Bump dependencies (#4265)

<!-- CURSOR_SUMMARY -->
> [!NOTE]
> **Medium Risk**
> Dependency upgrades (especially `transformers` major version and
`weaviate-client` API shift) can introduce runtime or test regressions;
CI runner change may also surface environment-specific failures.
> 
> **Overview**
> Bumps the release to `0.21.7` and updates dependency pins in
`pyproject.toml`, notably moving to `wrapt` 2.x+, `transformers` 5.x,
and `weaviate-client` 4.x (including constraint updates).
> 
> Updates the Weaviate staging integration test to use the
`weaviate.connect_to_embedded()` / `collections.*` API instead of the
legacy `Client`/schema API. CI unit-test jobs are moved from
`ubuntu-latest` to the `opensource-linux-8core` runner, and `.gitignore`
now ignores `.venv*` directories.
> 
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
8e26501. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->

Author: PastelStorm

.github/workflows/ci.yml

@@ -73,7 +73,7 @@ jobs:
     strategy:
       matrix:
         python-version: ["3.11", "3.12", "3.13"]
-    runs-on: ubuntu-latest
+    runs-on: opensource-linux-8core
     needs: [setup, lint]
     steps:
     - uses: actions/checkout@v4
@@ -144,7 +144,7 @@ jobs:
             uv-extras: "--extra pptx"
           - extra: xlsx
             uv-extras: "--extra xlsx"
-    runs-on: ubuntu-latest
+    runs-on: opensource-linux-8core
     needs: [setup, lint, test_unit_no_extras]
     steps:
     - uses: actions/checkout@v4

.gitignore

@@ -105,7 +105,7 @@ celerybeat.pid
 
 # Environments
 .env
-.venv
+.venv*
 env/
 venv/
 ENV/

CHANGELOG.md

@@ -1,3 +1,8 @@
+## 0.21.7
+
+### Enhancements
+- **Bump dependencies**: Update pinned dependency versions in the lockfile.
+
 ## 0.21.6
 
 ### Enhancements

pyproject.toml

@@ -42,7 +42,7 @@ dependencies = [
     "tqdm>=4.67.3, <5.0.0",
     "typing-extensions>=4.15.0, <5.0.0",
     "unstructured-client>=0.25.9, <1.0.0",
-    "wrapt>=1.0.0, <2.0.0",
+    "wrapt>=2.1.1, <3.0.0",
     "filelock>=3.12.0,<4.0.0",
 ]
 
@@ -122,7 +122,7 @@ huggingface = [
     "sentencepiece>=0.2.0, <1.0.0",
     "torch>=2.10.0, <3.0.0; platform_system != 'Windows'",
     "torch>=2.10.0, <3.0.0; platform_system == 'Windows' and python_version < '3.13'",
-    "transformers>=4.55.4, <5.0.0",
+    "transformers>=5.2.0, <6.0.0",
 ]
 local-inference = [
     "unstructured[all-docs]",
@@ -170,7 +170,7 @@ test = [
     "types-requests>=2.32.4.20260107, <3.0.0",
     "types-tabulate>=0.9.0.20241207, <1.0.0",
     "unstructured-pytesseract>=0.3.15, <1.0.0",
-    "weaviate-client>=3.26.7, <4.0.0",
+    "weaviate-client>=4.20.1, <5.0.0",
 ]
 dev = [
     "pre-commit>=4.5.1, <5.0.0",
@@ -198,7 +198,7 @@ constraint-dependencies = [
     "tokenizers>=0.21",
     "unstructured-client>=0.25.9",
     "urllib3>=2.0.0",
-    "weaviate-client>=3.26.7",
+    "weaviate-client>=4.20.1",
 ]
 
 [tool.pyright]

test_unstructured/staging/test_weaviate.py

@@ -7,8 +7,7 @@
 # NOTE(robinson) - allows tests that do not require the weaviate client to
 # run for the docker container
 with contextlib.suppress(ModuleNotFoundError):
-    from weaviate import Client
-    from weaviate.embedded import EmbeddedOptions
+    import weaviate
 
 from unstructured.partition.json import partition_json
 from unstructured.staging.weaviate import (
@@ -58,6 +57,10 @@ def test_stage_for_weaviate():
 @pytest.mark.skipif(is_in_docker, reason="Skipping this test in Docker container")
 def test_weaviate_schema_is_valid():
     unstructured_class = create_unstructured_weaviate_class()
-    schema = {"classes": [unstructured_class]}
-    client = Client(embedded_options=EmbeddedOptions())
-    client.schema.create(schema)
+    class_name = unstructured_class["class"]
+    client = weaviate.connect_to_embedded()
+    try:
+        client.collections.delete(class_name)
+        client.collections.create_from_dict(unstructured_class)
+    finally:
+        client.close()

unstructured/__version__.py

@@ -1 +1 @@
-__version__ = "0.21.6"  # pragma: no cover
+__version__ = "0.21.7"  # pragma: no cover