revert unstructured-client pin and make pip-compile

CHANGELOG.md

@@ -1,6 +1,8 @@
 ## 0.14.10-dev5
 
 ### Enhancements
+* **Update unstructured-client dependency** Change unstructured-client dependency pin back to
+  greater than min version and updated tests that were failing given the update.
 
 * **`.doc` files are now supported in the `arm64` image.**. `libreoffice24` is added to the `arm64` image, meaning `.doc` files are now supported. We have follow on work planned to investigate adding `.ppt` support for `arm64` as well.
 

requirements/base.txt

@@ -4,13 +4,19 @@
 #
 #    pip-compile ./base.in
 #
+anyio==3.7.1
+    # via
+    #   -c ././deps/constraints.txt
+    #   httpx
 backoff==2.2.1
     # via -r ./base.in
 beautifulsoup4==4.12.3
     # via -r ./base.in
 certifi==2024.6.2
     # via
     #   -c ././deps/constraints.txt
+    #   httpcore
+    #   httpx
     #   requests
     #   unstructured-client
 chardet==5.2.0
@@ -22,15 +28,27 @@ charset-normalizer==3.3.2
 click==8.1.7
     # via nltk
 dataclasses-json==0.6.7
-    # via -r ./base.in
-dataclasses-json-speakeasy==0.5.11
+    # via
+    #   -r ./base.in
+    #   unstructured-client
+deepdiff==7.0.1
     # via unstructured-client
 emoji==2.12.1
     # via -r ./base.in
+exceptiongroup==1.2.1
+    # via anyio
 filetype==1.2.0
     # via -r ./base.in
+h11==0.14.0
+    # via httpcore
+httpcore==1.0.5
+    # via httpx
+httpx==0.27.0
+    # via unstructured-client
 idna==3.7
     # via
+    #   anyio
+    #   httpx
     #   requests
     #   unstructured-client
 joblib==1.4.2
@@ -44,23 +62,28 @@ lxml==5.2.2
 marshmallow==3.21.3
     # via
     #   dataclasses-json
-    #   dataclasses-json-speakeasy
     #   unstructured-client
 mypy-extensions==1.0.0
     # via
     #   typing-inspect
     #   unstructured-client
+nest-asyncio==1.6.0
+    # via unstructured-client
 nltk==3.8.1
     # via -r ./base.in
 numpy==1.26.4
     # via -r ./base.in
+ordered-set==4.1.0
+    # via deepdiff
 packaging==23.2
     # via
     #   -c ././deps/constraints.txt
     #   marshmallow
     #   unstructured-client
 psutil==6.0.0
     # via -r ./base.in
+pypdf==4.2.0
+    # via unstructured-client
 python-dateutil==2.9.0.post0
     # via unstructured-client
 python-iso639==2024.4.27
@@ -74,12 +97,19 @@ regex==2024.5.15
 requests==2.32.3
     # via
     #   -r ./base.in
+    #   requests-toolbelt
     #   unstructured-client
+requests-toolbelt==1.0.0
+    # via unstructured-client
 six==1.16.0
     # via
     #   langdetect
     #   python-dateutil
     #   unstructured-client
+sniffio==1.3.1
+    # via
+    #   anyio
+    #   httpx
 soupsieve==2.5
     # via beautifulsoup4
 tabulate==0.9.0
@@ -92,14 +122,14 @@ typing-extensions==4.12.2
     # via
     #   -r ./base.in
     #   emoji
+    #   pypdf
     #   typing-inspect
     #   unstructured-client
 typing-inspect==0.9.0
     # via
     #   dataclasses-json
-    #   dataclasses-json-speakeasy
     #   unstructured-client
-unstructured-client==0.18.0
+unstructured-client==0.23.8
     # via
     #   -c ././deps/constraints.txt
     #   -r ./base.in

requirements/deps/constraints.txt

@@ -49,7 +49,7 @@ urllib3<1.27
 botocore<1.34.52
 
 # NOTE(jennings): pinned due to later versions not supporting api_key_auth in UnstructuredClient
-unstructured-client<=0.18.0
+unstructured-client>=0.15.1
 
 fsspec==2024.5.0
 

requirements/dev.txt

@@ -7,6 +7,7 @@
 anyio==3.7.1
     # via
     #   -c ././deps/constraints.txt
+    #   -c ./base.txt
     #   httpx
     #   jupyter-server
 appnope==0.1.4
@@ -76,6 +77,7 @@ distlib==0.3.8
     # via virtualenv
 exceptiongroup==1.2.1
     # via
+    #   -c ./base.txt
     #   -c ./test.txt
     #   anyio
 executing==2.0.1
@@ -87,11 +89,17 @@ filelock==3.15.4
 fqdn==1.5.1
     # via jsonschema
 h11==0.14.0
-    # via httpcore
+    # via
+    #   -c ./base.txt
+    #   httpcore
 httpcore==1.0.5
-    # via httpx
+    # via
+    #   -c ./base.txt
+    #   httpx
 httpx==0.27.0
-    # via jupyterlab
+    # via
+    #   -c ./base.txt
+    #   jupyterlab
 identify==2.5.36
     # via pre-commit
 idna==3.7
@@ -111,7 +119,7 @@ importlib-metadata==7.1.0
     #   jupyterlab
     #   jupyterlab-server
     #   nbconvert
-ipykernel==6.29.4
+ipykernel==6.29.5
     # via
     #   jupyter
     #   jupyter-console
@@ -218,7 +226,9 @@ nbformat==5.10.4
     #   nbclient
     #   nbconvert
 nest-asyncio==1.6.0
-    # via ipykernel
+    # via
+    #   -c ./base.txt
+    #   ipykernel
 nodeenv==1.9.1
     # via pre-commit
 notebook==7.2.1
@@ -348,6 +358,7 @@ six==1.16.0
     #   rfc3339-validator
 sniffio==1.3.1
     # via
+    #   -c ./base.txt
     #   anyio
     #   httpx
 soupsieve==2.5

requirements/extra-pdf-image.txt

@@ -48,7 +48,7 @@ fsspec==2024.5.0
     #   torch
 google-api-core[grpc]==2.19.1
     # via google-cloud-vision
-google-auth==2.30.0
+google-auth==2.31.0
     # via
     #   google-api-core
     #   google-cloud-vision
@@ -164,7 +164,7 @@ pillow==10.4.0
     #   pytesseract
     #   torchvision
     #   unstructured-pytesseract
-pillow-heif==0.16.0
+pillow-heif==0.17.0
     # via -r ./extra-pdf-image.in
 portalocker==2.10.0
     # via iopath
@@ -199,7 +199,9 @@ pyparsing==3.0.9
     #   -c ././deps/constraints.txt
     #   matplotlib
 pypdf==4.2.0
-    # via -r ./extra-pdf-image.in
+    # via
+    #   -c ./base.txt
+    #   -r ./extra-pdf-image.in
 pypdfium2==4.30.0
     # via pdfplumber
 pytesseract==0.3.10

requirements/ingest/airtable.txt

@@ -23,9 +23,9 @@ inflection==0.5.1
     # via pyairtable
 pyairtable==2.3.3
     # via -r ./ingest/airtable.in
-pydantic==2.7.4
+pydantic==2.8.0
     # via pyairtable
-pydantic-core==2.18.4
+pydantic-core==2.20.0
     # via pydantic
 requests==2.32.3
     # via

requirements/ingest/astra.txt

@@ -6,6 +6,7 @@
 #
 anyio==3.7.1
     # via
+    #   -c ./ingest/../base.txt
     #   -c ./ingest/../deps/constraints.txt
     #   httpx
 astrapy==1.3.1
@@ -34,19 +35,27 @@ click==8.1.7
 deprecation==2.1.0
     # via astrapy
 exceptiongroup==1.2.1
-    # via anyio
+    # via
+    #   -c ./ingest/../base.txt
+    #   anyio
 geomet==0.2.1.post1
     # via cassandra-driver
 h11==0.14.0
-    # via httpcore
+    # via
+    #   -c ./ingest/../base.txt
+    #   httpcore
 h2==4.1.0
     # via httpx
 hpack==4.0.0
     # via h2
 httpcore==1.0.5
-    # via httpx
+    # via
+    #   -c ./ingest/../base.txt
+    #   httpx
 httpx[http2]==0.27.0
-    # via astrapy
+    # via
+    #   -c ./ingest/../base.txt
+    #   astrapy
 hyperframe==6.0.1
     # via h2
 idna==3.7
@@ -80,6 +89,7 @@ six==1.16.0
     #   python-dateutil
 sniffio==1.3.1
     # via
+    #   -c ./ingest/../base.txt
     #   anyio
     #   httpx
 toml==0.10.2

requirements/ingest/box.txt

@@ -46,7 +46,9 @@ requests==2.32.3
     #   boxsdk
     #   requests-toolbelt
 requests-toolbelt==1.0.0
-    # via boxsdk
+    # via
+    #   -c ./ingest/../base.txt
+    #   boxsdk
 six==1.16.0
     # via
     #   -c ./ingest/../base.txt

requirements/ingest/chroma.txt

@@ -8,6 +8,7 @@ annotated-types==0.7.0
     # via pydantic
 anyio==3.7.1
     # via
+    #   -c ./ingest/../base.txt
     #   -c ./ingest/../deps/constraints.txt
     #   httpx
     #   starlette
@@ -52,7 +53,9 @@ deprecated==1.2.14
     #   opentelemetry-api
     #   opentelemetry-exporter-otlp-proto-grpc
 exceptiongroup==1.2.1
-    # via anyio
+    # via
+    #   -c ./ingest/../base.txt
+    #   anyio
 fastapi==0.110.3
     # via chromadb
 filelock==3.15.4
@@ -63,7 +66,7 @@ fsspec==2024.5.0
     # via
     #   -c ./ingest/../deps/constraints.txt
     #   huggingface-hub
-google-auth==2.30.0
+google-auth==2.31.0
     # via kubernetes
 googleapis-common-protos==1.63.2
     # via opentelemetry-exporter-otlp-proto-grpc
@@ -73,14 +76,19 @@ grpcio==1.64.1
     #   opentelemetry-exporter-otlp-proto-grpc
 h11==0.14.0
     # via
+    #   -c ./ingest/../base.txt
     #   httpcore
     #   uvicorn
 httpcore==1.0.5
-    # via httpx
+    # via
+    #   -c ./ingest/../base.txt
+    #   httpx
 httptools==0.6.1
     # via uvicorn
 httpx==0.27.0
-    # via chromadb
+    # via
+    #   -c ./ingest/../base.txt
+    #   chromadb
 huggingface-hub==0.23.4
     # via tokenizers
 humanfriendly==10.0
@@ -182,11 +190,11 @@ pyasn1==0.6.0
     #   rsa
 pyasn1-modules==0.4.0
     # via google-auth
-pydantic==2.7.4
+pydantic==2.8.0
     # via
     #   chromadb
     #   fastapi
-pydantic-core==2.18.4
+pydantic-core==2.20.0
     # via pydantic
 pypika==0.48.9
     # via chromadb
@@ -225,6 +233,7 @@ six==1.16.0
     #   python-dateutil
 sniffio==1.3.1
     # via
+    #   -c ./ingest/../base.txt
     #   anyio
     #   httpx
 starlette==0.37.2

requirements/ingest/databricks-volumes.txt

@@ -17,7 +17,7 @@ charset-normalizer==3.3.2
     #   requests
 databricks-sdk==0.29.0
     # via -r ./ingest/databricks-volumes.in
-google-auth==2.30.0
+google-auth==2.31.0
     # via databricks-sdk
 idna==3.7
     # via