Dockerfile fixes

pdelfin/beakerpipeline.py

@@ -638,15 +638,17 @@ async def main():
         pdf_s3 = pdf_session.client("s3")
 
     check_poppler_version()
-    logger.info(f"Starting pipeline with PID {os.getpid()}")
 
     if args.pdfs:
+        logger.info("Got --pdfs argument, going to add to the work queue")
         await populate_pdf_work_queue(args)
 
     if args.beaker:
         submit_beaker_job(args)
         return
 
+    logger.info(f"Starting pipeline with PID {os.getpid()}")
+
     # Create a semaphore to control worker access
     # We only allow one worker to move forward with requests, until the server has no more requests in its queue
     # This lets us get full utilization by having many workers, but also to be outputting dolma docs as soon as possible

pdelfin/version.py

@@ -2,7 +2,7 @@
 _MINOR = "1"
 # On main and in a nightly release the patch should be one ahead of the last
 # released build.
-_PATCH = "1"
+_PATCH = "3"
 # This is mainly for nightly builds which have the suffix ".dev$DATE". See
 # https://semver.org/#is-v123-a-semantic-version for the semantics.
 _SUFFIX = ""

scripts/beaker/Dockerfile-inference

@@ -4,6 +4,11 @@ RUN apt-get update -y && apt-get install -y software-properties-common \
     && add-apt-repository ppa:deadsnakes/ppa \
     && apt-get -y update
 
+# Install requirements specific to pdfs
+RUN apt-get update && apt-get -y install python3-apt
+RUN echo "ttf-mscorefonts-installer msttcorefonts/accepted-mscorefonts-eula select true" | debconf-set-selections
+RUN apt-get update -y && apt-get install -y poppler-utils ttf-mscorefonts-installer msttcorefonts fonts-crosextra-caladea fonts-crosextra-carlito gsfonts lcdf-typetools
+
 RUN apt-get update -y && apt-get install -y --no-install-recommends \
     python3.11 \
     python3.11-dev \
@@ -20,21 +25,23 @@ RUN rm -rf /var/lib/apt/lists/* \
     && curl -sS https://bootstrap.pypa.io/get-pip.py | python \
     && pip3 install -U pip    
 
-RUN apt-get update && apt-get -y install python3.11-venv
-
+RUN apt-get update && apt-get -y install python3.11-venv 
 ADD --chmod=755 https://astral.sh/uv/install.sh /install.sh
 RUN /install.sh && rm /install.sh
 
+# Flash inference install sooner
+RUN /root/.local/bin/uv pip install --system flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/
+
 ENV PYTHONUNBUFFERED=1
 WORKDIR /root
 COPY pyproject.toml pyproject.toml
-COPY pdelfin pdelfin
+COPY pdelfin/version.py pdelfin/version.py
 
 RUN /root/.local/bin/uv pip install --system --no-cache -e .[inference]
 
 # TODO You can remove this and move it into the pyproject.toml once sglang makes a release > 0.35.0
 RUN /root/.local/bin/uv pip install --system git+https://github.com/sgl-project/sglang.git@eff468dd5a3d24646560eb044276585f7a11ac3c#subdirectory=python&egg=sglang[all]
-RUN /root/.local/bin/uv pip install --system flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/
 
-RUN python3 -m pdelfin.beakerpipeline --help
+COPY pdelfin pdelfin
 
+RUN python3 -m pdelfin.beakerpipeline --help