Fix pdfminer-six dependencies.

.github/workflows/ci.yml

@@ -97,7 +97,7 @@ jobs:
       with:
         aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
         aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
-        aws-region: ${{ secrets.AWS_DEFAULT_REGION }}
+        aws-region: ${{ secrets.AWS_REGION }}
     - name: Test
       env:
         UNSTRUCTURED_HF_TOKEN: ${{ secrets.HF_TOKEN }}

CHANGELOG.md

@@ -1,3 +1,7 @@
+## 0.8.11-dev0
+
+* fix: dependencies of pdfminer-six and python 3.9
+
 ## 0.8.10
 
 * feat: unpin `numpy` and bump minimum for `onnxruntime` to be compatible with `numpy>=2`

Makefile

@@ -1,5 +1,5 @@
 PACKAGE_NAME := unstructured_inference
-PIP_VERSION := 23.2.1
+PIP_VERSION := 25.0.1
 CURRENT_DIR := $(shell pwd)
 
 
@@ -14,7 +14,7 @@ help: Makefile
 
 ## install-base:            installs core requirements needed for text processing bricks
 .PHONY: install-base
-install-base: install-base-pip-packages
+install-base: install-base-pip-packages requirements/base.in
 	python3 -m pip install -r requirements/base.txt
 
 ## install:                 installs all test, dev, and experimental requirements
@@ -29,16 +29,16 @@ install-base-pip-packages:
 	python3 -m pip install pip==${PIP_VERSION}
 
 .PHONY: install-test
-install-test: install-base
+install-test: install-base requirements/test.txt
 	python3 -m pip install -r requirements/test.txt
 
 .PHONY: install-dev
-install-dev: install-test
+install-dev: install-test requirements/dev.txt
 	python3 -m pip install -r requirements/dev.txt
 
 ## pip-compile:             compiles all base/dev/test requirements
 .PHONY: pip-compile
-pip-compile:
+pip-compile: requirements/base.txt requirements/test.txt requirements/dev.txt
 	pip-compile --upgrade requirements/base.in
 	pip-compile --upgrade requirements/test.in
 	pip-compile --upgrade requirements/dev.in

requirements/base.in

@@ -1,17 +1,28 @@
 -c constraints.in
 python-multipart
 huggingface-hub
-numpy
+numpy<2.1 ; python_version <= '3.9'
+numpy ; python_version > '3.10'
 opencv-python!=4.7.0.68
 onnx
-onnxruntime>=1.18.0
-matplotlib
+onnxruntime<1.20 ; python_version <= '3.9'
+onnxruntime ; python_version >= '3.10'
+matplotlib<3.10 ; python_version <= '3.9'
+matplotlib ; python_version >= '3.10'
 torch
 timm
 # NOTE(alan): Pinned because this is when the most recent module we import appeared
-transformers>=4.25.1
+#transformers>=4.25.1
+transformers>=4.25.1,<4.51
 rapidfuzz
 pandas
-scipy
+scipy<1.14 ; python_version <= '3.9'
+scipy ; python_version >= '3.10'
 pypdfium2
-pdfminer-six
+pdfminer-six>=20250327
+contourpy<1.4.0 ; python_version <= '3.9'
+contourpy ; python_version >= '3.10'
+kiwisolver<1.5 ; python_version <= '3.9'
+kiwisolver ; python_version >= '3.10'
+networkx==3.2.1 ; python_version <= '3.9'
+networkx ; python_version >= '3.10'

requirements/base.txt

@@ -1,5 +1,5 @@
 #
-# This file is autogenerated by pip-compile with Python 3.9
+# This file is autogenerated by pip-compile with Python 3.12
 # by the following command:
 #
 #    pip-compile requirements/base.in
@@ -14,26 +14,28 @@ charset-normalizer==3.4.1
     #   requests
 coloredlogs==15.0.1
     # via onnxruntime
-contourpy==1.3.0
-    # via matplotlib
+contourpy==1.3.1 ; python_version >= "3.10"
+    # via
+    #   -r requirements/base.in
+    #   matplotlib
 cryptography==44.0.2
     # via pdfminer-six
 cycler==0.12.1
     # via matplotlib
-filelock==3.17.0
+filelock==3.18.0
     # via
     #   huggingface-hub
     #   torch
     #   transformers
 flatbuffers==25.2.10
     # via onnxruntime
-fonttools==4.56.0
+fonttools==4.57.0
     # via matplotlib
-fsspec==2025.3.0
+fsspec==2025.3.2
     # via
     #   huggingface-hub
     #   torch
-huggingface-hub==0.29.3
+huggingface-hub==0.30.2
     # via
     #   -r requirements/base.in
     #   timm
@@ -43,21 +45,23 @@ humanfriendly==10.0
     # via coloredlogs
 idna==3.10
     # via requests
-importlib-resources==6.5.2
-    # via matplotlib
 jinja2==3.1.6
     # via torch
-kiwisolver==1.4.7
-    # via matplotlib
+kiwisolver==1.4.8 ; python_version >= "3.10"
+    # via
+    #   -r requirements/base.in
+    #   matplotlib
 markupsafe==3.0.2
     # via jinja2
-matplotlib==3.9.4
+matplotlib==3.10.1 ; python_version >= "3.10"
     # via -r requirements/base.in
 mpmath==1.3.0
     # via sympy
-networkx==3.2.1
-    # via torch
-numpy==2.0.2
+networkx==3.4.2 ; python_version >= "3.10"
+    # via
+    #   -r requirements/base.in
+    #   torch
+numpy==2.2.4 ; python_version > "3.10"
     # via
     #   -r requirements/base.in
     #   contourpy
@@ -69,9 +73,43 @@ numpy==2.0.2
     #   scipy
     #   torchvision
     #   transformers
+nvidia-cublas-cu12==12.4.5.8
+    # via
+    #   nvidia-cudnn-cu12
+    #   nvidia-cusolver-cu12
+    #   torch
+nvidia-cuda-cupti-cu12==12.4.127
+    # via torch
+nvidia-cuda-nvrtc-cu12==12.4.127
+    # via torch
+nvidia-cuda-runtime-cu12==12.4.127
+    # via torch
+nvidia-cudnn-cu12==9.1.0.70
+    # via torch
+nvidia-cufft-cu12==11.2.1.3
+    # via torch
+nvidia-curand-cu12==10.3.5.147
+    # via torch
+nvidia-cusolver-cu12==11.6.1.9
+    # via torch
+nvidia-cusparse-cu12==12.3.1.170
+    # via
+    #   nvidia-cusolver-cu12
+    #   torch
+nvidia-cusparselt-cu12==0.6.2
+    # via torch
+nvidia-nccl-cu12==2.21.5
+    # via torch
+nvidia-nvjitlink-cu12==12.4.127
+    # via
+    #   nvidia-cusolver-cu12
+    #   nvidia-cusparse-cu12
+    #   torch
+nvidia-nvtx-cu12==12.4.127
+    # via torch
 onnx==1.17.0
     # via -r requirements/base.in
-onnxruntime==1.19.2
+onnxruntime==1.21.0 ; python_version >= "3.10"
     # via -r requirements/base.in
 opencv-python==4.11.0.86
     # via -r requirements/base.in
@@ -83,19 +121,19 @@ packaging==24.2
     #   transformers
 pandas==2.2.3
     # via -r requirements/base.in
-pdfminer-six==20240706
+pdfminer-six==20250327
     # via -r requirements/base.in
 pillow==11.1.0
     # via
     #   matplotlib
     #   torchvision
-protobuf==6.30.0
+protobuf==6.30.2
     # via
     #   onnx
     #   onnxruntime
 pycparser==2.22
     # via cffi
-pyparsing==3.2.1
+pyparsing==3.2.3
     # via matplotlib
 pypdfium2==4.30.1
     # via -r requirements/base.in
@@ -105,14 +143,14 @@ python-dateutil==2.9.0.post0
     #   pandas
 python-multipart==0.0.20
     # via -r requirements/base.in
-pytz==2025.1
+pytz==2025.2
     # via pandas
 pyyaml==6.0.2
     # via
     #   huggingface-hub
     #   timm
     #   transformers
-rapidfuzz==3.12.2
+rapidfuzz==3.13.0
     # via -r requirements/base.in
 regex==2024.11.6
     # via transformers
@@ -124,7 +162,7 @@ safetensors==0.5.3
     # via
     #   timm
     #   transformers
-scipy==1.13.1
+scipy==1.15.2 ; python_version >= "3.10"
     # via -r requirements/base.in
 six==1.17.0
     # via python-dateutil
@@ -147,15 +185,18 @@ tqdm==4.67.1
     # via
     #   huggingface-hub
     #   transformers
-transformers==4.49.0
+transformers==4.50.3
     # via -r requirements/base.in
-typing-extensions==4.12.2
+triton==3.2.0
+    # via torch
+typing-extensions==4.13.1
     # via
     #   huggingface-hub
     #   torch
-tzdata==2025.1
+tzdata==2025.2
     # via pandas
 urllib3==2.3.0
     # via requests
-zipp==3.21.0
-    # via importlib-resources
+
+# The following packages are considered to be unsafe in a requirements file:
+# setuptools

requirements/dev.in

@@ -2,6 +2,7 @@
 -c base.txt
 -c test.txt 
 jupyter
-ipython
+ipython<=8.19; python_version <= '3.9'
+ipython; python_version >= '3.10'
 pip-tools
 matplotlib