diff --git a/libs/langchain/langchain/document_loaders/async_html.py b/libs/langchain/langchain/document_loaders/async_html.py index 95e55e7dfc..9ba8a94473 100644 --- a/libs/langchain/langchain/document_loaders/async_html.py +++ b/libs/langchain/langchain/document_loaders/async_html.py @@ -26,23 +26,15 @@ default_header_template = { class AsyncHtmlLoader(BaseLoader): """Loads HTML asynchronously.""" - web_paths: List[str] - - requests_per_second: int = 2 - """Max number of concurrent requests to make.""" - - requests_kwargs: Dict[str, Any] = {} - """kwargs for requests""" - - raise_for_status: bool = False - """Raise an exception if http status code denotes an error.""" - def __init__( self, web_path: Union[str, List[str]], header_template: Optional[dict] = None, verify_ssl: Optional[bool] = True, proxies: Optional[dict] = None, + requests_per_second: int = 2, + requests_kwargs: Dict[str, Any] = {}, + raise_for_status: bool = False, ): """Initialize with webpage path.""" @@ -74,6 +66,10 @@ class AsyncHtmlLoader(BaseLoader): if proxies: self.session.proxies.update(proxies) + self.requests_per_second = requests_per_second + self.requests_kwargs = requests_kwargs + self.raise_for_status = raise_for_status + async def _fetch( self, url: str, retries: int = 3, cooldown: int = 2, backoff: float = 1.5 ) -> str: