taprosoft
commited on
Commit
·
204f5db
1
Parent(s):
16e4c39
fix: update torch version
Browse files- Dockerfile +41 -0
- README.md +1 -3
- app.py +2 -2
- cuda_requirements.txt +2 -0
Dockerfile
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
FROM nvidia/cuda:12.1.1-cudnn8-devel-ubuntu22.04
|
| 2 |
+
|
| 3 |
+
ARG DEBIAN_FRONTEND=noninteractive
|
| 4 |
+
|
| 5 |
+
ENV PYTHONUNBUFFERED=1
|
| 6 |
+
|
| 7 |
+
RUN apt-get update && apt-get install --no-install-recommends -y \
|
| 8 |
+
build-essential \
|
| 9 |
+
python3.10-dev \
|
| 10 |
+
python3-pip \
|
| 11 |
+
git \
|
| 12 |
+
ffmpeg \
|
| 13 |
+
poppler-utils \
|
| 14 |
+
libpoppler-dev \
|
| 15 |
+
tesseract-ocr \
|
| 16 |
+
&& apt-get clean && rm -rf /var/lib/apt/lists/*
|
| 17 |
+
|
| 18 |
+
WORKDIR /code
|
| 19 |
+
|
| 20 |
+
COPY ./requirements.txt /code/requirements.txt
|
| 21 |
+
|
| 22 |
+
# Set up a new user named "user" with user ID 1000
|
| 23 |
+
RUN useradd -m -u 1000 user
|
| 24 |
+
# Switch to the "user" user
|
| 25 |
+
USER user
|
| 26 |
+
# Set home to the user's home directory
|
| 27 |
+
ENV HOME=/home/user \
|
| 28 |
+
PATH=/home/user/.local/bin:$PATH \
|
| 29 |
+
PYTHONPATH=$HOME/app \
|
| 30 |
+
PYTHONUNBUFFERED=1 \
|
| 31 |
+
GRADIO_SERVER_NAME=0.0.0.0
|
| 32 |
+
|
| 33 |
+
RUN pip3 install --no-cache-dir --upgrade -r /code/requirements.txt
|
| 34 |
+
|
| 35 |
+
# Set the working directory to the user's home directory
|
| 36 |
+
WORKDIR $HOME/app
|
| 37 |
+
|
| 38 |
+
# Copy the current directory contents into the container at $HOME/app setting the owner to the user
|
| 39 |
+
COPY --chown=user . $HOME/app
|
| 40 |
+
|
| 41 |
+
CMD ["python3", "app.py"]
|
README.md
CHANGED
|
@@ -3,9 +3,7 @@ title: PDFParsersPlayground
|
|
| 3 |
emoji: 🐢
|
| 4 |
colorFrom: blue
|
| 5 |
colorTo: green
|
| 6 |
-
sdk:
|
| 7 |
-
sdk_version: 5.7.1
|
| 8 |
-
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
short_description: Convert PDFs to Markdown with open-source parsers
|
| 11 |
---
|
|
|
|
| 3 |
emoji: 🐢
|
| 4 |
colorFrom: blue
|
| 5 |
colorTo: green
|
| 6 |
+
sdk: docker
|
|
|
|
|
|
|
| 7 |
pinned: false
|
| 8 |
short_description: Convert PDFs to Markdown with open-source parsers
|
| 9 |
---
|
app.py
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
-
from utils import fix_problematic_imports
|
| 2 |
|
| 3 |
fix_problematic_imports() # noqa
|
| 4 |
|
|
@@ -19,7 +19,7 @@ from backends import (
|
|
| 19 |
from backends.settings import ENABLE_DEBUG_MODE
|
| 20 |
from utils import remove_images_from_markdown, trim_pages
|
| 21 |
|
| 22 |
-
TRIMMED_PDF_PATH = Path("/tmp/
|
| 23 |
TRIMMED_PDF_PATH.mkdir(exist_ok=True)
|
| 24 |
|
| 25 |
|
|
|
|
| 1 |
+
from utils import fix_problematic_imports
|
| 2 |
|
| 3 |
fix_problematic_imports() # noqa
|
| 4 |
|
|
|
|
| 19 |
from backends.settings import ENABLE_DEBUG_MODE
|
| 20 |
from utils import remove_images_from_markdown, trim_pages
|
| 21 |
|
| 22 |
+
TRIMMED_PDF_PATH = Path("/tmp/trimmed_input")
|
| 23 |
TRIMMED_PDF_PATH.mkdir(exist_ok=True)
|
| 24 |
|
| 25 |
|
cuda_requirements.txt
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
torch @ https://download.pytorch.org/whl/test/cu118/torch-2.6.0%2Bcu118-cp310-cp310-linux_x86_64.whl
|
| 2 |
+
torchvision @ https://download.pytorch.org/whl/test/cu118/torchvision-0.21.0%2Bcu118-cp310-cp310-linux_x86_64.whl
|