Add pipeline code

This commit is contained in:
Grok Bot
2026-10-17 15:27:14 -05:00
parent 3cd5a4c658
commit 5f0e2a9768
21 changed files with 1612 additions and 0 deletions
+15
View File
@@ -0,0 +1,15 @@
# Pipeline container. Build from the repo root: docker build -f _pipeline/Dockerfile -t old-books-pipeline .
# Run: docker run --rm -v /path/to/old-books/books:/repo/books old-books-pipeline run "/repo/books/x.pdf" --chapters 1
# Not built yet. Voice and speech-to-text are separate off-the-shelf containers reached through the URLs in settings.yaml.
FROM python:3.13-slim
RUN apt-get update \
&& apt-get install -y --no-install-recommends ffmpeg poppler-utils tesseract-ocr tesseract-ocr-eng ghostscript \
&& rm -rf /var/lib/apt/lists/*
COPY _pipeline/requirements.txt /tmp/requirements.txt
RUN pip install --no-cache-dir -r /tmp/requirements.txt && rm /tmp/requirements.txt
COPY _pipeline /repo/_pipeline
WORKDIR /repo
ENTRYPOINT ["python3", "/repo/_pipeline/cli.py"]