~/talk

Unleashing the Power of AI: Write your own AI Extension

github:Vannsl
slides:none on file

Shows a working TipTap AI extension that runs through a front end talking to a backend proxy calling GPT-3.5 Turbo, implements a custom node with a set AI chat completion command and a slash-command suggestions menu, and uses React node view renderer instead of string HTML. Demo caches responses for speed, translates and rewrites text but initially strips formatting (bold lost) until prompts are adjusted, and warns about token limits (4k / 8k include prompt plus reply).

AI-written summary · about

  1. 0:00AI extensions for TipTap
  2. 1:12Server-side AI integration
  3. 3:20Demo: TipTap AI extension
  4. 7:16AI in rich text editors
  5. 8:20AI extension setup walkthrough
  6. 11:55Custom commands and suggestions
  7. 14:47TipTap TypeScript module
  8. 16:34AI extension node and commands
  9. 17:57React NodeView for UI
  10. 18:20Client fetch to backend API
  11. 19:03OpenAI API integration
  12. 20:07Token limits in AI responses
  13. 21:53Prompt engineering best practices
~/search
type to search 6,249 conferences, 138,987 speakers and 185,172 talks
~/help
cmdctrl k
search every conference, speaker and series
/
focus the filter search
h
home
c
conferences
s
speakers
e
series
t
light / dark — the status bar button does the same
?
this help
esc
close this, then clear every filter — or just the search, while you are typing in it

Ignored while you are typing. Pages without a filter rail have no search to focus.