Video wird geladen...
Video konnte nicht geladen werden
Multimodality and streaming is hard. I've been building something that allows you connect streaming devices like screen capture, microphone, camera, and text easily to craft generative streaming pipelines. It works well with Gemini 2.0 models. Happy to open source if anyone wants it.
17,837 Aufrufe • vor 1 Jahr •via X (Twitter)
10 Kommentare

Jaana Dogan ヤナ ドガンvor 1 Jahr
It allows building pipelines with a little bit of configuration. It's super easy to quickly see what the models are capable of given a mixture of different modalities and context including custom components that can augment the context.

khaled (another one)vor 1 Jahr
I’d like to use that

Sina Nejativor 1 Jahr
please do!

Samuel Navarrovor 1 Jahr
Really interested in something like this

Fakey McFakersonvor 1 Jahr
👀

Kaushalyavor 1 Jahr
eggcellent! I'd like to try it.

Justin Colleryvor 1 Jahr
Yes please!🙏

S4mpl3rvor 1 Jahr
Very cool! I built a similar thing in python a couple months ago before all the realtime stuff came around. It's already open-source here:

Mike Dvor 1 Jahr
+1 👆

Kesavvor 1 Jahr
Yes, please.



