unstructured/requirements/extra-pdf-image.txt
luke-kucing a7e90f7990
resolve CVEs and HF issue (#4009)
update reqs to resolve CVEs and add the HF ENV to stop it from reaching
out

updated the Dockerfile with
ENV HF_HUB_OFFLINE=1

to stop it from pinging HF. This was an issue for a gov customer. and
updated requirements to resolve some open CVEs

---------

Co-authored-by: cragwolfe <crag@unstructured.io>
Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com>
Co-authored-by: luke-kucing <luke-kucing@users.noreply.github.com>
2025-06-04 18:52:58 +00:00

298 lines
5.7 KiB
Plaintext

#
# This file is autogenerated by pip-compile with Python 3.9
# by the following command:
#
# pip-compile ./extra-pdf-image.in
#
accelerate==1.7.0
# via unstructured-inference
antlr4-python3-runtime==4.9.3
# via omegaconf
cachetools==5.5.2
# via google-auth
certifi==2025.4.26
# via
# -c ./base.txt
# requests
cffi==1.17.1
# via
# -c ./base.txt
# cryptography
charset-normalizer==3.4.2
# via
# -c ./base.txt
# pdfminer-six
# requests
coloredlogs==15.0.1
# via onnxruntime
contourpy==1.3.0
# via matplotlib
cryptography==45.0.3
# via
# -c ./base.txt
# pdfminer-six
cycler==0.12.1
# via matplotlib
deprecated==1.2.18
# via pikepdf
effdet==0.4.1
# via -r ./extra-pdf-image.in
filelock==3.18.0
# via
# huggingface-hub
# torch
# transformers
flatbuffers==25.2.10
# via onnxruntime
fonttools==4.58.1
# via matplotlib
fsspec==2025.5.1
# via
# huggingface-hub
# torch
google-api-core[grpc]==2.25.0
# via google-cloud-vision
google-auth==2.40.2
# via
# google-api-core
# google-cloud-vision
google-cloud-vision==3.10.1
# via -r ./extra-pdf-image.in
googleapis-common-protos==1.70.0
# via
# google-api-core
# grpcio-status
grpcio==1.72.1
# via
# -c ././deps/constraints.txt
# google-api-core
# grpcio-status
grpcio-status==1.72.1
# via google-api-core
hf-xet==1.1.2
# via huggingface-hub
huggingface-hub==0.32.3
# via
# accelerate
# timm
# tokenizers
# transformers
# unstructured-inference
humanfriendly==10.0
# via coloredlogs
idna==3.10
# via
# -c ./base.txt
# requests
importlib-resources==6.5.2
# via matplotlib
jinja2==3.1.6
# via torch
kiwisolver==1.4.7
# via matplotlib
lxml==5.4.0
# via
# -c ./base.txt
# pikepdf
markupsafe==3.0.2
# via jinja2
matplotlib==3.9.4
# via unstructured-inference
mpmath==1.3.0
# via sympy
networkx==3.2.1
# via torch
numpy==2.0.2
# via
# -c ./base.txt
# accelerate
# contourpy
# matplotlib
# onnx
# onnxruntime
# opencv-python
# pandas
# pycocotools
# scipy
# torchvision
# transformers
# unstructured-inference
omegaconf==2.3.0
# via effdet
onnx==1.18.0
# via
# -r ./extra-pdf-image.in
# unstructured-inference
onnxruntime==1.19.2
# via
# -r ./extra-pdf-image.in
# unstructured-inference
opencv-python==4.11.0.86
# via unstructured-inference
packaging==25.0
# via
# -c ./base.txt
# accelerate
# huggingface-hub
# matplotlib
# onnxruntime
# pikepdf
# transformers
# unstructured-pytesseract
pandas==2.2.3
# via unstructured-inference
pdf2image==1.17.0
# via -r ./extra-pdf-image.in
pdfminer-six==20250327
# via
# -c ././deps/constraints.txt
# -r ./extra-pdf-image.in
# unstructured-inference
pi-heif==0.22.0
# via -r ./extra-pdf-image.in
pikepdf==9.8.1
# via -r ./extra-pdf-image.in
pillow==11.2.1
# via
# matplotlib
# pdf2image
# pi-heif
# pikepdf
# torchvision
# unstructured-pytesseract
proto-plus==1.26.1
# via
# google-api-core
# google-cloud-vision
protobuf==6.31.1
# via
# -c ././deps/constraints.txt
# google-api-core
# google-cloud-vision
# googleapis-common-protos
# grpcio-status
# onnx
# onnxruntime
# proto-plus
psutil==7.0.0
# via
# -c ./base.txt
# accelerate
pyasn1==0.6.1
# via
# pyasn1-modules
# rsa
pyasn1-modules==0.4.2
# via google-auth
pycocotools==2.0.9
# via effdet
pycparser==2.22
# via
# -c ./base.txt
# cffi
pyparsing==3.2.3
# via matplotlib
pypdf==5.6.0
# via
# -c ./base.txt
# -r ./extra-pdf-image.in
pypdfium2==4.30.1
# via unstructured-inference
python-dateutil==2.9.0.post0
# via
# -c ./base.txt
# matplotlib
# pandas
python-multipart==0.0.20
# via unstructured-inference
pytz==2025.2
# via pandas
pyyaml==6.0.2
# via
# accelerate
# huggingface-hub
# omegaconf
# timm
# transformers
rapidfuzz==3.13.0
# via
# -c ./base.txt
# unstructured-inference
regex==2024.11.6
# via
# -c ./base.txt
# transformers
requests==2.32.3
# via
# -c ./base.txt
# google-api-core
# huggingface-hub
# transformers
rsa==4.9.1
# via google-auth
safetensors==0.5.3
# via
# accelerate
# timm
# transformers
scipy==1.13.1
# via unstructured-inference
six==1.17.0
# via
# -c ./base.txt
# python-dateutil
sympy==1.14.0
# via
# onnxruntime
# torch
timm==1.0.15
# via
# effdet
# unstructured-inference
tokenizers==0.21.1
# via
# -c ././deps/constraints.txt
# transformers
torch==2.7.0
# via
# accelerate
# effdet
# timm
# torchvision
# unstructured-inference
torchvision==0.22.0
# via
# effdet
# timm
tqdm==4.67.1
# via
# -c ./base.txt
# huggingface-hub
# transformers
transformers==4.52.4
# via unstructured-inference
typing-extensions==4.14.0
# via
# -c ./base.txt
# huggingface-hub
# onnx
# pypdf
# torch
tzdata==2025.2
# via pandas
unstructured-inference==1.0.2
# via -r ./extra-pdf-image.in
unstructured-pytesseract==0.3.15
# via -r ./extra-pdf-image.in
urllib3==1.26.20
# via
# -c ././deps/constraints.txt
# -c ./base.txt
# requests
wrapt==1.17.2
# via
# -c ./base.txt
# deprecated
zipp==3.22.0
# via importlib-resources