Unstructured-IO · qued · Oct 13, 2023 · Oct 3, 2023 · Oct 3, 2023 · Oct 3, 2023
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -113,6 +113,7 @@ jobs:
     runs-on: ubuntu-latest
     env:
       NLTK_DATA: ${{ github.workspace }}/nltk_data
+      UNSTRUCTURED_HF_TOKEN: ${{ secrets.HF_TOKEN }}
     needs: [setup, lint]
     steps:
     - uses: actions/checkout@v3
@@ -216,6 +217,7 @@ jobs:
     - name: Test
       env:
         UNS_API_KEY: ${{ secrets.UNS_API_KEY }}
+        UNSTRUCTURED_HF_TOKEN: ${{ secrets.HF_TOKEN }}
       run: |
         source .venv-${{ matrix.extra }}/bin/activate
         # NOTE(newelh) - determine what needs to be installed here
@@ -422,5 +424,6 @@ jobs:
         run: |
           source .venv/bin/activate
           echo "UNS_API_KEY=${{ secrets.UNS_API_KEY }}" > uns_test_env_file
+          echo "UNSTRUCTURED_HF_TOKEN=${{ secrets.HF_TOKEN }}" > uns_test_env_file
           make docker-build
           make docker-test CI=true UNSTRUCTURED_INCLUDE_DEBUG_METADATA=true
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -2,6 +2,7 @@
 
 ### Enhancements
 
+* **bump `unstructured-inference` to `0.7.3`** The updated version of `unstructured-inference` supports a new version of the Chipper model, as well as a cleaner schema for its output classes. Support is included for new inference features such as hierarchy and ordering.
 * **Expose skip_infer_table_types in ingest CLI.** For each connector a new `--skip-infer-table-types` parameter was added to map to the `skip_infer_table_types` partition argument. This gives more granular control to unstructured-ingest users, allowing them to specify the file types for which we should attempt table extraction.
 
 ### Features

diff --git a/requirements/dev.txt b/requirements/dev.txt
@@ -144,7 +144,7 @@ jsonschema-specifications==2023.7.1
     # via jsonschema
 jupyter==1.0.0
     # via -r requirements/dev.in
-jupyter-client==8.3.1
+jupyter-client==8.4.0
     # via
     #   ipykernel
     #   jupyter-console
@@ -153,7 +153,7 @@ jupyter-client==8.3.1
     #   qtconsole
 jupyter-console==6.6.3
     # via jupyter
-jupyter-core==5.3.2
+jupyter-core==5.4.0
     # via
     #   -c requirements/constraints.in
     #   ipykernel
@@ -178,7 +178,7 @@ jupyter-server==2.7.3
     #   notebook-shim
 jupyter-server-terminals==0.4.4
     # via jupyter-server
-jupyterlab==4.0.6
+jupyterlab==4.0.7
     # via notebook
 jupyterlab-pygments==0.2.2
     # via nbconvert
@@ -213,7 +213,7 @@ nest-asyncio==1.5.8
     # via ipykernel
 nodeenv==1.8.0
     # via pre-commit
-notebook==7.0.4
+notebook==7.0.5
     # via jupyter
 notebook-shim==0.2.3
     # via
@@ -320,7 +320,7 @@ rfc3986-validator==0.1.1
     # via
     #   jsonschema
     #   jupyter-events
-rpds-py==0.10.4
+rpds-py==0.10.6
     # via
     #   jsonschema
     #   referencing

diff --git a/requirements/extra-docx.txt b/requirements/extra-docx.txt
@@ -8,5 +8,9 @@ lxml==4.9.3
     # via
     #   -c requirements/base.txt
     #   python-docx
-python-docx==0.8.11
+python-docx==1.0.0
     # via -r requirements/extra-docx.in
+typing-extensions==4.8.0
+    # via
+    #   -c requirements/base.txt
+    #   python-docx
diff --git a/requirements/extra-odt.txt b/requirements/extra-odt.txt
@@ -10,5 +10,9 @@ lxml==4.9.3
     #   python-docx
 pypandoc==1.11
     # via -r requirements/extra-odt.in
-python-docx==0.8.11
+python-docx==1.0.0
     # via -r requirements/extra-odt.in
+typing-extensions==4.8.0
+    # via
+    #   -c requirements/base.txt
+    #   python-docx
diff --git a/requirements/extra-paddleocr.txt b/requirements/extra-paddleocr.txt
@@ -31,7 +31,7 @@ contourpy==1.1.1
     # via matplotlib
 cssselect==1.2.0
     # via premailer
-cssutils==2.7.1
+cssutils==2.8.0
     # via premailer
 cycler==0.12.1
     # via matplotlib

diff --git a/requirements/extra-pdf-image.in b/requirements/extra-pdf-image.in
@@ -5,7 +5,7 @@ pdf2image
 pdfminer.six
 # Do not move to contsraints.in, otherwise unstructured-inference will not be upgraded
 # when unstructured library is.
-unstructured-inference==0.7.2
+unstructured-inference==0.7.3
 # unstructured fork of pytesseract that provides an interface to allow for multiple output formats
 # from one tesseract call
 unstructured.pytesseract>=0.3.12
diff --git a/requirements/extra-pdf-image.txt b/requirements/extra-pdf-image.txt
@@ -149,7 +149,7 @@ pyparsing==3.0.9
     # via
     #   -c requirements/constraints.in
     #   matplotlib
-pypdfium2==4.20.0
+pypdfium2==4.21.0
     # via pdfplumber
 pytesseract==0.3.10
     # via layoutparser
@@ -231,7 +231,7 @@ typing-extensions==4.8.0
     #   torch
 tzdata==2023.3
     # via pandas
-unstructured-inference==0.7.2
+unstructured-inference==0.7.3
     # via -r requirements/extra-pdf-image.in
 unstructured-pytesseract==0.3.12
     # via

diff --git a/requirements/ingest-azure.txt b/requirements/ingest-azure.txt
@@ -23,7 +23,7 @@ azure-datalake-store==0.0.53
     # via adlfs
 azure-identity==1.14.1
     # via adlfs
-azure-storage-blob==12.18.2
+azure-storage-blob==12.18.3
     # via adlfs
 certifi==2023.7.22
     # via

diff --git a/requirements/ingest-gcs.txt b/requirements/ingest-gcs.txt
@@ -64,7 +64,7 @@ google-crc32c==1.5.0
     # via google-resumable-media
 google-resumable-media==2.6.0
     # via google-cloud-storage
-googleapis-common-protos==1.60.0
+googleapis-common-protos==1.61.0
     # via google-api-core
 idna==3.4
     # via

diff --git a/requirements/ingest-google-drive.txt b/requirements/ingest-google-drive.txt
@@ -17,7 +17,7 @@ charset-normalizer==3.3.0
     #   requests
 google-api-core==2.12.0
     # via google-api-python-client
-google-api-python-client==2.102.0
+google-api-python-client==2.103.0
     # via -r requirements/ingest-google-drive.in
 google-auth==2.23.3
     # via
@@ -26,7 +26,7 @@ google-auth==2.23.3
     #   google-auth-httplib2
 google-auth-httplib2==0.1.1
     # via google-api-python-client
-googleapis-common-protos==1.60.0
+googleapis-common-protos==1.61.0
     # via google-api-core
 httplib2==0.22.0
     # via

diff --git a/requirements/ingest-openai.txt b/requirements/ingest-openai.txt
@@ -50,7 +50,7 @@ jsonpatch==1.33
     # via langchain
 jsonpointer==2.4
     # via jsonpatch
-langchain==0.0.311
+langchain==0.0.313
     # via -r requirements/ingest-openai.in
 langsmith==0.0.43
     # via langchain

diff --git a/requirements/test.txt b/requirements/test.txt
@@ -54,7 +54,7 @@ mccabe==0.7.0
     # via flake8
 multidict==6.0.4
     # via yarl
-mypy==1.5.1
+mypy==1.6.0
     # via -r requirements/test.in
 mypy-extensions==1.0.0
     # via

diff --git a/test_unstructured/partition/pdf_image/test_image.py b/test_unstructured/partition/pdf_image/test_image.py
@@ -62,7 +62,7 @@ def __init__(self, number: int, image: Image):
     @property
     def elements(self):
         return [
-            layout.LayoutElement(
+            layout.LayoutElement.from_coords(
                 type="Title",
                 x1=0,
                 y1=0,