jlimolina
e3936fd4cf
- Ingestor: reactivar ETag/Last-Modified (304), http.Client compartido, rate-limit por host y Retry-After - Traducción: batch 128, cache en Redis con TTL (efímera), commit por lote - Scraper: worker pool paralelo (SCRAPER_WORKERS) - Config: compose lee RSS_/TRANSLATOR_ variables del .env (fuente única)
44 lines
1.1 KiB
Text
44 lines
1.1 KiB
Text
FROM python:3.11-slim-bookworm
|
|
|
|
RUN apt-get update && apt-get install -y --no-install-recommends \
|
|
patchelf libpq-dev gcc git curl wget \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
ENV PYTHONUNBUFFERED=1 \
|
|
PIP_DISABLE_PIP_VERSION_CHECK=1 \
|
|
TOKENIZERS_PARALLELISM=false \
|
|
HF_HOME=/root/.cache/huggingface
|
|
|
|
WORKDIR /app
|
|
|
|
COPY requirements.txt .
|
|
RUN pip install --no-cache-dir --upgrade pip
|
|
|
|
RUN pip install --no-cache-dir torch==2.1.0 torchvision==0.16.0 --index-url https://download.pytorch.org/whl/cpu
|
|
|
|
RUN pip install --no-cache-dir \
|
|
ctranslate2==3.24.0 \
|
|
sentencepiece \
|
|
transformers==4.36.0 \
|
|
protobuf==3.20.3 \
|
|
"numpy<2" \
|
|
psycopg2-binary \
|
|
langdetect \
|
|
redis
|
|
|
|
# === ARREGLAR EL EXECUTABLE STACK ===
|
|
RUN find /usr/local/lib/python3.11/site-packages/ctranslate2* \
|
|
-name "libctranslate2-*.so.*" -o -name "libctranslate2.so*" | \
|
|
xargs -I {} patchelf --clear-execstack {} || true
|
|
|
|
COPY workers/ ./workers/
|
|
COPY init-db/ ./init-db/
|
|
COPY migrations/ ./migrations/
|
|
|
|
ENV DB_HOST=db
|
|
ENV DB_PORT=5432
|
|
ENV DB_NAME=rss
|
|
ENV DB_USER=rss
|
|
ENV DB_PASS=x
|
|
|
|
CMD ["python", "-m", "workers.ctranslator_worker"]
|