Hey guys,
is anyone using autogen with a local model to do multi agent stuff? I have used it with openai api but now wondering if their new assistants thing makes it obsolete? If I could run it all locally that would be a new large value add…
I just saw a video about this come up on my “home” page on youtube the other day. This guy does lots of stuff with oobabooga.
Disclaimer- haven’t watched this all the way through, but it really looks to be what you need.
FYI - I’ve seen a couple of Medium articles about doing this.
Well I did get Autogen working with local models through LM Studio. It works but I haven’t found a good use case for it. I was wanting to set up something like chatdev (which I also got working through LM Studio) but it just doesn’t write any code. I guess for now I’m waiting for a model that will do what I want and thinking over what I can actually do with it.