Dette er CodeArts blog. Vi deler thought-leadership og tekniske tips og tricks - men som regel på engelsk.
AI Assisted Content Creation - in Optimizely CMS & Commerce (AI Series - Part 2)
AI assisted content creation is an exciting new approach driven by algorithms and models like GPT-3, DALL-E, Stable Diffusion and more. At CodeArt we've been experimenting how to use these technologies to enhance the editorial process. In this second part of the blog series on the topic I'll share a video of a prototype integration to Optimizely (Episerver) CMS of content creation using AI for both images and text.
Named Entity Recognition Demo
When working with a content heavy site, it can be very practical to use AI for identifying named entities in the text. Last summer I made a prototype service using Named Entity Recognition in danish, english and swedish to tag content - but not until now did I find time to describe it in a blog post.
Using TwentyThree video service with Episerver
Videos and well executed webinars are key tools in achieving a higher engagement and conversion rate from your visitors and customers. TwentyThree is a powerful video hub and webinar service. I was lucky enough to get an account and access to their API and that escalated quickly into a prototype integration into Episerver.
Linking to a specific text fragment on another page in Episerver
Chrome 80 introduced a new cool feature that you may or may not have noticed in your google search results. You can now link directly to a text fragment on a page, and Chrome (along with a few other browsers) will then scroll to it and highlight it. Perfect for ultra deep linking and search results. I took the standard Alloy site and put it to the test.
Profile Manager v2 - KQL edition
We just launched a new version of the online tool Profile Manager - a tool that makes it easier for developers and content analysts to work with Episervers Profile Store. The new version lets you easily try out different KQL queries and build Filter Definitions with them.
Experimenting with Wikipedia topics for Content
Automatically tagging your content with topics from a known, well described topic base like Wikipedia can have many cool uses. You can organize your content, suggesting keywords and outbound links, not to mention that you can build up interest profiles of your visitors. These interest profiles can the be used to suggest appropriate content and keep your visitors engaged. Inspired by Episerver Content Intelligence and a couple of earlier projects I've done in the past, I decided to perform an experiment to see how far I could get with a DIY approach as opposed to the traditional cloud-based NLP/AI.
Exploring the Episerver Nuget Feed
The best thing about Episerver is the community and all the great contributions coming from it. Many of them make it into packages on the Episerver nuget feed - along side Episervers own packages. I have for a long time worked on building tools to explore and visualize this more - and now I'm finally ready to one-by-one share some of the tools coming out of it.
Powerslice: Identify unused blocks
Powerslice might have a few years on it's back, but it's still a great editorial tool, when you are working with large amounts of content and have access to Episerver Find. Here's an example of a recent slice I made that let's editors easily identify unused blocks.