Hi All, I'm working on a project where there is a public webpage with multiple PDFs I want the agent to scrap the page -> Pdfs -> find the information inside the pdf. Current I've imported it via Data Cloud, this since the pdfs gets update frequently, this is not the best approach. Regards, Catherine.
I haven't tried this but a quick search tells me that if you navigate to Setup --> search for Other Connectors --> click New --> search Web Content (Crawler) and configure it as given in this documentation, you maybe able to achieve your objective. From here on it should be a familiar setup, configure Data Stream, map DLO, build a Search Index, configure Retriever, create a Prompt Template, configure an Agent Action to invoke the template.
