chore: remove pins (#3579)

- Remove constraint pins for `Office365-REST-Python-Client`,
`weaviate-client`, and `platformdirs`. Removing the pin for `Office365`
brought to light some bugs in the Onedrive connector, so some changes
were also made to
`unstructured/ingest/v2/processes/connectors/onedrive.py`.
- Also, as part of updating dependencies `unstructured-client` was
updated to `0.25.8`, which introduced a new default for the `strategy`
param and required updating a test fixture.
- The `hubspot.sh` integration test was failing and is now ignored in CI
with this PR per discussion with @rbiseck3.

May be easiest to review commit-by-commit.

CHANGELOG.md

@@ -1,3 +1,11 @@
+## 0.15.12-dev0
+
+### Enhancements
+
+### Features
+
+### Fixes
+
 ## 0.15.11
 
 ### Enhancements

requirements/base.txt

@@ -133,7 +133,7 @@ typing-inspect==0.9.0
     # via
     #   dataclasses-json
     #   unstructured-client
-unstructured-client==0.25.7
+unstructured-client==0.25.8
     # via -r ./base.in
 urllib3==1.26.20
     # via

requirements/deps/constraints.txt

@@ -6,23 +6,13 @@
 # consistency with local-inference-pin
 protobuf<4.24
 grpcio>=1.65.5
-# NOTE(alan) Pinned to avoid error that occurs with 2.4.3:
-# AttributeError: 'ResourcePath' object has no attribute 'collection'
-Office365-REST-Python-Client<2.4.3
-# 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
-platformdirs==3.10.0
-
 # TODO: Constaint due to boto, with python before 3.10 not requiring openssl 1.1.1, remove when that gets
 # updated or we drop support for 3.9
 urllib3<1.27
-
 # TODO: Constriant due to aiobotocore, remove when that gets updates:
 botocore<1.34.132
-
 # python 3.12 support
 wrapt>=1.14.0
-
 langchain-community>=0.2.5

requirements/dev.txt

@@ -30,9 +30,8 @@ packaging==24.1
     #   build
 pip-tools==7.4.1
     # via -r ./dev.in
-platformdirs==3.10.0
+platformdirs==4.3.2
     # via
-    #   -c ././deps/constraints.txt
     #   -c ./test.txt
     #   virtualenv
 pre-commit==3.8.0

requirements/extra-paddleocr.txt

@@ -58,7 +58,7 @@ imageio==2.35.1
     #   scikit-image
 imgaug==0.4.0
     # via unstructured-paddleocr
-importlib-resources==6.4.4
+importlib-resources==6.4.5
     # via matplotlib
 kiwisolver==1.4.7
     # via matplotlib

requirements/extra-pdf-image.txt

@@ -75,7 +75,7 @@ idna==3.8
     # via
     #   -c ./base.txt
     #   requests
-importlib-resources==6.4.4
+importlib-resources==6.4.5
     # via matplotlib
 iopath==0.1.10
     # via layoutparser

requirements/ingest/astradb.txt

@@ -8,9 +8,9 @@ anyio==4.4.0
     # via
     #   -c ./ingest/../base.txt
     #   httpx
-astrapy==1.4.1
+astrapy==1.4.2
     # via -r ./ingest/astradb.in
-cassandra-driver==3.29.1
+cassandra-driver==3.29.2
     # via cassio
 cassio==0.1.8
     # via astrapy
@@ -96,5 +96,5 @@ urllib3==1.26.20
     #   -c ./ingest/../base.txt
     #   -c ./ingest/../deps/constraints.txt
     #   requests
-uuid6==2024.1.12
+uuid6==2024.7.10
     # via astrapy

requirements/ingest/azure.txt

@@ -67,7 +67,7 @@ msal==1.31.0
     #   msal-extensions
 msal-extensions==1.2.0
     # via azure-identity
-multidict==6.0.5
+multidict==6.1.0
     # via
     #   aiohttp
     #   yarl
@@ -94,10 +94,11 @@ typing-extensions==4.12.2
     #   azure-core
     #   azure-identity
     #   azure-storage-blob
+    #   multidict
 urllib3==1.26.20
     # via
     #   -c ./ingest/../base.txt
     #   -c ./ingest/../deps/constraints.txt
     #   requests
-yarl==1.11.0
+yarl==1.11.1
     # via aiohttp

requirements/ingest/chroma.txt

@@ -102,7 +102,7 @@ importlib-metadata==8.4.0
     #   -r ./ingest/chroma.in
     #   build
     #   opentelemetry-api
-importlib-resources==6.4.4
+importlib-resources==6.4.5
     # via chromadb
 kubernetes==30.1.0
     # via chromadb
@@ -172,7 +172,7 @@ packaging==24.1
     #   build
     #   huggingface-hub
     #   onnxruntime
-posthog==3.6.4
+posthog==3.6.5
     # via chromadb
 protobuf==4.23.4
     # via

requirements/ingest/clarifai.txt

@@ -60,7 +60,7 @@ requests==2.32.3
     # via
     #   -c ./ingest/../base.txt
     #   clarifai-grpc
-rich==13.8.0
+rich==13.8.1
     # via clarifai
 schema==0.7.5
     # via clarifai

requirements/ingest/databricks-volumes.txt

@@ -14,7 +14,7 @@ charset-normalizer==3.3.2
     # via
     #   -c ./ingest/../base.txt
     #   requests
-databricks-sdk==0.32.0
+databricks-sdk==0.32.1
     # via -r ./ingest/databricks-volumes.in
 google-auth==2.34.0
     # via databricks-sdk

requirements/ingest/discord.txt

@@ -24,9 +24,13 @@ idna==3.8
     # via
     #   -c ./ingest/../base.txt
     #   yarl
-multidict==6.0.5
+multidict==6.1.0
     # via
     #   aiohttp
     #   yarl
-yarl==1.11.0
+typing-extensions==4.12.2
+    # via
+    #   -c ./ingest/../base.txt
+    #   multidict
+yarl==1.11.1
     # via aiohttp

requirements/ingest/elasticsearch.txt

@@ -20,7 +20,7 @@ certifi==2024.8.30
     #   elastic-transport
 elastic-transport==8.15.0
     # via elasticsearch
-elasticsearch[async]==8.15.0
+elasticsearch[async]==8.15.1
     # via -r ./ingest/elasticsearch.in
 frozenlist==1.4.1
     # via
@@ -30,14 +30,18 @@ idna==3.8
     # via
     #   -c ./ingest/../base.txt
     #   yarl
-multidict==6.0.5
+multidict==6.1.0
     # via
     #   aiohttp
     #   yarl
+typing-extensions==4.12.2
+    # via
+    #   -c ./ingest/../base.txt
+    #   multidict
 urllib3==1.26.20
     # via
     #   -c ./ingest/../base.txt
     #   -c ./ingest/../deps/constraints.txt
     #   elastic-transport
-yarl==1.11.0
+yarl==1.11.1
     # via aiohttp

requirements/ingest/embed-aws-bedrock.txt

@@ -93,7 +93,7 @@ langchain-core==0.2.38
     #   langchain-text-splitters
 langchain-text-splitters==0.2.4
     # via langchain
-langsmith==0.1.116
+langsmith==0.1.117
     # via
     #   langchain
     #   langchain-community
@@ -102,7 +102,7 @@ marshmallow==3.22.0
     # via
     #   -c ./ingest/../base.txt
     #   dataclasses-json
-multidict==6.0.5
+multidict==6.1.0
     # via
     #   aiohttp
     #   yarl
@@ -169,6 +169,7 @@ typing-extensions==4.12.2
     #   -c ./ingest/../base.txt
     #   anyio
     #   langchain-core
+    #   multidict
     #   pydantic
     #   pydantic-core
     #   sqlalchemy
@@ -183,5 +184,5 @@ urllib3==1.26.20
     #   -c ./ingest/../deps/constraints.txt
     #   botocore
     #   requests
-yarl==1.11.0
+yarl==1.11.1
     # via aiohttp

requirements/ingest/embed-huggingface.txt

@@ -71,7 +71,7 @@ langchain-core==0.2.38
     # via langchain-huggingface
 langchain-huggingface==0.0.3
     # via -r ./ingest/embed-huggingface.in
-langsmith==0.1.116
+langsmith==0.1.117
     # via langchain-core
 markupsafe==2.1.5
     # via jinja2

requirements/ingest/embed-octoai.txt

@@ -47,7 +47,7 @@ idna==3.8
     #   requests
 jiter==0.5.0
     # via openai
-openai==1.44.0
+openai==1.44.1
     # via -r ./ingest/embed-octoai.in
 pydantic==2.9.1
     # via openai

requirements/ingest/embed-openai.txt

@@ -56,9 +56,9 @@ langchain-core==0.2.38
     # via langchain-openai
 langchain-openai==0.1.23
     # via -r ./ingest/embed-openai.in
-langsmith==0.1.116
+langsmith==0.1.117
     # via langchain-core
-openai==1.44.0
+openai==1.44.1
     # via langchain-openai
 orjson==3.10.7
     # via langsmith

requirements/ingest/embed-vertexai.txt

@@ -147,7 +147,7 @@ langchain-google-vertexai==1.0.10
     # via -r ./ingest/embed-vertexai.in
 langchain-text-splitters==0.2.4
     # via langchain
-langsmith==0.1.116
+langsmith==0.1.117
     # via
     #   langchain
     #   langchain-community
@@ -156,7 +156,7 @@ marshmallow==3.22.0
     # via
     #   -c ./ingest/../base.txt
     #   dataclasses-json
-multidict==6.0.5
+multidict==6.1.0
     # via
     #   aiohttp
     #   yarl
@@ -253,6 +253,7 @@ typing-extensions==4.12.2
     #   -c ./ingest/../base.txt
     #   anyio
     #   langchain-core
+    #   multidict
     #   pydantic
     #   pydantic-core
     #   sqlalchemy
@@ -266,5 +267,5 @@ urllib3==1.26.20
     #   -c ./ingest/../base.txt
     #   -c ./ingest/../deps/constraints.txt
     #   requests
-yarl==1.11.0
+yarl==1.11.1
     # via aiohttp

requirements/ingest/embed-voyageai.txt

@@ -78,11 +78,11 @@ langchain-text-splitters==0.2.4
     # via langchain
 langchain-voyageai==0.1.1
     # via -r ./ingest/embed-voyageai.in
-langsmith==0.1.116
+langsmith==0.1.117
     # via
     #   langchain
     #   langchain-core
-multidict==6.0.5
+multidict==6.1.0
     # via
     #   aiohttp
     #   yarl
@@ -131,6 +131,7 @@ typing-extensions==4.12.2
     #   -c ./ingest/../base.txt
     #   anyio
     #   langchain-core
+    #   multidict
     #   pydantic
     #   pydantic-core
     #   sqlalchemy
@@ -141,5 +142,5 @@ urllib3==1.26.20
     #   requests
 voyageai==0.2.3
     # via langchain-voyageai
-yarl==1.11.0
+yarl==1.11.1
     # via aiohttp

requirements/ingest/gcs.txt

@@ -72,7 +72,7 @@ idna==3.8
     #   -c ./ingest/../base.txt
     #   requests
     #   yarl
-multidict==6.0.5
+multidict==6.1.0
     # via
     #   aiohttp
     #   yarl
@@ -107,10 +107,14 @@ soupsieve==2.6
     # via
     #   -c ./ingest/../base.txt
     #   beautifulsoup4
+typing-extensions==4.12.2
+    # via
+    #   -c ./ingest/../base.txt
+    #   multidict
 urllib3==1.26.20
     # via
     #   -c ./ingest/../base.txt
     #   -c ./ingest/../deps/constraints.txt
     #   requests
-yarl==1.11.0
+yarl==1.11.1
     # via aiohttp

requirements/ingest/onedrive.txt

@@ -32,10 +32,8 @@ msal==1.31.0
     # via
     #   -r ./ingest/onedrive.in
     #   office365-rest-python-client
-office365-rest-python-client==2.4.2
-    # via
-    #   -c ./ingest/../deps/constraints.txt
-    #   -r ./ingest/onedrive.in
+office365-rest-python-client==2.5.12
+    # via -r ./ingest/onedrive.in
 pycparser==2.22
     # via cffi
 pyjwt[crypto]==2.9.0
@@ -51,6 +49,10 @@ soupsieve==2.6
     # via
     #   -c ./ingest/../base.txt
     #   beautifulsoup4
+typing-extensions==4.12.2
+    # via
+    #   -c ./ingest/../base.txt
+    #   office365-rest-python-client
 urllib3==1.26.20
     # via
     #   -c ./ingest/../base.txt

requirements/ingest/outlook.txt

@@ -26,10 +26,8 @@ msal==1.31.0
     # via
     #   -r ./ingest/outlook.in
     #   office365-rest-python-client
-office365-rest-python-client==2.4.2
-    # via
-    #   -c ./ingest/../deps/constraints.txt
-    #   -r ./ingest/outlook.in
+office365-rest-python-client==2.5.12
+    # via -r ./ingest/outlook.in
 pycparser==2.22
     # via cffi
 pyjwt[crypto]==2.9.0
@@ -41,6 +39,10 @@ requests==2.32.3
     #   -c ./ingest/../base.txt
     #   msal
     #   office365-rest-python-client
+typing-extensions==4.12.2
+    # via
+    #   -c ./ingest/../base.txt
+    #   office365-rest-python-client
 urllib3==1.26.20
     # via
     #   -c ./ingest/../base.txt