Merge branch 'refs/heads/main' into feature/zh_adaptation

# Conflicts: # CHANGELOG.md
Unstructured-IO · Aug 15, 2024 · 7c0adf7 · 7c0adf7
2 parents 6dc2aed + 9b778e2
commit 7c0adf7
Show file tree

Hide file tree

Showing 6 changed files with 23 additions and 10 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,8 +1,22 @@
-## 0.15.2-dev1
+## 0.15.4
 
 ### Enhancements
 
-* Fix Compatibility Issue with Chinese Text in Document Parsing
+### Features
+
+### Fixes
+
+* **Resolve an installation error with `pytesseract>=0.3.12` that occurred during `pip install unstructured[pdf]==0.15.3`.**  
+
+## 0.15.3
+
+### Enhancements
+
+### Features
+
+### Fixes
+
+* **Remove the custom index URL from `extra-paddleocr.in` to resolve the error in the `setup.py` configuration.**
 
 ## 0.15.2
 

diff --git a/requirements/deps/constraints.txt b/requirements/deps/constraints.txt
@@ -22,8 +22,7 @@ Office365-REST-Python-Client<2.4.3
 # unstructured-inference to be upgraded when unstructured library is upgraded
 # https://github.com/Unstructured-IO/unstructured/issues/1458
 # unstructured-inference
-# use the known compatible version of weaviate and pytesseract
-pytesseract @ git+https://github.com/madmaze/[email protected]
+# use the known compatible version of weaviate
 weaviate-client>3.25.0
 # TODO: Pinned in transformers package, remove when that gets updated
 tokenizers>=0.19,<0.20

diff --git a/requirements/extra-paddleocr.in b/requirements/extra-paddleocr.in
@@ -1,5 +1,5 @@
 -c ./deps/constraints.txt
 -c base.txt
 
-paddlepaddle==3.0.0b1 -i https://www.paddlepaddle.org.cn/packages/stable/cpu/
+paddlepaddle==3.0.0b1
 unstructured.paddleocr==2.8.0.1
diff --git a/requirements/extra-pdf-image.in b/requirements/extra-pdf-image.in
@@ -12,4 +12,6 @@ effdet
 # Do not move to constraints.in, otherwise unstructured-inference will not be upgraded
 # when unstructured library is.
 unstructured-inference==0.7.36
-pytesseract>=0.3.12
+# NOTE(christine): Pinned to a specific version of pytesseract from the GitHub repository.
+# Remove this pin and switch to the latest version from PyPI once version 0.3.13 or newer is officially released.
+pytesseract @ git+https://github.com/madmaze/[email protected]
diff --git a/requirements/extra-pdf-image.txt b/requirements/extra-pdf-image.txt
@@ -202,9 +202,7 @@ pypdf==4.3.1
 pypdfium2==4.30.0
     # via pdfplumber
 pytesseract @ git+https://github.com/madmaze/[email protected]
-    # via
-    #   -c ././deps/constraints.txt
-    #   -r ./extra-pdf-image.in
+    # via -r ./extra-pdf-image.in
 python-dateutil==2.9.0.post0
     # via
     #   -c ./base.txt

diff --git a/unstructured/__version__.py b/unstructured/__version__.py
@@ -1 +1 @@
-__version__ = "0.15.2"  # pragma: no cover
+__version__ = "0.15.4"  # pragma: no cover
Original file line number	Diff line number	Diff line change
		@@ -1 +1 @@
		__version__ = "0.15.2" # pragma: no cover
		__version__ = "0.15.4" # pragma: no cover