Machine Learning

1 readers

1 users here now

Community Rules:

Be nice. No offensive behavior, insults or attacks: we encourage a diverse community in which members feel safe and have a voice.
Make your post clear and comprehensive: posts that lack insight or effort will be removed. (ex: questions which are easily googled)
Beginner or career related questions go elsewhere. This community is focused in discussion of research and new projects that advance the state-of-the-art.
Limit self-promotion. Comments and posts should be first and foremost about topics of interest to ML observers and practitioners. Limited self-promotion is tolerated, but the sub is not here as merely a source for free advertisement. Such posts will be removed at the discretion of the mods.

founded 2 years ago

MODERATORS

communick@academy.garden

[Discussion] Is it possible to built a Multi-LLM Assistant? (alien.top)

submitted 2 years ago by SykA196286@alien.top to c/machinelearning@academy.garden

1 comments fedilink hide all child comments

For example with the following structure:

System = GPT-4 Turbo + Llama2 +3rd LLM (!)+ Google or Bing API for websearch + Langchain + any vectorDB + Document upload + longterm Memory + …

Idee behind it is to get more accurate, updated (websearch) and specialized system or even let the LLms discuss your prompt before completion! Question is also, how shall the interaction of multiple LLMs in a system be organzied (Algorithm, Python Library …)? And what kind of Interaction can/should this be? Master-slave or Multi-Master system?

you are viewing a single comment's thread
view the rest of the comments

[–] crazymonezyy@alien.top 1 points 2 years ago

Practically the latency on this is going to be so bad the user will go to sleep before your thing responds.