Can ADK use multi-modality model-driven agents to interact directly with web pages? #336

Activity

1. wyf7107 commented on Apr 22, 2025

   

   wyf7107

   on Apr 22, 2025

   Collaborator

   More actions

   Our runner currentlt does not support multi-modality as of now, you will need to customize your own runner for the time being, we are looking into support it in the near future
2. seanzhou1023 commented on Apr 28, 2025

   

   seanzhou1023

   on Apr 28, 2025

   Collaborator

   More actions

   Currently we only support TEXT and AUDIO and I think only Live support Audio, use the run_live API.
3. seanzhou1023

   self-assigned this

   on Apr 28, 2025
4. seanzhou1023

   added

   documentation[Component] This issue is related to documentation, it will be transferred to adk-docs[Component] This issue is related to documentation, it will be transferred to adk-docs

   on Apr 28, 2025
5. seanzhou1023

   added the

   Feature

   issue type on Apr 28, 2025
6. seanzhou1023

   assigned

   polong-lin

   on Apr 28, 2025
7. seanzhou1023

   removed their assignment

   on May 28, 2025
8. google

   locked and limited conversation to collaborators on May 28, 2025
9. seanzhou1023

   converted this issue into a discussion #980 on May 28, 2025