[Bug fix] Fix typos, static methods and other sanity improvements in the package (#1129)

This commit is contained in:
Sandra Serrano
2024-01-08 19:47:46 +01:00
committed by GitHub
parent 62c0c52e31
commit 2496ed133e
41 changed files with 133 additions and 103 deletions

View File

@@ -201,8 +201,7 @@ def detect_datatype(source: Any) -> DataType:
formatted_source = format_source(str(source), 30)
if url:
from langchain.document_loaders.youtube import \
ALLOWED_NETLOCK as YOUTUBE_ALLOWED_NETLOCS
from langchain.document_loaders.youtube import ALLOWED_NETLOCK as YOUTUBE_ALLOWED_NETLOCS
if url.netloc in YOUTUBE_ALLOWED_NETLOCS:
logging.debug(f"Source of `{formatted_source}` detected as `youtube_video`.")
@@ -345,7 +344,7 @@ def detect_datatype(source: Any) -> DataType:
return DataType.TEXT_FILE
# If the source is a valid file, that's not detectable as a type, an error is raised.
# It does not fallback to text.
# It does not fall back to text.
raise ValueError(
"Source points to a valid file, but based on the filename, no `data_type` can be detected. Please be aware, that not all data_types allow conventional file references, some require the use of the `file URI scheme`. Please refer to the embedchain documentation (https://docs.embedchain.ai/advanced/data_types#remote-data-types)." # noqa: E501
)