Deploy from GitHub Actions: a63dd9879e7bd1021036f94c5954ae8e098dd204

Dockerfile

@@ -2,9 +2,13 @@ FROM python:3.12-slim
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
   ca-certificates \
-  libmagic1 \
+  libmagic-dev \
   libgl1 \
   libglib2.0-0 \
+  libxml2 \
+  libxslt1-dev \
+  poppler-utils \
+  tesseract-ocr \
   && rm -rf /var/lib/apt/lists/*
 
 COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /bin/
@@ -12,13 +16,15 @@ COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /bin/
 ENV ENV=production \
   PORT=7860 \
   PYTHONUNBUFFERED=1 \
-  PYTHONDONTWRITEBYTECODE=1
+  PYTHONDONTWRITEBYTECODE=1 \
+  NLTK_DATA=/home/user/nltk_data
 
 RUN useradd -m -u 1000 user
 WORKDIR /home/user/app
 
 COPY requirements.txt .
 RUN uv pip install --no-cache --system -r requirements.txt
+RUN python -m nltk.downloader -d /home/user/nltk_data punkt averaged_perceptron_tagger punkt_tab averaged_perceptron_tagger_eng
 
 RUN chown -R user:user /home/user/app
 

requirements.txt

@@ -14,6 +14,10 @@ google-generativeai
 
 langchain-pymupdf4llm
 unstructured[csv,docx,pptx,xlsx]
-python-pptx
+python-pptx 
+python-pptx #HF
+python-magic #HF
+docx2txt #HF
+openpyxl #HF
 markdown
 jq