Merge branch 'main' into datetime-stats

docs/source/postgresql.md

@@ -45,9 +45,7 @@ You can now query the table using standard SQL.
 select * from squad limit 10;
 ```
 
-<Tip>
 Full documentation for the `ai.load_dataset` function can be found [here](https://github.com/timescale/pgai/blob/main/docs/load_dataset_from_huggingface.md).
-</Tip>
 
 ## Import only a subset of the dataset
 

services/worker/src/worker/job_runners/config/parquet_and_info.py

@@ -27,6 +27,7 @@
 from datasets.builder import DatasetBuilder
 from datasets.data_files import EmptyDatasetError as _EmptyDatasetError
 from datasets.download import StreamingDownloadManager
+from datasets.packaged_modules.imagefolder.imagefolder import ImageFolder as ImageFolderBuilder
 from datasets.packaged_modules.parquet.parquet import Parquet as ParquetBuilder
 from datasets.packaged_modules.videofolder.videofolder import VideoFolder as VideoFolderBuilder
 from datasets.splits import SplitDict, SplitGenerator, SplitInfo
@@ -96,6 +97,8 @@
 
 T = TypeVar("T")
 
+ImageFolderBuilder.EXTENSIONS = list(set(ImageFolderBuilder.EXTENSIONS) - {".h5", ".hdf"})  # fix for datasets <= 3.2.0
+
 
 def http_backoff_with_timeout(method: HTTP_METHOD_T, url: str, **kwargs: Any) -> Response:
     kwargs["timeout"] = kwargs.get("timeout", 10)