⚡️ Speed up function boxes_iou by 13% in PR #4112 (feat/track-text-source)

CHANGELOG.md

@@ -1,3 +1,12 @@
+## 0.18.17-dev0
+
+### Enhancement
+- Flag extracted elements as such in the metadata for downstream use
+
+### Features
+
+### Fixes
+
 ## 0.18.16
 
 ### Enhancement

requirements/base.txt

@@ -27,7 +27,7 @@ click==8.3.0
     # via
     #   nltk
     #   python-oxmsg
-cryptography==46.0.2
+cryptography==46.0.3
     # via unstructured-client
 dataclasses-json==0.6.7
     # via
@@ -85,11 +85,11 @@ packaging==25.0
     # via
     #   marshmallow
     #   unstructured-client
-psutil==7.1.0
+psutil==7.1.3
     # via -r ./base.in
 pycparser==2.23
     # via cffi
-pypdf==6.1.1
+pypdf==6.1.3
     # via unstructured-client
 python-dateutil==2.9.0.post0
     # via unstructured-client
@@ -99,9 +99,9 @@ python-magic==0.4.27
     # via -r ./base.in
 python-oxmsg==0.0.2
     # via -r ./base.in
-rapidfuzz==3.14.1
+rapidfuzz==3.14.3
     # via -r ./base.in
-regex==2025.9.18
+regex==2025.11.3
     # via nltk
 requests==2.32.5
     # via
@@ -150,5 +150,5 @@ urllib3==2.5.0
     #   unstructured-client
 webencodings==0.5.1
     # via html5lib
-wrapt==1.17.3
+wrapt==2.0.0
     # via -r ./base.in

requirements/dev.txt

@@ -50,7 +50,7 @@ typing-extensions==4.15.0
     #   -c ./base.txt
     #   -c ./test.txt
     #   virtualenv
-virtualenv==20.35.3
+virtualenv==20.35.4
     # via pre-commit
 wheel==0.45.1
     # via pip-tools

requirements/extra-markdown.txt

@@ -4,5 +4,5 @@
 #
 #    pip-compile ./extra-markdown.in
 #
-markdown==3.9
+markdown==3.10
     # via -r ./extra-markdown.in

requirements/extra-paddleocr.txt

@@ -30,7 +30,7 @@ charset-normalizer==3.4.4
     # via
     #   -c ./base.txt
     #   requests
-cython==3.1.4
+cython==3.2.0
     # via unstructured-paddleocr
 exceptiongroup==1.3.0
     # via
@@ -58,7 +58,7 @@ idna==3.11
     #   anyio
     #   httpx
     #   requests
-imageio==2.37.0
+imageio==2.37.2
     # via scikit-image
 lazy-loader==0.4
     # via scikit-image
@@ -101,31 +101,31 @@ packaging==25.0
     #   -c ./base.txt
     #   lazy-loader
     #   scikit-image
-paddlepaddle==3.2.0
+paddlepaddle==3.2.1
     # via -r ./extra-paddleocr.in
-pillow==11.3.0
+pillow==12.0.0
     # via
     #   imageio
     #   paddlepaddle
     #   scikit-image
     #   unstructured-paddleocr
-protobuf==6.32.1
+protobuf==6.33.0
     # via
     #   -c ./deps/constraints.txt
     #   paddlepaddle
 pyclipper==1.3.0.post6
     # via unstructured-paddleocr
-pydantic==2.12.2
+pydantic==2.12.4
     # via albumentations
-pydantic-core==2.41.4
+pydantic-core==2.41.5
     # via pydantic
 python-docx==1.2.0
     # via unstructured-paddleocr
 pyyaml==6.0.3
     # via
     #   albumentations
     #   unstructured-paddleocr
-rapidfuzz==3.14.1
+rapidfuzz==3.14.3
     # via
     #   -c ./base.txt
     #   unstructured-paddleocr
@@ -153,9 +153,9 @@ soupsieve==2.8
     # via
     #   -c ./base.txt
     #   beautifulsoup4
-stringzilla==4.2.1
+stringzilla==4.2.3
     # via albucore
-termcolor==3.1.0
+termcolor==3.2.0
     # via fire
 tifffile==2025.5.10
     # via scikit-image

requirements/extra-pdf-image.in

@@ -12,5 +12,5 @@ google-cloud-vision
 effdet
 # Do not move to constraints.in, otherwise unstructured-inference will not be upgraded
 # when unstructured library is.
-unstructured-inference>=1.0.5
+unstructured-inference>=1.1.1
 unstructured.pytesseract>=0.3.12

requirements/extra-pdf-image.txt

@@ -4,7 +4,7 @@
 #
 #    pip-compile ./extra-pdf-image.in
 #
-accelerate==1.10.1
+accelerate==1.11.0
     # via unstructured-inference
 antlr4-python3-runtime==4.9.3
     # via omegaconf
@@ -27,13 +27,13 @@ coloredlogs==15.0.1
     # via onnxruntime
 contourpy==1.3.2
     # via matplotlib
-cryptography==46.0.2
+cryptography==46.0.3
     # via
     #   -c ./base.txt
     #   pdfminer-six
 cycler==0.12.1
     # via matplotlib
-deprecated==1.2.18
+deprecated==1.3.1
     # via pikepdf
 effdet==0.4.1
     # via -r ./extra-pdf-image.in
@@ -46,31 +46,32 @@ flatbuffers==25.9.23
     # via onnxruntime
 fonttools==4.60.1
     # via matplotlib
-fsspec==2025.9.0
+fsspec==2025.10.0
     # via
     #   huggingface-hub
     #   torch
-google-api-core[grpc]==2.26.0
+google-api-core[grpc]==2.28.1
     # via google-cloud-vision
-google-auth==2.41.1
+google-auth==2.42.1
     # via
     #   google-api-core
     #   google-cloud-vision
-google-cloud-vision==3.10.2
+google-cloud-vision==3.11.0
     # via -r ./extra-pdf-image.in
-googleapis-common-protos==1.70.0
+googleapis-common-protos==1.71.0
     # via
     #   google-api-core
     #   grpcio-status
-grpcio==1.75.1
+grpcio==1.76.0
     # via
     #   google-api-core
+    #   google-cloud-vision
     #   grpcio-status
-grpcio-status==1.75.1
+grpcio-status==1.76.0
     # via google-api-core
-hf-xet==1.1.10
+hf-xet==1.2.0
     # via huggingface-hub
-huggingface-hub==0.35.3
+huggingface-hub==0.36.0
     # via
     #   accelerate
     #   timm
@@ -123,7 +124,7 @@ onnx==1.19.1
     # via
     #   -r ./extra-pdf-image.in
     #   unstructured-inference
-onnxruntime==1.23.1
+onnxruntime==1.23.2
     # via
     #   -r ./extra-pdf-image.in
     #   unstructured-inference
@@ -150,9 +151,9 @@ pdfminer-six==20250327
     #   unstructured-inference
 pi-heif==1.1.1
     # via -r ./extra-pdf-image.in
-pikepdf==9.11.0
+pikepdf==10.0.0
     # via -r ./extra-pdf-image.in
-pillow==11.3.0
+pillow==12.0.0
     # via
     #   matplotlib
     #   pdf2image
@@ -164,7 +165,7 @@ proto-plus==1.26.1
     # via
     #   google-api-core
     #   google-cloud-vision
-protobuf==6.32.1
+protobuf==6.33.0
     # via
     #   -c ./deps/constraints.txt
     #   google-api-core
@@ -174,7 +175,7 @@ protobuf==6.32.1
     #   onnx
     #   onnxruntime
     #   proto-plus
-psutil==7.1.0
+psutil==7.1.3
     # via
     #   -c ./base.txt
     #   accelerate
@@ -192,11 +193,11 @@ pycparser==2.23
     #   cffi
 pyparsing==3.2.5
     # via matplotlib
-pypdf==6.1.1
+pypdf==6.1.3
     # via
     #   -c ./base.txt
     #   -r ./extra-pdf-image.in
-pypdfium2==4.30.0
+pypdfium2==5.0.0
     # via unstructured-inference
 python-dateutil==2.9.0.post0
     # via
@@ -214,11 +215,11 @@ pyyaml==6.0.3
     #   omegaconf
     #   timm
     #   transformers
-rapidfuzz==3.14.1
+rapidfuzz==3.14.3
     # via
     #   -c ./base.txt
     #   unstructured-inference
-regex==2025.9.18
+regex==2025.11.3
     # via
     #   -c ./base.txt
     #   transformers
@@ -245,7 +246,7 @@ sympy==1.14.0
     # via
     #   onnxruntime
     #   torch
-timm==1.0.20
+timm==1.0.22
     # via
     #   effdet
     #   unstructured-inference
@@ -282,7 +283,7 @@ typing-extensions==4.15.0
     #   torch
 tzdata==2025.2
     # via pandas
-unstructured-inference==1.0.5
+unstructured-inference==1.1.1
     # via -r ./extra-pdf-image.in
 unstructured-pytesseract==0.3.15
     # via -r ./extra-pdf-image.in
@@ -291,7 +292,7 @@ urllib3==2.5.0
     #   -c ./base.txt
     #   -c ./deps/constraints.txt
     #   requests
-wrapt==1.17.3
+wrapt==2.0.0
     # via
     #   -c ./base.txt
     #   deprecated

requirements/extra-pptx.txt

@@ -6,7 +6,7 @@
 #
 lxml==6.0.2
     # via python-pptx
-pillow==11.3.0
+pillow==12.0.0
     # via python-pptx
 python-pptx==1.0.2
     # via -r ./extra-pptx.in

requirements/extra-xlsx.txt

@@ -8,16 +8,16 @@ cffi==2.0.0
     # via
     #   -c ./base.txt
     #   cryptography
-cryptography==46.0.2
+cryptography==46.0.3
     # via
     #   -c ./base.txt
     #   msoffcrypto-tool
 et-xmlfile==2.0.0
     # via openpyxl
 msoffcrypto-tool==5.4.2
-    # via -r ./extra-xlsx.in
+    # via -r extra-xlsx.in
 networkx==3.4.2
-    # via -r ./extra-xlsx.in
+    # via -r extra-xlsx.in
 numpy==2.2.6
     # via
     #   -c ./base.txt
@@ -27,9 +27,9 @@ olefile==0.47
     #   -c ./base.txt
     #   msoffcrypto-tool
 openpyxl==3.1.5
-    # via -r ./extra-xlsx.in
+    # via -r extra-xlsx.in
 pandas==2.3.3
-    # via -r ./extra-xlsx.in
+    # via -r extra-xlsx.in
 pycparser==2.23
     # via
     #   -c ./base.txt
@@ -51,4 +51,4 @@ typing-extensions==4.15.0
 tzdata==2025.2
     # via pandas
 xlrd==2.0.2
-    # via -r ./extra-xlsx.in
+    # via -r extra-xlsx.in

requirements/huggingface.txt

@@ -21,13 +21,13 @@ filelock==3.20.0
     #   huggingface-hub
     #   torch
     #   transformers
-fsspec==2025.9.0
+fsspec==2025.10.0
     # via
     #   huggingface-hub
     #   torch
-hf-xet==1.1.10
+hf-xet==1.2.0
     # via huggingface-hub
-huggingface-hub==0.35.3
+huggingface-hub==0.36.0
     # via
     #   tokenizers
     #   transformers
@@ -64,7 +64,7 @@ pyyaml==6.0.3
     # via
     #   huggingface-hub
     #   transformers
-regex==2025.9.18
+regex==2025.11.3
     # via
     #   -c ./base.txt
     #   sacremoses