chore: bump unstructured-inference 0.7.36 (#3275)

### Summary
- bump unstructured-inference to `0.7.35` which fixed `ValueError` when
converting cells to HTML in the table processing subpipeline
- cut a release for `0.14.8`

---------

Co-authored-by: Matt Robinson <[email protected]>
Co-authored-by: Matt Robinson <[email protected]>

Author: christinestraub

.github/workflows/docker-publish.yml

@@ -47,6 +47,7 @@ jobs:
         password: ${{ secrets.QUAY_IO_ROBOT_TOKEN }}
     - name: Build images
       run: |
+        ARCH=$(cut -d "/" -f2 <<< ${{ matrix.docker-platform }})
         DOCKER_BUILDKIT=1 docker buildx build --platform=${{ matrix.docker-platform }} --load \
           -f Dockerfile \
           --build-arg PIP_VERSION=$PIP_VERSION \

CHANGELOG.md

@@ -1,4 +1,4 @@
-## 0.14.8-dev4
+## 0.14.8
 
 ### Enhancements
 
@@ -8,6 +8,7 @@
 
 ### Fixes
 
+* **Bump unstructured-inference==0.7.36** Fix `ValueError` when converting cells to html.
 * **`partition()` now forwards `strategy` arg to `partition_docx()`, `partition_ppt()`, and `partition_pptx()`.** A `strategy` argument passed to `partition()` (or the default value "auto" assigned by `partition()`) is now forwarded to `partition_docx()`, `partition_ppt()`, and `partition_pptx()` when those filetypes are detected.
 
 * **Fix missing sensitive field markers** for embedders

requirements/base.txt

@@ -103,7 +103,7 @@ unstructured-client==0.18.0
     # via
     #   -c ././deps/constraints.txt
     #   -r ./base.in
-urllib3==1.26.18
+urllib3==1.26.19
     # via
     #   -c ././deps/constraints.txt
     #   requests

requirements/deps/constraints.txt

@@ -62,3 +62,7 @@ wrapt>=1.14.0
 
 # NOTE(robinson): for compatiblity with voyage embeddings
 langsmith==0.1.62
+
+# 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
+importlib-metadata==7.1.0

requirements/dev.txt

@@ -82,7 +82,7 @@ executing==2.0.1
     # via stack-data
 fastjsonschema==2.20.0
     # via nbformat
-filelock==3.15.1
+filelock==3.15.4
     # via virtualenv
 fqdn==1.5.1
     # via jsonschema
@@ -104,6 +104,7 @@ idna==3.7
     #   requests
 importlib-metadata==7.1.0
     # via
+    #   -c ././deps/constraints.txt
     #   build
     #   jupyter-client
     #   jupyter-lsp
@@ -265,7 +266,7 @@ prompt-toolkit==3.0.47
     # via
     #   ipython
     #   jupyter-console
-psutil==5.9.8
+psutil==6.0.0
     # via ipykernel
 ptyprocess==0.7.0
     # via
@@ -400,13 +401,13 @@ typing-extensions==4.12.2
     #   ipython
 uri-template==1.3.0
     # via jsonschema
-urllib3==1.26.18
+urllib3==1.26.19
     # via
     #   -c ././deps/constraints.txt
     #   -c ./base.txt
     #   -c ./test.txt
     #   requests
-virtualenv==20.26.2
+virtualenv==20.26.3
     # via pre-commit
 wcwidth==0.2.13
     # via prompt-toolkit

requirements/extra-markdown.txt

@@ -5,7 +5,9 @@
 #    pip-compile ./extra-markdown.in
 #
 importlib-metadata==7.1.0
-    # via markdown
+    # via
+    #   -c ././deps/constraints.txt
+    #   markdown
 markdown==3.6
     # via -r ./extra-markdown.in
 zipp==3.19.2

requirements/extra-paddleocr.txt

@@ -53,14 +53,16 @@ idna==3.7
     # via
     #   -c ./base.txt
     #   requests
-imageio==2.34.1
+imageio==2.34.2
     # via
     #   imgaug
     #   scikit-image
 imgaug==0.4.0
     # via unstructured-paddleocr
 importlib-metadata==7.1.0
-    # via flask
+    # via
+    #   -c ././deps/constraints.txt
+    #   flask
 importlib-resources==6.4.0
     # via matplotlib
 itsdangerous==2.2.0
@@ -151,7 +153,7 @@ protobuf==4.23.4
     # via
     #   -c ././deps/constraints.txt
     #   visualdl
-psutil==5.9.8
+psutil==6.0.0
     # via visualdl
 pyclipper==1.3.0.post5
     # via unstructured-paddleocr
@@ -181,7 +183,7 @@ requests==2.32.3
     #   -c ./base.txt
     #   premailer
     #   visualdl
-scikit-image==0.22.0
+scikit-image==0.24.0
     # via
     #   imgaug
     #   unstructured-paddleocr
@@ -202,7 +204,7 @@ six==1.16.0
     #   imgaug
     #   python-dateutil
     #   visualdl
-tifffile==2024.5.22
+tifffile==2024.6.18
     # via scikit-image
 tqdm==4.66.4
     # via
@@ -212,7 +214,7 @@ tzdata==2024.1
     # via pandas
 unstructured-paddleocr==2.6.1.3
     # via -r ./extra-paddleocr.in
-urllib3==1.26.18
+urllib3==1.26.19
     # via
     #   -c ././deps/constraints.txt
     #   -c ./base.txt

requirements/extra-pdf-image.in

@@ -12,7 +12,7 @@ google-cloud-vision
 effdet
 # Do not move to constraints.in, otherwise unstructured-inference will not be upgraded
 # when unstructured library is.
-unstructured-inference==0.7.35
+unstructured-inference==0.7.36
 # unstructured fork of pytesseract that provides an interface to allow for multiple output formats
 # from one tesseract call
 unstructured.pytesseract>=0.3.12

requirements/extra-pdf-image.txt

@@ -32,7 +32,7 @@ deprecated==1.2.14
     # via pikepdf
 effdet==0.4.1
     # via -r ./extra-pdf-image.in
-filelock==3.15.1
+filelock==3.15.4
     # via
     #   huggingface-hub
     #   torch
@@ -167,9 +167,9 @@ pillow==10.3.0
     #   unstructured-pytesseract
 pillow-heif==0.16.0
     # via -r ./extra-pdf-image.in
-portalocker==2.8.2
+portalocker==2.10.0
     # via iopath
-proto-plus==1.23.0
+proto-plus==1.24.0
     # via
     #   google-api-core
     #   google-cloud-vision
@@ -253,7 +253,7 @@ sympy==1.12.1
     # via
     #   onnxruntime
     #   torch
-timm==1.0.3
+timm==1.0.7
     # via
     #   effdet
     #   unstructured-inference
@@ -287,13 +287,13 @@ typing-extensions==4.12.2
     #   torch
 tzdata==2024.1
     # via pandas
-unstructured-inference==0.7.35
+unstructured-inference==0.7.36
     # via -r ./extra-pdf-image.in
 unstructured-pytesseract==0.3.12
     # via
     #   -c ././deps/constraints.txt
     #   -r ./extra-pdf-image.in
-urllib3==1.26.18
+urllib3==1.26.19
     # via
     #   -c ././deps/constraints.txt
     #   -c ./base.txt

requirements/huggingface.txt

@@ -17,7 +17,7 @@ click==8.1.7
     # via
     #   -c ./base.txt
     #   sacremoses
-filelock==3.15.1
+filelock==3.15.4
     # via
     #   huggingface-hub
     #   torch
@@ -107,7 +107,7 @@ typing-extensions==4.12.2
     #   -c ./base.txt
     #   huggingface-hub
     #   torch
-urllib3==1.26.18
+urllib3==1.26.19
     # via
     #   -c ././deps/constraints.txt
     #   -c ./base.txt

requirements/ingest/airtable.txt

@@ -37,7 +37,7 @@ typing-extensions==4.12.2
     #   pyairtable
     #   pydantic
     #   pydantic-core
-urllib3==1.26.18
+urllib3==1.26.19
     # via
     #   -c ./ingest/../base.txt
     #   -c ./ingest/../deps/constraints.txt

requirements/ingest/astra.txt

@@ -8,7 +8,7 @@ anyio==3.7.1
     # via
     #   -c ./ingest/../deps/constraints.txt
     #   httpx
-astrapy==1.2.1
+astrapy==1.3.0
     # via -r ./ingest/astra.in
 bson==0.5.10
     # via astrapy
@@ -85,7 +85,7 @@ sniffio==1.3.1
     #   httpx
 toml==0.10.2
     # via astrapy
-urllib3==1.26.18
+urllib3==1.26.19
     # via
     #   -c ./ingest/../base.txt
     #   -c ./ingest/../deps/constraints.txt

requirements/ingest/azure-cognitive-search.txt

@@ -38,7 +38,7 @@ typing-extensions==4.12.2
     # via
     #   -c ./ingest/../base.txt
     #   azure-core
-urllib3==1.26.18
+urllib3==1.26.19
     # via
     #   -c ./ingest/../base.txt
     #   -c ./ingest/../deps/constraints.txt

requirements/ingest/azure.txt

@@ -21,7 +21,7 @@ azure-core==1.30.2
     #   azure-storage-blob
 azure-datalake-store==0.0.53
     # via adlfs
-azure-identity==1.16.1
+azure-identity==1.17.1
     # via adlfs
 azure-storage-blob==12.20.0
     # via adlfs
@@ -60,23 +60,18 @@ idna==3.7
     #   yarl
 isodate==0.6.1
     # via azure-storage-blob
-msal==1.28.1
+msal==1.29.0
     # via
     #   azure-datalake-store
     #   azure-identity
     #   msal-extensions
-msal-extensions==1.1.0
+msal-extensions==1.2.0
     # via azure-identity
 multidict==6.0.5
     # via
     #   aiohttp
     #   yarl
-packaging==23.2
-    # via
-    #   -c ./ingest/../base.txt
-    #   -c ./ingest/../deps/constraints.txt
-    #   msal-extensions
-portalocker==2.8.2
+portalocker==2.10.0
     # via msal-extensions
 pycparser==2.22
     # via cffi
@@ -97,8 +92,9 @@ typing-extensions==4.12.2
     # via
     #   -c ./ingest/../base.txt
     #   azure-core
+    #   azure-identity
     #   azure-storage-blob
-urllib3==1.26.18
+urllib3==1.26.19
     # via
     #   -c ./ingest/../base.txt
     #   -c ./ingest/../deps/constraints.txt

requirements/ingest/box.txt

@@ -51,7 +51,7 @@ six==1.16.0
     # via
     #   -c ./ingest/../base.txt
     #   python-dateutil
-urllib3==1.26.18
+urllib3==1.26.19
     # via
     #   -c ./ingest/../base.txt
     #   -c ./ingest/../deps/constraints.txt

requirements/ingest/chroma.txt

@@ -9,6 +9,7 @@ annotated-types==0.7.0
 anyio==3.7.1
     # via
     #   -c ./ingest/../deps/constraints.txt
+    #   httpx
     #   starlette
     #   watchfiles
 asgiref==3.8.1
@@ -27,6 +28,8 @@ certifi==2024.6.2
     # via
     #   -c ./ingest/../base.txt
     #   -c ./ingest/../deps/constraints.txt
+    #   httpcore
+    #   httpx
     #   kubernetes
     #   requests
 charset-normalizer==3.3.2
@@ -35,7 +38,7 @@ charset-normalizer==3.3.2
     #   requests
 chroma-hnswlib==0.7.3
     # via chromadb
-chromadb==0.5.0
+chromadb==0.5.3
     # via -r ./ingest/chroma.in
 click==8.1.7
     # via
@@ -52,7 +55,7 @@ exceptiongroup==1.2.1
     # via anyio
 fastapi==0.110.3
     # via chromadb
-filelock==3.15.1
+filelock==3.15.4
     # via huggingface-hub
 flatbuffers==24.3.25
     # via onnxruntime
@@ -69,9 +72,15 @@ grpcio==1.64.1
     #   chromadb
     #   opentelemetry-exporter-otlp-proto-grpc
 h11==0.14.0
-    # via uvicorn
+    # via
+    #   httpcore
+    #   uvicorn
+httpcore==1.0.5
+    # via httpx
 httptools==0.6.1
     # via uvicorn
+httpx==0.27.0
+    # via chromadb
 huggingface-hub==0.23.4
     # via tokenizers
 humanfriendly==10.0
@@ -80,9 +89,11 @@ idna==3.7
     # via
     #   -c ./ingest/../base.txt
     #   anyio
+    #   httpx
     #   requests
 importlib-metadata==7.1.0
     # via
+    #   -c ./ingest/../deps/constraints.txt
     #   -r ./ingest/chroma.in
     #   build
     #   opentelemetry-api
@@ -214,7 +225,9 @@ six==1.16.0
     #   posthog
     #   python-dateutil
 sniffio==1.3.1
-    # via anyio
+    # via
+    #   anyio
+    #   httpx
 starlette==0.37.2
     # via fastapi
 sympy==1.12.1
@@ -247,7 +260,7 @@ typing-extensions==4.12.2
     #   starlette
     #   typer
     #   uvicorn
-urllib3==1.26.18
+urllib3==1.26.19
     # via
     #   -c ./ingest/../base.txt
     #   -c ./ingest/../deps/constraints.txt