chore(deps): bump unstructured to 0.10.25 (#291)

Revert the workaround added in #285

Author: awalker4

CHANGELOG.md

@@ -1,9 +1,9 @@
-## 0.0.54-dev2
+## 0.0.54
 
-* Bump unstructured to 0.10.24
+* Bump unstructured to 0.10.25
 * Use a generator when splitting pdfs in parallel mode
 * Add a default memory minimum for 503 check
-* Fix a UnboundLocalError when an invalid docx file is caught
+* Fix an UnboundLocalError when an invalid docx file is caught
 
 ## 0.0.53
 

prepline_general/api/general.py

@@ -403,13 +403,6 @@ def pipeline_api(
             )
         )
 
-        # TODO(austin) - Latest unstructured won't accept model_name=None
-        # Just pass if it's set until the fix is released
-        # https://github.com/Unstructured-IO/unstructured/issues/1754
-        kwargs = {}
-        if hi_res_model_name:
-            kwargs["model_name"] = hi_res_model_name
-
         # Be careful of naming differences in api params vs partition params!
         # These kwargs are going back into the api, not into partition
         # If there's a difference, remap the param in partition_pdf_splits
@@ -444,6 +437,7 @@ def pipeline_api(
                 # partition_kwargs
                 encoding=encoding,
                 include_page_breaks=include_page_breaks,
+                model_name=hi_res_model_name,
                 ocr_languages=ocr_languages,
                 pdf_infer_table_structure=pdf_infer_table_structure,
                 skip_infer_table_types=skip_infer_table_types,
@@ -454,7 +448,6 @@ def pipeline_api(
                 multipage_sections=multipage_sections,
                 combine_under_n_chars=combine_under_n_chars,
                 new_after_n_chars=new_after_n_chars,
-                **kwargs,
             )
     except ValueError as e:
         if "Invalid file" in e.args[0]:

requirements/base.txt

@@ -51,7 +51,7 @@ et-xmlfile==1.1.0
     # via openpyxl
 exceptiongroup==1.1.3
     # via anyio
-fastapi==0.103.2
+fastapi==0.104.0
     # via -r requirements/base.in
 filelock==3.12.4
     # via
@@ -114,7 +114,7 @@ msg-parser==1.2.0
     # via unstructured
 mypy-extensions==1.0.0
     # via typing-inspect
-networkx==3.1
+networkx==3.2
     # via
     #   torch
     #   unstructured
@@ -139,7 +139,9 @@ olefile==0.46
 omegaconf==2.3.0
     # via effdet
 onnx==1.14.1
-    # via unstructured
+    # via
+    #   unstructured
+    #   unstructured-inference
 onnxruntime==1.15.1
     # via unstructured-inference
 opencv-python==4.8.1.78
@@ -205,7 +207,7 @@ pyparsing==3.1.1
     # via matplotlib
 pypdf==3.16.4
     # via -r requirements/base.in
-pypdfium2==4.21.0
+pypdfium2==4.22.0
     # via pdfplumber
 pytesseract==0.3.10
     # via layoutparser
@@ -273,7 +275,7 @@ sympy==1.12
     #   torch
 tabulate==0.9.0
     # via unstructured
-timm==0.9.7
+timm==0.9.8
     # via effdet
 tokenizers==0.14.1
     # via transformers
@@ -294,7 +296,7 @@ tqdm==4.66.1
     #   iopath
     #   nltk
     #   transformers
-transformers==4.34.0
+transformers==4.34.1
     # via unstructured-inference
 typing-extensions==4.8.0
     # via
@@ -312,17 +314,17 @@ typing-inspect==0.9.0
     # via dataclasses-json
 tzdata==2023.3
     # via pandas
-unstructured[local-inference]==0.10.24
+unstructured[local-inference]==0.10.25
     # via -r requirements/base.in
-unstructured-inference==0.7.7
+unstructured-inference==0.7.9
     # via unstructured
 unstructured-pytesseract==0.3.12
     # via unstructured
-urllib3==2.0.6
+urllib3==2.0.7
     # via requests
 uvicorn==0.23.2
     # via -r requirements/base.in
 xlrd==2.0.1
     # via unstructured
-xlsxwriter==3.1.8
+xlsxwriter==3.1.9
     # via python-pptx

requirements/test.txt

@@ -50,7 +50,7 @@ beautifulsoup4==4.12.2
     #   -r requirements/base.txt
     #   nbconvert
     #   unstructured
-black==23.9.1
+black==23.10.0
     # via -r requirements/test.in
 bleach==6.1.0
     # via nbconvert
@@ -86,9 +86,7 @@ coloredlogs==15.0.1
     #   -r requirements/base.txt
     #   onnxruntime
 comm==0.1.4
-    # via
-    #   ipykernel
-    #   ipywidgets
+    # via ipykernel
 contourpy==1.1.1
     # via
     #   -r requirements/base.txt
@@ -139,7 +137,7 @@ execnb==0.1.5
     # via nbdev
 executing==2.0.0
     # via stack-data
-fastapi==0.103.2
+fastapi==0.104.0
     # via -r requirements/base.txt
 fastcore==1.5.29
     # via
@@ -212,6 +210,7 @@ iopath==0.1.10
     #   layoutparser
 ipykernel==6.25.2
     # via
+    #   ipywidgets
     #   jupyter
     #   jupyter-console
     #   jupyterlab
@@ -224,8 +223,10 @@ ipython==8.16.1
     #   jupyter-console
 ipython-genutils==0.2.0
     # via qtconsole
-ipywidgets==8.1.1
-    # via jupyter
+ipywidgets==8.0.4
+    # via
+    #   jupyter
+    #   nbdev
 isoduration==20.11.0
     # via jsonschema
 jedi==0.19.1
@@ -350,7 +351,7 @@ msg-parser==1.2.0
     # via
     #   -r requirements/base.txt
     #   unstructured
-mypy==1.6.0
+mypy==1.6.1
     # via -r requirements/test.in
 mypy-extensions==1.0.0
     # via
@@ -364,7 +365,7 @@ nbconvert==7.9.2
     # via
     #   jupyter
     #   jupyter-server
-nbdev==2.3.12
+nbdev==2.3.13
     # via -r requirements/test.in
 nbformat==5.9.2
     # via
@@ -373,7 +374,7 @@ nbformat==5.9.2
     #   nbconvert
 nest-asyncio==1.5.8
     # via ipykernel
-networkx==3.1
+networkx==3.2
     # via
     #   -r requirements/base.txt
     #   torch
@@ -415,6 +416,7 @@ onnx==1.14.1
     # via
     #   -r requirements/base.txt
     #   unstructured
+    #   unstructured-inference
 onnxruntime==1.15.1
     # via
     #   -r requirements/base.txt
@@ -556,7 +558,7 @@ pyparsing==3.1.1
     #   matplotlib
 pypdf==3.16.4
     # via -r requirements/base.txt
-pypdfium2==4.21.0
+pypdfium2==4.22.0
     # via
     #   -r requirements/base.txt
     #   pdfplumber
@@ -570,7 +572,7 @@ pytest==7.4.2
     #   pytest-mock
 pytest-cov==4.1.0
     # via -r requirements/test.in
-pytest-mock==3.11.1
+pytest-mock==3.12.0
     # via -r requirements/test.in
 python-dateutil==2.8.2
     # via
@@ -714,7 +716,7 @@ terminado==0.17.1
     # via
     #   jupyter-server
     #   jupyter-server-terminals
-timm==0.9.7
+timm==0.9.8
     # via
     #   -r requirements/base.txt
     #   effdet
@@ -776,7 +778,7 @@ traitlets==5.11.2
     #   nbconvert
     #   nbformat
     #   qtconsole
-transformers==4.34.0
+transformers==4.34.1
     # via
     #   -r requirements/base.txt
     #   unstructured-inference
@@ -805,9 +807,9 @@ tzdata==2023.3
     # via
     #   -r requirements/base.txt
     #   pandas
-unstructured[local-inference]==0.10.24
+unstructured[local-inference]==0.10.25
     # via -r requirements/base.txt
-unstructured-inference==0.7.7
+unstructured-inference==0.7.9
     # via
     #   -r requirements/base.txt
     #   unstructured
@@ -817,7 +819,7 @@ unstructured-pytesseract==0.3.12
     #   unstructured
 uri-template==1.3.0
     # via jsonschema
-urllib3==2.0.6
+urllib3==2.0.7
     # via
     #   -r requirements/base.txt
     #   requests
@@ -843,7 +845,7 @@ xlrd==2.0.1
     # via
     #   -r requirements/base.txt
     #   unstructured
-xlsxwriter==3.1.8
+xlsxwriter==3.1.9
     # via
     #   -r requirements/base.txt
     #   python-pptx

scripts/smoketest.py

@@ -163,4 +163,6 @@ def test_table_support(strategy, pdf_infer_table_structure, expected_table_num):
     assert len(extracted_tables) == expected_table_num
     if expected_table_num > 0:
         # Test a text form a table is extracted
-        assert "Layouts of scanned modern magazines and scientific reports" in extracted_tables[0]
+        # Note(austin) - table output has changed - this line isn't returned
+        # assert "Layouts of scanned modern magazines and scientific reports" in extracted_tables[0]
+        assert "Layouts of history" in extracted_tables[0]