cragwolfe
cragwolfe
By default, UnstructuredURLLoader now continues processing remaining `urls` if encountering an error for a particular url. If failure of the entire loader is desired as was previously the case, use...
Currently, there is no way to pass in headers to UnstructuredURLLoader, e.g. for `"User-Agent"`. There should be. Upstream issue: https://github.com/Unstructured-IO/unstructured/issues/396
As reported by Kranos in Discord, there is no a way to robustly iterate through a list of URL's with UnstructuredURLLoader. The workaround for now is to create a UnstructuredURLLoader...
**Is your feature request related to a problem? Please describe.** Currently, element_id's are simply a hash of the element's text. This is not great, since id's may then be duplicated...
Updates references to the Unstructured API URL to the non-deprecated version. Note that this URL is also shown after logging into https://app.unstructured.io/ , as in the screenshot. 
**Is your feature request related to a problem? Please describe.** [chunk_by_title](https://github.com/Unstructured-IO/unstructured/blob/f98d5e6/unstructured/chunking/title.py#L52) is a great way to combine related text elements. however, the caller may not want to combine all element...