Private, open source chat UIs (Practical AI #267)

Changelog Master Feed

We recently gathered some Practical AI listeners for a live webinar with Danny from LibreChat to discuss the future of private, open source chat UIs. During the discussion we hear about the motivations behind LibreChat, why enterprise users are hosting their own chat UIs, and how Danny (and the LibreChat community) is creating amazing features (like RAG and plugins).

Leave us a comment

Changelog++ members save 1 minute on this episode because they made the ads disappear. Join today!

Sponsors:

• Fly.io – The home of Changelog.com — Deploy your apps and databases close to your users. In minutes you can run your Ruby, Go, Node, Deno, Python, or Elixir app (and databases!) all over the world. No ops required. Learn more at fly.io/changelog and check out the speedrun in their docs.

Featuring:

• Danny Avila – Twitter
• Chris Benson – Twitter, GitHub, LinkedIn, Website
• Daniel Whitenack – Twitter, GitHub, Website

Show Notes:

• Register for our next webinar (similar to this one) focused on multimodal AI
• LibreChat
• Prediction Guard

Something missing or broken? PRs welcome!

Chapters

1. Welcome to Practical AI (00:00:00)

2. Practical AI webinar (00:00:43)

3. AI pushback (00:01:33)

4. Danny LibreChat (00:02:45)

5. Own your own data (00:05:57)

6. large scale applications (00:08:04)

7. LibreChat showcase (00:09:42)

8. Switching models in threads (00:13:04)

9. RAG performance (00:16:47)

10. Multi-modality (00:17:53)

11. PredictionGuard usecase (00:19:24)

12. LLM evaluation tools (00:25:03)

13. Plugins? (00:26:25)

14. LIbreChat community (00:28:16)

15. Organizations adopting LibreChat? (00:29:52)

16. Factuality checks (00:30:54)

17. Integrating Flowise & crewAI (00:32:37)

18. Future of LibreChat (00:34:23)

19. Thanks for joining us! (00:36:45)

20. Outro (00:37:38)