Video yükleniyor...
Video Yüklenemedi
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.
17,851 görüntüleme • 1 yıl önce •via X (Twitter)
10 Yorum

Jaana Dogan ヤナ ドガン1 yıl önce
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)1 yıl önce
I’d like to use that

Sina Nejati1 yıl önce
please do!

Samuel Navarro1 yıl önce
Really interested in something like this

Fakey McFakerson1 yıl önce
👀

Kaushalya1 yıl önce
eggcellent! I'd like to try it.

Justin Collery1 yıl önce
Yes please!🙏

S4mpl3r1 yıl önce
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 D1 yıl önce
+1 👆

Kesav1 yıl önce
Yes, please.


