route both entrypoints through a shared docker/component_entrypoint.sh that mirrors the monolith's prod_entrypoint.sh contract, including the DD_TRACE_OPENAI_ENABLED=False export that keeps ddtrace's openai integration from double-reporting calls litellm instruments itself. Co-authored-by: Yassin Kortam <yassin.kortam@gmail.com>
99 lines
3.9 KiB
Docker
99 lines
3.9 KiB
Docker
ARG LITELLM_BUILD_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:42df77a9974d6ec8b17a5ee8bc23b532600a44d705acef2409e0933c1251b45f
|
|
ARG LITELLM_RUNTIME_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:42df77a9974d6ec8b17a5ee8bc23b532600a44d705acef2409e0933c1251b45f
|
|
ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.11.7@sha256:240fb85ab0f263ef12f492d8476aa3a2e4e1e333f7d67fbdd923d00a506a516a
|
|
|
|
FROM $UV_IMAGE AS uvbin
|
|
|
|
# ---------- Builder ----------
|
|
FROM $LITELLM_BUILD_IMAGE AS builder
|
|
|
|
WORKDIR /app
|
|
USER root
|
|
|
|
COPY --from=uvbin /uv /uvx /usr/local/bin/
|
|
|
|
# nodejs/npm so `prisma generate` uses Wolfi's Node via PRISMA_USE_GLOBAL_NODE
|
|
# instead of nodeenv downloading one whose dynamic deps may not be in Wolfi
|
|
# (e.g. Node 26.2.0 needs libatomic). Retry for transient apk.cgr.dev flakes.
|
|
RUN for i in 1 2 3; do \
|
|
apk add --no-cache bash gcc python3 python3-dev openssl openssl-dev libsndfile nodejs npm && break; \
|
|
[ $i = 3 ] && { echo "apk add failed after 3 retries" >&2; exit 1; }; \
|
|
sleep 5; \
|
|
done
|
|
|
|
# UV_COMPILE_BYTECODE=1 precompiles .pyc at install time → faster cold start.
|
|
# UV_LINK_MODE=copy avoids hardlink warnings when uv installs from a
|
|
# BuildKit cache mount (different filesystem).
|
|
# UV_PYTHON_DOWNLOADS=0 force uv to use the apk-installed CPython instead of
|
|
# silently pulling a managed interpreter.
|
|
# PRISMA_USE_GLOBAL_NODE explicit (matches default) so an env override can't
|
|
# silently re-enable nodeenv's Node download.
|
|
ENV UV_PROJECT_ENVIRONMENT=/app/.venv \
|
|
UV_LINK_MODE=copy \
|
|
UV_COMPILE_BYTECODE=1 \
|
|
UV_PYTHON_DOWNLOADS=0 \
|
|
PRISMA_USE_GLOBAL_NODE=true \
|
|
PATH="/app/.venv/bin:${PATH}"
|
|
|
|
# Stage 1 — install dependencies only.
|
|
RUN --mount=type=cache,target=/root/.cache/uv \
|
|
--mount=type=bind,source=pyproject.toml,target=pyproject.toml \
|
|
--mount=type=bind,source=uv.lock,target=uv.lock \
|
|
--mount=type=bind,source=enterprise/pyproject.toml,target=enterprise/pyproject.toml \
|
|
--mount=type=bind,source=litellm-proxy-extras/pyproject.toml,target=litellm-proxy-extras/pyproject.toml \
|
|
uv sync --frozen --no-install-project --no-install-workspace --no-default-groups --no-editable \
|
|
--extra proxy \
|
|
--extra proxy-runtime \
|
|
--extra extra_proxy \
|
|
--extra semantic-router \
|
|
--python python3
|
|
|
|
# Stage 2 — copy source and install the project + workspace members.
|
|
COPY . .
|
|
|
|
RUN --mount=type=cache,target=/root/.cache/uv \
|
|
uv sync --frozen --no-default-groups --no-editable \
|
|
--extra proxy \
|
|
--extra proxy-runtime \
|
|
--extra extra_proxy \
|
|
--extra semantic-router \
|
|
--python python3
|
|
|
|
RUN mkdir -p /home/nonroot && \
|
|
HOME=/home/nonroot prisma generate --schema=./schema.prisma && \
|
|
chown -R nonroot:nonroot /home/nonroot/.cache
|
|
|
|
RUN sed -i 's/\r$//' docker/component_entrypoint.sh && chmod +x docker/component_entrypoint.sh
|
|
|
|
# ---------- Runtime ----------
|
|
FROM $LITELLM_RUNTIME_IMAGE AS runtime
|
|
|
|
USER root
|
|
|
|
RUN for i in 1 2 3; do \
|
|
apk add --no-cache bash openssl tzdata python3 libsndfile libatomic && break; \
|
|
[ $i = 3 ] && { echo "apk add failed after 3 retries" >&2; exit 1; }; \
|
|
sleep 5; \
|
|
done
|
|
|
|
# wolfi-base ships an unprivileged `nonroot` account (UID/GID 65532) with
|
|
# /home/nonroot. We run the backend as that user
|
|
WORKDIR /app
|
|
ENV HOME=/home/nonroot \
|
|
PATH="/app/.venv/bin:${PATH}" \
|
|
PYTHONPATH="/app" \
|
|
PYTHONDONTWRITEBYTECODE=1 \
|
|
PYTHONUNBUFFERED=1
|
|
|
|
COPY --from=builder --chown=nonroot:nonroot /app /app
|
|
COPY --from=builder --chown=nonroot:nonroot /home/nonroot/.cache /home/nonroot/.cache
|
|
|
|
RUN find /app/.venv -type f -path "*/tornado/test/*" -delete && \
|
|
find /app/.venv -type d -path "*/tornado/test" -delete
|
|
|
|
USER nonroot
|
|
|
|
EXPOSE 4001/tcp
|
|
|
|
ENTRYPOINT ["/app/docker/component_entrypoint.sh", "uvicorn", "backend.main:app"]
|
|
CMD ["--host", "0.0.0.0", "--port", "4001"]
|