fix: use ZERO

Dockerfile

@@ -1,42 +0,0 @@
-FROM nvidia/cuda:12.1.1-cudnn8-devel-ubuntu22.04
-
-ARG DEBIAN_FRONTEND=noninteractive
-
-ENV PYTHONUNBUFFERED=1
-
-RUN apt-get update && apt-get install --no-install-recommends -y \
-    build-essential \
-    python3.10-dev \
-    python3-pip \
-    wget \
-    git \
-    ffmpeg \
-    poppler-utils \
-    libpoppler-dev \
-    tesseract-ocr \
-    && apt-get clean && rm -rf /var/lib/apt/lists/*
-
-WORKDIR /code
-
-COPY ./requirements.txt /code/requirements.txt
-
-# Set up a new user named "user" with user ID 1000
-RUN useradd -m -u 1000 user
-# Switch to the "user" user
-USER user
-# Set home to the user's home directory
-ENV HOME=/home/user \
-    PATH=/home/user/.local/bin:$PATH \
-    PYTHONPATH=$HOME/app \
-    PYTHONUNBUFFERED=1 \
-    GRADIO_SERVER_NAME=0.0.0.0
-
-RUN pip3 install --no-cache-dir --upgrade -r /code/requirements.txt
-
-# Set the working directory to the user's home directory
-WORKDIR $HOME/app
-
-# Copy the current directory contents into the container at $HOME/app setting the owner to the user
-COPY --chown=user . $HOME/app
-
-CMD ["python3", "app.py"]

README.md

@@ -3,7 +3,10 @@ title: SmolDoclingPreview
 emoji: 🐢
 colorFrom: blue
 colorTo: green
-sdk: docker
+sdk: gradio
+sdk_version: 5.12.0
+app_file: app.py
+license: apache-2.0
 pinned: false
 header: mini
 short_description: Convert PDFs to Markdown with SmolDoclingPreview

app.py

@@ -26,6 +26,13 @@ MAX_SELECTED_METHODS = int(os.getenv("MAX_SELECTED_METHODS", "6"))
 MAX_PAGES = int(os.getenv("MAX_PAGES", "2"))
 
 
+# Install poppler-utils
+import os
+
+os.system("apt-get update")
+os.system("apt-get install --no-install-recommends -y poppler-utils tesseract-ocr")
+
+
 def convert_document(path, method, start_page=0, enabled=True):
     if enabled:
         print("Processing file", path, "with method", method)

backends/smoldocling.py

@@ -3,6 +3,7 @@
 # pip install docling_core
 # pip install transformers
 
+import spaces
 import torch
 from docling_core.types.doc import DoclingDocument
 from docling_core.types.doc.document import DocTagsDocument
@@ -32,6 +33,7 @@ messages = [
 ]
 
 
+@spaces.GPU(duration=120)
 def convert_smoldocling(path: str, file_name: str):
     doc = PDF(path)
     output_md = ""

requirements.txt

@@ -2,7 +2,6 @@ gradio-pdf>=0.0.21
 PyMuPDF>=1.24.9,<1.24.14
 pymupdf4llm
 unstructured[pdf]
-ultralytics>=8.3.48
 openai
 img2table
 gmft
@@ -10,3 +9,5 @@ transformers<5.0.0,>=4.45.2
 pypdf
 docling_core
 opencv-contrib-python
+huggingface_hub
+spaces