fix: pdf2image library is core requirement (#745)

Author: cragwolfe

CHANGELOG.md

@@ -1,19 +1,19 @@
-## 0.7.5-dev2
+## 0.7.5
 
 ### Enhancements
 
 * Adds functionality to sort elements in `partition_pdf` for `fast` strategy
 * Adds ingest tests with `--fast` strategy on PDF documents
 * Adds --api-key to unstructured-ingest
 
-
 ### Features
 
 * Adds `partition_rst` for processed ReStructured Text documents.
 
 ### Fixes
 
 * Adds handling for emails that do not have a datetime to extract.
+* Adds pdf2image package as core requirement of unstructured (with no extras)
 
 ## 0.7.4
 

requirements/base.in

@@ -7,6 +7,7 @@ msg_parser
 nltk
 openpyxl
 pandas
+pdf2image
 pdfminer.six
 pillow
 pypandoc

requirements/base.txt

@@ -82,11 +82,14 @@ pandas==1.5.3
     # via
     #   -r requirements/base.in
     #   argilla
+pdf2image==1.16.3
+    # via -r requirements/base.in
 pdfminer-six==20221105
     # via -r requirements/base.in
 pillow==9.5.0
     # via
     #   -r requirements/base.in
+    #   pdf2image
     #   python-pptx
 pycparser==2.21
     # via cffi

requirements/dev.txt

@@ -63,7 +63,7 @@ executing==1.2.0
     # via stack-data
 fastjsonschema==2.17.1
     # via nbformat
-filelock==3.12.1
+filelock==3.12.2
     # via virtualenv
 fqdn==1.5.1
     # via jsonschema
@@ -82,7 +82,7 @@ importlib-metadata==6.6.0
     #   nbconvert
 importlib-resources==5.12.0
     # via jsonschema
-ipykernel==6.23.1
+ipykernel==6.23.2
     # via
     #   ipywidgets
     #   jupyter
@@ -171,7 +171,7 @@ nbclassic==1.0.0
     # via notebook
 nbclient==0.8.0
     # via nbconvert
-nbconvert==7.4.0
+nbconvert==7.5.0
     # via
     #   jupyter
     #   jupyter-server
@@ -224,7 +224,7 @@ platformdirs==3.5.3
     #   -c requirements/test.txt
     #   jupyter-core
     #   virtualenv
-pre-commit==3.3.2
+pre-commit==3.3.3
     # via -r requirements/dev.in
 prometheus-client==0.17.0
     # via

requirements/huggingface.txt

@@ -17,7 +17,7 @@ click==8.1.3
     # via
     #   -c requirements/base.txt
     #   sacremoses
-filelock==3.12.1
+filelock==3.12.2
     # via
     #   huggingface-hub
     #   torch
@@ -90,7 +90,7 @@ tqdm==4.65.0
     #   huggingface-hub
     #   sacremoses
     #   transformers
-transformers==4.30.1
+transformers==4.30.2
     # via -r requirements/huggingface.in
 typing-extensions==4.6.3
     # via

requirements/ingest-azure.txt

@@ -14,7 +14,7 @@ async-timeout==4.0.2
     # via aiohttp
 attrs==23.1.0
     # via aiohttp
-azure-core==1.27.0
+azure-core==1.27.1
     # via
     #   adlfs
     #   azure-identity

requirements/ingest-discord.txt

@@ -16,7 +16,7 @@ charset-normalizer==3.1.0
     # via
     #   -c requirements/base.txt
     #   aiohttp
-discord-py==2.2.3
+discord-py==2.3.0
     # via -r requirements/ingest-discord.in
 frozenlist==1.3.3
     # via

requirements/ingest-google-drive.txt

@@ -17,16 +17,16 @@ charset-normalizer==3.1.0
     #   requests
 google-api-core==2.11.0
     # via google-api-python-client
-google-api-python-client==2.88.0
+google-api-python-client==2.89.0
     # via -r requirements/ingest-google-drive.in
-google-auth==2.19.1
+google-auth==2.20.0
     # via
     #   google-api-core
     #   google-api-python-client
     #   google-auth-httplib2
 google-auth-httplib2==0.1.0
     # via google-api-python-client
-googleapis-common-protos==1.59.0
+googleapis-common-protos==1.59.1
     # via google-api-core
 httplib2==0.22.0
     # via

requirements/local-inference.txt

@@ -22,7 +22,7 @@ charset-normalizer==3.1.0
     #   requests
 coloredlogs==15.0.1
     # via onnxruntime
-contourpy==1.0.7
+contourpy==1.1.0
     # via matplotlib
 cryptography==41.0.1
     # via
@@ -32,7 +32,7 @@ cycler==0.11.0
     # via matplotlib
 effdet==0.4.1
     # via layoutparser
-filelock==3.12.1
+filelock==3.12.2
     # via
     #   huggingface-hub
     #   torch
@@ -106,7 +106,9 @@ pandas==1.5.3
     #   -c requirements/base.txt
     #   layoutparser
 pdf2image==1.16.3
-    # via layoutparser
+    # via
+    #   -c requirements/base.txt
+    #   layoutparser
 pdfminer-six==20221105
     # via
     #   -c requirements/base.txt
@@ -201,7 +203,7 @@ tqdm==4.65.0
     #   huggingface-hub
     #   iopath
     #   transformers
-transformers==4.30.1
+transformers==4.30.2
     # via unstructured-inference
 typing-extensions==4.6.3
     # via

unstructured/__version__.py

@@ -1 +1 @@
-__version__ = "0.7.5-dev2"  # pragma: no cover
+__version__ = "0.7.5"  # pragma: no cover