checkpoint: pipeline + 27k/h baseline before sitemap discovery

This commit is contained in:
qananasikq
2026-04-18 16:34:09 +03:00
parent a8c5f8aa41
commit 5999c2e42d
30 changed files with 4993 additions and 61 deletions

View File

@@ -13,6 +13,10 @@ RUN pip install --no-cache-dir uv \
&& pip install --no-cache-dir -r /tmp/requirements.txt \
&& pip install --no-cache-dir playwright-stealth
# Speed-up libs: orjson (fast JSON parse), brotli (HTTP br decompress).
# Pinned outside uv.lock to avoid lock-regen churn.
RUN pip install --no-cache-dir "orjson>=3.10.0" "brotli>=1.1.0"
# Install both Chromium and Firefox. Chromium is the default engine in Docker
# because it works more reliably with the current IAAI listing page.
RUN python -m playwright install chromium firefox