Skip to content

Prewarm tiktoken cache to avoid Foundry egress #18

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
anand-testcompare merged 2 commits into from
Feb 15, 2026
Merged

Prewarm tiktoken cache to avoid Foundry egress #18

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e1f4769
Prewarm tiktoken cache for Foundry runtime
anand-testcompare Feb 15, 2026
11572d3
Fix tiktoken prewarm to use venv python
anand-testcompare Feb 15, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 9 additions & 2 deletions Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,14 +16,20 @@ RUN uv sync --frozen --no-dev
COPY src ./src
COPY artifacts ./artifacts

# Pre-warm tiktoken encoding cache during build so the runtime does not
# need outbound access to openaipublic.blob.core.windows.net.
RUN mkdir -p /app/.tiktoken_cache \
&& TIKTOKEN_CACHE_DIR=/app/.tiktoken_cache /app/.venv/bin/python -c 'import tiktoken; tiktoken.get_encoding("cl100k_base")'


FROM python:3.13-slim AS runtime

ARG SERVER_OPENAPI="{}"

ENV PYTHONUNBUFFERED=1 \
PATH="/app/.venv/bin:${PATH}" \
PYTHONPATH="/app"
PYTHONPATH="/app" \
TIKTOKEN_CACHE_DIR="/app/.tiktoken_cache"

WORKDIR /app

Expand All @@ -33,9 +39,10 @@ RUN groupadd --gid 5000 app \
COPY --from=builder --chown=5000:5000 /app/.venv /app/.venv
COPY --from=builder --chown=5000:5000 /app/src ./src
COPY --from=builder --chown=5000:5000 /app/artifacts ./artifacts
COPY --from=builder --chown=5000:5000 /app/.tiktoken_cache /app/.tiktoken_cache
COPY --chown=5000:5000 pyproject.toml uv.lock README.md ./

RUN mkdir -p /app/data/.dspy_cache && chown -R 5000:5000 /app
RUN mkdir -p /app/data/.dspy_cache /app/.tiktoken_cache && chown -R 5000:5000 /app

LABEL server.openapi="${SERVER_OPENAPI}"

Expand Down