Chore: bump unstructured library to 0.9.0 (#174)

* pip compile

* chnagelog

* change field to drop last_modified

Author: yuming-long

CHANGELOG.md

@@ -1,5 +1,6 @@
-## 0.0.34-dev1
+## 0.0.34
 
+* Bump unstructured library to 0.9.0
 * Add table support for image with parameter `skip_infer_table_types`
 * Add support for gzipped files
 

pipeline-notebooks/pipeline-general.ipynb

@@ -886,10 +886,8 @@
     "        if not show_coordinates and element.metadata.coordinates:\n",
     "            elements[i].metadata.coordinates = None\n",
     "        \n",
-    "        # Note(yuming): currently removing date from metadata\n",
-    "        # since it should be fixed in the core library\n",
-    "        if element.metadata.date:\n",
-    "            elements[i].metadata.date = None\n",
+    "        if element.metadata.last_modified:\n",
+    "            elements[i].metadata.last_modified = None\n",
     "        \n",
     "    if response_type == \"text/csv\":\n",
     "        df = convert_to_dataframe(elements)\n",

prepline_general/api/general.py

@@ -364,10 +364,8 @@ def pipeline_api(
         if not show_coordinates and element.metadata.coordinates:
             elements[i].metadata.coordinates = None
 
-        # Note(yuming): currently removing date from metadata
-        # since it should be fixed in the core library
-        if element.metadata.date:
-            elements[i].metadata.date = None
+        if element.metadata.last_modified:
+            elements[i].metadata.last_modified = None
 
     if response_type == "text/csv":
         df = convert_to_dataframe(elements)

requirements/base.txt

@@ -24,7 +24,7 @@ certifi==2023.7.22
     # via requests
 cffi==1.15.1
     # via cryptography
-chardet==5.1.0
+chardet==5.2.0
     # via unstructured
 charset-normalizer==3.2.0
     # via
@@ -40,7 +40,7 @@ coloredlogs==15.0.1
     # via onnxruntime
 contourpy==1.1.0
     # via matplotlib
-cryptography==41.0.2
+cryptography==41.0.3
     # via pdfminer-six
 cycler==0.11.0
     # via matplotlib
@@ -65,7 +65,7 @@ filetype==1.2.0
     # via unstructured
 flatbuffers==23.5.26
     # via onnxruntime
-fonttools==4.41.1
+fonttools==4.42.0
     # via matplotlib
 fsspec==2023.6.0
     # via huggingface-hub
@@ -103,7 +103,7 @@ jinja2==3.1.2
     #   unstructured-api-tools
 joblib==1.3.1
     # via nltk
-jsonschema==4.18.4
+jsonschema==4.18.6
     # via nbformat
 jsonschema-specifications==2023.7.1
     # via jsonschema
@@ -205,7 +205,7 @@ pdfminer-six==20221105
     #   unstructured
 pdfplumber==0.10.2
     # via layoutparser
-pillow==10.0.0
+pillow==9.5.0
     # via
     #   layoutparser
     #   matplotlib
@@ -278,7 +278,7 @@ pyzmq==25.1.0
     # via jupyter-client
 ratelimit==2.2.1
     # via -r requirements/base.in
-referencing==0.30.0
+referencing==0.30.1
     # via
     #   jsonschema
     #   jsonschema-specifications
@@ -319,7 +319,7 @@ sympy==1.12
     #   torch
 tabulate==0.9.0
     # via unstructured
-timm==0.9.2
+timm==0.9.5
     # via effdet
 tinycss2==1.2.1
     # via nbconvert
@@ -378,7 +378,7 @@ typing-extensions==4.7.1
     #   uvicorn
 tzdata==2023.3
     # via pandas
-unstructured[local-inference]==0.8.7
+unstructured[local-inference]==0.9.0
     # via -r requirements/base.in
 unstructured-api-tools==0.10.10
     # via -r requirements/base.in

requirements/test.txt

@@ -67,7 +67,7 @@ cffi==1.15.1
     #   -r requirements/base.txt
     #   argon2-cffi-bindings
     #   cryptography
-chardet==5.1.0
+chardet==5.2.0
     # via
     #   -r requirements/base.txt
     #   unstructured
@@ -88,15 +88,17 @@ coloredlogs==15.0.1
     # via
     #   -r requirements/base.txt
     #   onnxruntime
-comm==0.1.3
-    # via ipykernel
+comm==0.1.4
+    # via
+    #   ipykernel
+    #   ipywidgets
 contourpy==1.1.0
     # via
     #   -r requirements/base.txt
     #   matplotlib
 coverage[toml]==7.2.7
     # via pytest-cov
-cryptography==41.0.2
+cryptography==41.0.3
     # via
     #   -r requirements/base.txt
     #   pdfminer-six
@@ -158,7 +160,7 @@ flatbuffers==23.5.26
     # via
     #   -r requirements/base.txt
     #   onnxruntime
-fonttools==4.41.1
+fonttools==4.42.0
     # via
     #   -r requirements/base.txt
     #   matplotlib
@@ -225,7 +227,6 @@ iopath==0.1.10
     #   layoutparser
 ipykernel==6.25.0
     # via
-    #   ipywidgets
     #   jupyter
     #   jupyter-console
     #   jupyterlab
@@ -238,7 +239,7 @@ ipython==8.12.2
     #   jupyter-console
 ipython-genutils==0.2.0
     # via qtconsole
-ipywidgets==8.0.7
+ipywidgets==8.1.0
     # via jupyter
 isoduration==20.11.0
     # via jsonschema
@@ -261,7 +262,7 @@ json5==0.9.14
     # via jupyterlab-server
 jsonpointer==2.4
     # via jsonschema
-jsonschema[format-nongpl]==4.18.4
+jsonschema[format-nongpl]==4.18.6
     # via
     #   -r requirements/base.txt
     #   jupyter-events
@@ -308,7 +309,7 @@ jupyter-server==2.7.0
     #   notebook-shim
 jupyter-server-terminals==0.4.4
     # via jupyter-server
-jupyterlab==4.0.3
+jupyterlab==4.0.4
     # via notebook
 jupyterlab-pygments==0.2.2
     # via
@@ -403,7 +404,7 @@ nltk==3.8.1
     # via
     #   -r requirements/base.txt
     #   unstructured
-notebook==7.0.1
+notebook==7.0.2
     # via jupyter
 notebook-shim==0.2.3
     # via
@@ -496,7 +497,7 @@ pexpect==4.8.0
     # via ipython
 pickleshare==0.7.5
     # via ipython
-pillow==10.0.0
+pillow==9.5.0
     # via
     #   -r requirements/base.txt
     #   layoutparser
@@ -654,7 +655,7 @@ qtpy==2.3.1
     # via qtconsole
 ratelimit==2.2.1
     # via -r requirements/base.txt
-referencing==0.30.0
+referencing==0.30.1
     # via
     #   -r requirements/base.txt
     #   jsonschema
@@ -734,7 +735,7 @@ terminado==0.17.1
     # via
     #   jupyter-server
     #   jupyter-server-terminals
-timm==0.9.2
+timm==0.9.5
     # via
     #   -r requirements/base.txt
     #   effdet
@@ -837,7 +838,7 @@ tzdata==2023.3
     # via
     #   -r requirements/base.txt
     #   pandas
-unstructured[local-inference]==0.8.7
+unstructured[local-inference]==0.9.0
     # via -r requirements/base.txt
 unstructured-api-tools==0.10.10
     # via -r requirements/base.txt