Skip navigation
Multimodality and streaming is hard. I've been building something that allows you connect streaming…
0:00 / 0:26

Multimodality and streaming is hard. I've been building something that allows you connect streaming…

Jaana Dogan ヤナ ドガン

@rakyll167K followers

Visit on X
186 likesDownloadOriginal post

17,851 views

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.

10 Comments

Comments from the original post on X (Twitter)

  • Jaana Dogan ヤナ ドガン's profile picture

    @rakyll

    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.

    18 likes

  • khaled (another one)'s profile picture

    @notdjkhaled7

    I’d like to use that

    3 likes

  • Sina Nejati's profile picture

    @Xinanexa

    please do!

    2 likes

  • Samuel Navarro's profile picture

    @samuel_n7

    Really interested in something like this

    1 like

  • Fakey McFakerson's profile picture

    @FakeMcFakeyFace

    👀

  • Kaushalya's profile picture

    @kau_mad

    eggcellent! I'd like to try it.

  • Justin Collery's profile picture

    @jcollery

    Yes please!🙏

  • S4mpl3r's profile picture

    @_5upr4

    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 D's profile picture

    @00x1337

    +1 👆

  • Kesav's profile picture

    @Kesav_Sundar

    Yes, please.