remove layoutparser lib (#403)

this PR is to remove the layoutparser lib as we no longer rely on it
anymore

hence the README.md is also updated to drop the note on supporting
layoutparser model zoo

Author: tbs17

CHANGELOG.md

@@ -1,3 +1,9 @@
+## 0.8.3
+
+* fix: removed `layoutelement.from_lp_textblock()` and related tests as it's not used
+* fix: update requirements to drop `layoutparser` lib
+* fix: update `README.md` to remove layoutparser model zoo support note
+
 ## 0.8.2
 
 * fix: fix bug when an empty list is passed into `TextRegions.from_list` triggers `IndexError`

README.md

@@ -72,10 +72,6 @@ model = get_model("yolox")
 layout = DocumentLayout.from_file("sample-docs/layout-parser-paper.pdf", detection_model=model)
 ```
 
-### Using models from the layoutparser model zoo
-
-The `UnstructuredDetectronModel` class in `unstructured_inference.modelts.detectron2` uses the `faster_rcnn_R_50_FPN_3x` model pretrained on DocLayNet, but by using different construction parameters, any model in the `layoutparser` [model zoo](https://layout-parser.readthedocs.io/en/latest/notes/modelzoo.html) can be used. `UnstructuredDetectronModel` is a light wrapper around the `layoutparser` `Detectron2LayoutModel` object, and accepts the same arguments. See [layoutparser documentation](https://layout-parser.readthedocs.io/en/latest/api_doc/models.html#layoutparser.models.Detectron2LayoutModel) for details.
-
 ### Using your own model
 
 Any detection model can be used for in the `unstructured_inference` pipeline by wrapping the model in the `UnstructuredObjectDetectionModel` class. To integrate with the `DocumentLayout` class, a subclass of `UnstructuredObjectDetectionModel` must have a `predict` method that accepts a `PIL.Image.Image` and returns a list of `LayoutElement`s, and an `initialize` method, which loads the model and prepares it for inference.

requirements/base.in

@@ -1,5 +1,4 @@
 -c constraints.in
-layoutparser
 python-multipart
 huggingface-hub
 numpy<2
@@ -12,3 +11,6 @@ timm
 # NOTE(alan): Pinned because this is when the most recent module we import appeared
 transformers>=4.25.1
 rapidfuzz
+pandas
+scipy
+pdfplumber

requirements/base.txt

@@ -4,58 +4,54 @@
 #
 #    pip-compile requirements/base.in
 #
-certifi==2024.8.30
+certifi==2024.12.14
     # via requests
 cffi==1.17.1
     # via cryptography
-charset-normalizer==3.3.2
+charset-normalizer==3.4.1
     # via
     #   pdfminer-six
     #   requests
 coloredlogs==15.0.1
     # via onnxruntime
 contourpy==1.3.0
     # via matplotlib
-cryptography==43.0.1
+cryptography==44.0.0
     # via pdfminer-six
 cycler==0.12.1
     # via matplotlib
-filelock==3.16.0
+filelock==3.16.1
     # via
     #   huggingface-hub
     #   torch
     #   transformers
-flatbuffers==24.3.25
+flatbuffers==24.12.23
     # via onnxruntime
-fonttools==4.53.1
+fonttools==4.55.3
     # via matplotlib
-fsspec==2024.9.0
+fsspec==2024.12.0
     # via
     #   huggingface-hub
     #   torch
-huggingface-hub==0.24.7
+huggingface-hub==0.27.1
     # via
     #   -r requirements/base.in
     #   timm
     #   tokenizers
     #   transformers
 humanfriendly==10.0
     # via coloredlogs
-idna==3.8
+idna==3.10
     # via requests
-importlib-resources==6.4.5
+importlib-resources==6.5.2
     # via matplotlib
-iopath==0.1.10
-    # via layoutparser
-jinja2==3.1.4
+jinja2==3.1.5
     # via torch
 kiwisolver==1.4.7
     # via matplotlib
-layoutparser==0.3.4
-    # via -r requirements/base.in
-markupsafe==2.1.5
+markupsafe==3.0.2
     # via jinja2
-matplotlib==3.9.2
+matplotlib==3.9.4
     # via -r requirements/base.in
 mpmath==1.3.0
     # via sympy
@@ -65,7 +61,6 @@ numpy==1.26.4
     # via
     #   -r requirements/base.in
     #   contourpy
-    #   layoutparser
     #   matplotlib
     #   onnx
     #   onnxruntime
@@ -74,107 +69,96 @@ numpy==1.26.4
     #   scipy
     #   torchvision
     #   transformers
-onnx==1.16.2
+onnx==1.17.0
     # via -r requirements/base.in
 onnxruntime==1.19.2
     # via -r requirements/base.in
-opencv-python==4.10.0.84
-    # via
-    #   -r requirements/base.in
-    #   layoutparser
-packaging==24.1
+opencv-python==4.11.0.86
+    # via -r requirements/base.in
+packaging==24.2
     # via
     #   huggingface-hub
     #   matplotlib
     #   onnxruntime
     #   transformers
-pandas==2.2.2
-    # via layoutparser
-pdf2image==1.17.0
-    # via layoutparser
+pandas==2.2.3
+    # via -r requirements/base.in
 pdfminer-six==20231228
     # via pdfplumber
-pdfplumber==0.11.4
-    # via layoutparser
-pillow==10.4.0
+pdfplumber==0.11.5
+    # via -r requirements/base.in
+pillow==11.1.0
     # via
-    #   layoutparser
     #   matplotlib
-    #   pdf2image
     #   pdfplumber
     #   torchvision
-portalocker==2.10.1
-    # via iopath
-protobuf==5.28.1
+protobuf==5.29.3
     # via
     #   onnx
     #   onnxruntime
 pycparser==2.22
     # via cffi
-pyparsing==3.1.4
+pyparsing==3.2.1
     # via matplotlib
-pypdfium2==4.30.0
+pypdfium2==4.30.1
     # via pdfplumber
 python-dateutil==2.9.0.post0
     # via
     #   matplotlib
     #   pandas
-python-multipart==0.0.9
+python-multipart==0.0.20
     # via -r requirements/base.in
 pytz==2024.2
     # via pandas
 pyyaml==6.0.2
     # via
     #   huggingface-hub
-    #   layoutparser
     #   timm
     #   transformers
-rapidfuzz==3.9.7
+rapidfuzz==3.11.0
     # via -r requirements/base.in
-regex==2024.9.11
+regex==2024.11.6
     # via transformers
 requests==2.32.3
     # via
     #   huggingface-hub
     #   transformers
-safetensors==0.4.5
+safetensors==0.5.2
     # via
     #   timm
     #   transformers
 scipy==1.13.1
-    # via layoutparser
-six==1.16.0
+    # via -r requirements/base.in
+six==1.17.0
     # via python-dateutil
-sympy==1.13.2
+sympy==1.13.1
     # via
     #   onnxruntime
     #   torch
-timm==1.0.9
+timm==1.0.13
     # via -r requirements/base.in
-tokenizers==0.19.1
+tokenizers==0.21.0
     # via transformers
-torch==2.4.1
+torch==2.5.1
     # via
     #   -r requirements/base.in
     #   timm
     #   torchvision
-torchvision==0.19.1
+torchvision==0.20.1
     # via timm
-tqdm==4.66.5
+tqdm==4.67.1
     # via
     #   huggingface-hub
-    #   iopath
     #   transformers
-transformers==4.44.2
+transformers==4.48.0
     # via -r requirements/base.in
 typing-extensions==4.12.2
     # via
     #   huggingface-hub
-    #   iopath
     #   torch
-tzdata==2024.1
+tzdata==2024.2
     # via pandas
-urllib3==2.2.3
+urllib3==2.3.0
     # via requests
-zipp==3.20.2
+zipp==3.21.0
     # via importlib-resources