search

kbeaugrand / SemanticKernel.Assistants

Microsoft Semantic Kernel Assistants This enables the usage of assistants for the Semantic Kernel. It provides different scenarios for the usage of assistants such as: Assistant with Semantic Kernel plugins Multi-Assistant conversation
MIT License
95 stars 8 forks source link

Bring Autogen Agent implementations!! #14

Closed joslat closed 9 months ago

joslat commented 9 months ago

Why not too take some code from LittleLittleCloud and implement some of the Autogen abstractions? ;) PR for the Autogen .NET implementation: https://github.com/microsoft/autogen/pull/924/files

I don't like the handling of multi-model but if we do this first and delegate anything on the models to the kernel there we go... we can start bringing in the ConversableAgent, and all the others, including the super cool implementation of the advanced analysis (self coding skill) implemented with dotnetinteractive and source generators :)

The plan:

  1. We got those abstractions working on this codebase. 2, We bring them to the PR in SK.
  2. We bring them into Autogen (once PR of .NET is approved).
kbeaugrand commented 9 months ago

@joslat what functional differences do you see between the AutoGen ConversableAgent and the current implementation?

joslat commented 9 months ago

let me review that and get back to you...

kbeaugrand commented 9 months ago

Please see #18

I provided a same kind of feature provided by Auto-gen but leveraging on Assistants APIs.

I have 2 agents:

I have only 1 specialized plugin for the code execution (which interop Docker), the others are simply prompted assistants...

kbeaugrand commented 9 months ago

As we saw, since AutoGen from MS doesn't rely in SK, it's hard to map this approach easily? Then I realize 2 assistants that works together to provide same kind of feature.

See https://github.com/kbeaugrand/SemanticKernel.Assistants?tab=readme-ov-file#autogen to get more info about how to use it.