Merge remote-tracking branch 'origin/main' into potter/all-doc-types

CHANGELOG.md

@@ -1,11 +1,9 @@
-## 0.14.9-dev7
+## 0.14.9-dev9
 
 ### Enhancements
 
-* **Added visualization and OD model result dump for PDF** In PDF `hi_res` strategy the `analysis` parameter can be used
-  to visualize the result of the OD model and dump the result to a file.
-  Additionally, the visualization of bounding boxes of each layout source is rendered and saved
-  for each page.
+* **Added visualization and OD model result dump for PDF** In PDF `hi_res` strategy the `analysis` parameter can be used to visualize the result of the OD model and dump the result to a file. Additionally, the visualization of bounding boxes of each layout source is rendered and saved for each page.
+* **`partition_docx()` distinguishes "file not found" from "not a ZIP archive" error.** `partition_docx()` now provides different error messages for "file not found" and "file is not a ZIP archive (and therefore not a DOCX file)". This aids diagnosis since these two conditions generally point in different directions as to the cause and fix.
 
 ### Features
 

requirements/deps/constraints.txt

@@ -56,9 +56,7 @@ fsspec==2024.5.0
 # python 3.12 support
 wrapt>=1.14.0
 
-
-# NOTE(robinson): for compatiblity with voyage embeddings
-langsmith==0.1.62
+langchain-community>=0.2.5
 
 # NOTE(robinson): choma was pinned to importlib-metadata>=7.1.0 but 7.1.0 was installed
 # instead of 7.2.0. Need to investigate

requirements/dev.txt

@@ -66,7 +66,7 @@ comm==0.2.2
     # via
     #   ipykernel
     #   ipywidgets
-debugpy==1.8.1
+debugpy==1.8.2
     # via ipykernel
 decorator==5.1.1
     # via ipython
@@ -186,7 +186,7 @@ jupyter-server==2.14.1
     #   notebook-shim
 jupyter-server-terminals==0.5.3
     # via jupyter-server
-jupyterlab==4.2.2
+jupyterlab==4.2.3
     # via notebook
 jupyterlab-pygments==0.3.0
     # via nbconvert

requirements/ingest/embed-aws-bedrock.txt

@@ -55,20 +55,21 @@ jsonpatch==1.33
     # via langchain-core
 jsonpointer==3.0.0
     # via jsonpatch
-langchain==0.2.3
+langchain==0.2.6
     # via langchain-community
-langchain-community==0.2.4
-    # via -r ./ingest/embed-aws-bedrock.in
-langchain-core==0.2.2
+langchain-community==0.2.6
+    # via
+    #   -c ./ingest/../deps/constraints.txt
+    #   -r ./ingest/embed-aws-bedrock.in
+langchain-core==0.2.10
     # via
     #   langchain
     #   langchain-community
     #   langchain-text-splitters
-langchain-text-splitters==0.2.1
+langchain-text-splitters==0.2.2
     # via langchain
-langsmith==0.1.62
+langsmith==0.1.82
     # via
-    #   -c ./ingest/../deps/constraints.txt
     #   langchain
     #   langchain-community
     #   langchain-core

requirements/ingest/embed-huggingface.txt

@@ -67,20 +67,21 @@ jsonpatch==1.33
     # via langchain-core
 jsonpointer==3.0.0
     # via jsonpatch
-langchain==0.2.3
+langchain==0.2.6
     # via langchain-community
-langchain-community==0.2.4
-    # via -r ./ingest/embed-huggingface.in
-langchain-core==0.2.2
+langchain-community==0.2.6
+    # via
+    #   -c ./ingest/../deps/constraints.txt
+    #   -r ./ingest/embed-huggingface.in
+langchain-core==0.2.10
     # via
     #   langchain
     #   langchain-community
     #   langchain-text-splitters
-langchain-text-splitters==0.2.1
+langchain-text-splitters==0.2.2
     # via langchain
-langsmith==0.1.62
+langsmith==0.1.82
     # via
-    #   -c ./ingest/../deps/constraints.txt
     #   langchain
     #   langchain-community
     #   langchain-core

requirements/ingest/embed-octoai.txt

@@ -38,7 +38,7 @@ idna==3.7
     #   anyio
     #   httpx
     #   requests
-openai==1.35.3
+openai==1.35.5
     # via -r ./ingest/embed-octoai.in
 pydantic==2.7.4
     # via openai

requirements/ingest/embed-openai.txt

@@ -63,20 +63,21 @@ jsonpatch==1.33
     # via langchain-core
 jsonpointer==3.0.0
     # via jsonpatch
-langchain==0.2.3
+langchain==0.2.6
     # via langchain-community
-langchain-community==0.2.4
-    # via -r ./ingest/embed-openai.in
-langchain-core==0.2.2
+langchain-community==0.2.6
+    # via
+    #   -c ./ingest/../deps/constraints.txt
+    #   -r ./ingest/embed-openai.in
+langchain-core==0.2.10
     # via
     #   langchain
     #   langchain-community
     #   langchain-text-splitters
-langchain-text-splitters==0.2.1
+langchain-text-splitters==0.2.2
     # via langchain
-langsmith==0.1.62
+langsmith==0.1.82
     # via
-    #   -c ./ingest/../deps/constraints.txt
     #   langchain
     #   langchain-community
     #   langchain-core
@@ -97,7 +98,7 @@ numpy==1.26.4
     #   -c ./ingest/../base.txt
     #   langchain
     #   langchain-community
-openai==1.35.3
+openai==1.35.5
     # via -r ./ingest/embed-openai.in
 orjson==3.10.5
     # via langsmith

requirements/ingest/embed-vertexai.txt

@@ -100,25 +100,26 @@ jsonpatch==1.33
     # via langchain-core
 jsonpointer==3.0.0
     # via jsonpatch
-langchain==0.2.3
+langchain==0.2.6
     # via
     #   -r ./ingest/embed-vertexai.in
     #   langchain-community
-langchain-community==0.2.4
-    # via -r ./ingest/embed-vertexai.in
-langchain-core==0.2.2
+langchain-community==0.2.6
+    # via
+    #   -c ./ingest/../deps/constraints.txt
+    #   -r ./ingest/embed-vertexai.in
+langchain-core==0.2.10
     # via
     #   langchain
     #   langchain-community
     #   langchain-google-vertexai
     #   langchain-text-splitters
-langchain-google-vertexai==1.0.5
+langchain-google-vertexai==1.0.6
     # via -r ./ingest/embed-vertexai.in
-langchain-text-splitters==0.2.1
+langchain-text-splitters==0.2.2
     # via langchain
-langsmith==0.1.62
+langsmith==0.1.82
     # via
-    #   -c ./ingest/../deps/constraints.txt
     #   langchain
     #   langchain-community
     #   langchain-core

requirements/ingest/embed-voyageai.txt

@@ -42,20 +42,19 @@ jsonpatch==1.33
     # via langchain-core
 jsonpointer==3.0.0
     # via jsonpatch
-langchain==0.2.3
+langchain==0.2.6
     # via -r ./ingest/embed-voyageai.in
-langchain-core==0.2.2
+langchain-core==0.2.10
     # via
     #   langchain
     #   langchain-text-splitters
     #   langchain-voyageai
-langchain-text-splitters==0.2.1
+langchain-text-splitters==0.2.2
     # via langchain
 langchain-voyageai==0.1.1
     # via -r ./ingest/embed-voyageai.in
-langsmith==0.1.62
+langsmith==0.1.82
     # via
-    #   -c ./ingest/../deps/constraints.txt
     #   langchain
     #   langchain-core
 multidict==6.0.5

test_unstructured/partition/test_docx.py

@@ -770,6 +770,19 @@ def opts_args() -> dict[str, Any]:
 class DescribeDocxPartitionerOptions:
     """Unit-test suite for `unstructured.partition.docx.DocxPartitionerOptions` objects."""
 
+    # -- .load() ---------------------------------
+
+    def it_provides_a_validating_constructor(self, opts_args: dict[str, Any]):
+        opts_args["file_path"] = example_doc_path("simple.docx")
+
+        opts = DocxPartitionerOptions.load(**opts_args)
+
+        assert isinstance(opts, DocxPartitionerOptions)
+
+    def and_it_raises_when_options_are_not_valid(self, opts_args: dict[str, Any]):
+        with pytest.raises(ValueError, match="no DOCX document specified, "):
+            DocxPartitionerOptions.load(**opts_args)
+
     # -- .document -------------------------------
 
     def it_loads_the_docx_document(
@@ -1024,13 +1037,31 @@ def and_it_uses_the_provided_file_directly_when_not_a_SpooledTemporaryFile(
         assert isinstance(docx_file, io.BytesIO)
         assert docx_file.getvalue() == b"abcdefg"
 
-    def but_it_raises_ValueError_when_neither_a_file_path_or_file_is_provided(
+    # -- ._validate() ----------------------------
+
+    def it_raises_when_no_file_exists_at_file_path(self, opts_args: dict[str, Any]):
+        opts_args["file_path"] = "l/m/n.docx"
+        with pytest.raises(FileNotFoundError, match="no such file or directory: 'l/m/n.docx'"):
+            DocxPartitionerOptions.load(**opts_args)
+
+    def and_it_raises_when_the_file_at_file_path_is_not_a_ZIP_archive(
         self, opts_args: dict[str, Any]
     ):
-        opts = DocxPartitionerOptions(**opts_args)
+        opts_args["file_path"] = example_doc_path("simple.doc")
+        with pytest.raises(ValueError, match=r"not a ZIP archive \(so not a DOCX file\): "):
+            DocxPartitionerOptions.load(**opts_args)
 
-        with pytest.raises(ValueError, match="No DOCX document specified, either `filename` or "):
-            opts._docx_file
+    def and_it_raises_when_the_file_like_object_is_not_a_ZIP_archive(
+        self, opts_args: dict[str, Any]
+    ):
+        with open(example_doc_path("simple.doc"), "rb") as f:
+            opts_args["file"] = f
+            with pytest.raises(ValueError, match=r"not a ZIP archive \(so not a DOCX file\): "):
+                DocxPartitionerOptions.load(**opts_args)
+
+    def and_it_raises_when_neither_a_file_path_or_file_is_provided(self, opts_args: dict[str, Any]):
+        with pytest.raises(ValueError, match="no DOCX document specified, either `filename` or "):
+            DocxPartitionerOptions.load(**opts_args)
 
     # -- fixtures --------------------------------------------------------------------------------
 

test_unstructured_ingest/expected-structured-output/Sharepoint-with-permissions/Shared Documents/Document.docx.json

@@ -0,0 +1 @@
+[]