Training LLM AI on Articulate Content
We are piloting a Large Language Model AI for internal use and are training the LLM on all content on our intranet. It is working well with other file types (PDFs, SharePoint sites, etc.) but is struggling with reading Articulate content - it can only read content from the first page. Has anyone done something similar with an LLM? Is there any backend metadata/video transcripts/text export that you have tried or that you might suggest? We are not using an LMS, we are exporting to HTML and launching index.html from our intranet (it's our simplest option to maintain control over updating our content vs fighting the bureaucracy of making changes in the old-as-dirt LMS). TIA.
