Update Unstructured with NLTK changes (#1852)

py/Dockerfile.unstructured

@@ -1,29 +0,0 @@
-FROM python:3.12-slim AS builder
-
-# Install system dependencies (including those needed for Unstructured and OpenCV)
-RUN apt-get update && apt-get install -y --no-install-recommends \
-    gcc g++ musl-dev curl libffi-dev gfortran libopenblas-dev \
-    tesseract-ocr libtesseract-dev libleptonica-dev pkg-config \
-    poppler-utils libmagic1 pandoc libreoffice \
-    libgl1-mesa-glx libglib2.0-0 \
-    && apt-get clean && rm -rf /var/lib/apt/lists/*
-
-ENV TESSDATA_PREFIX=/usr/share/tesseract-ocr/5/tessdata
-
-ENV PYTHONDONTWRITEBYTECODE=1
-ENV PYTHONUNBUFFERED=1
-
-WORKDIR /app
-
-RUN pip install --no-cache-dir unstructured "unstructured[all-docs]"
-
-
-RUN python -c "from unstructured.partition.model_init import initialize; initialize()"
-
-RUN pip install gunicorn uvicorn fastapi httpx
-
-COPY core/integrations/unstructured/main.py .
-
-EXPOSE 7275
-
-CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7275", "--workers", "8"]

services/unstructured/Dockerfile.unstructured

@@ -18,6 +18,10 @@ WORKDIR /app
 RUN pip install --no-cache-dir unstructured "unstructured[all-docs]"
 
 
+ENV NLTK_DATA=/usr/share/nltk_data
+RUN mkdir -p ${NLTK_DATA}
+RUN python -m nltk.downloader -d ${NLTK_DATA} punkt_tab averaged_perceptron_tagger_eng
+
 RUN python -c "from unstructured.partition.model_init import initialize; initialize()"
 
 RUN pip install gunicorn uvicorn fastapi httpx