From 58a2abf08989a1dd5b48cec48f9ec8445795254f Mon Sep 17 00:00:00 2001 From: Hemslo Wang Date: Sat, 2 Mar 2024 07:08:20 +1100 Subject: [PATCH] community[patch]: fix RecursiveUrlLoader metadata_extractor return type (#18193) **Description:** Fix `metadata_extractor` type for `RecursiveUrlLoader`, the default `_metadata_extractor` returns `dict` instead of `str`. **Issue:** N/A **Dependencies:** N/A **Twitter handle:** N/A Signed-off-by: Hemslo Wang --- .../document_loaders/recursive_url_loader.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/libs/community/langchain_community/document_loaders/recursive_url_loader.py b/libs/community/langchain_community/document_loaders/recursive_url_loader.py index 4d3a6019143..698af55c606 100644 --- a/libs/community/langchain_community/document_loaders/recursive_url_loader.py +++ b/libs/community/langchain_community/document_loaders/recursive_url_loader.py @@ -86,7 +86,7 @@ class RecursiveUrlLoader(BaseLoader): max_depth: Optional[int] = 2, use_async: Optional[bool] = None, extractor: Optional[Callable[[str], str]] = None, - metadata_extractor: Optional[Callable[[str, str], str]] = None, + metadata_extractor: Optional[Callable[[str, str], dict]] = None, exclude_dirs: Optional[Sequence[str]] = (), timeout: Optional[int] = 10, prevent_outside: bool = True,