#Is there a way to specify in the LLM conversation instructions which user is interacting with it?
1 messages · Page 1 of 1 (latest)
set the zone of the device and light. then "turn off the light" will assume you mean the light in the room you are in.
So we already include that metadata to the context of conversation?
I don't have room-based zones yet with something like bermuda, but i would still like it to know what i mean by "my bedroom"
My user is called John Doe (for example)
and the zone of the room is called "John" or "John Bedroom"
shouldn't it be able to infer that?
you dont need to know where YOU are, just that sattelite your speaking to is in the bedroom. so if anyone speaks to that device in the bedroom and asks to "turn off the light" they probably mean the light in the bedroom
I see, I am using the Assist on my phone or in the browser on my desktop, so not sure that would work?
oh right
you could add it to the prompt of the llm that any time you refer to "my light" it means light.XYZ
then if you need the same thing for multiple users you could have seperate llm connections and seperate assist pipelines that each could use
i dont think the username is not provided in context to the llm
Damn, that really sucks ngl
The instructions aren't per-pipeline though
they're in the actual conversation entity from the integration of the Google AI thing
It can be a template, but I don't know what is available in that context that I can reference in the template
I guess I can create multiple conversation agents
and then in some way pick a pipeline dynamically for the user?
But I think that feature doesn't exist
for the most part its designed around voice satellites which wont have a user attached to them