Allow custom semantic backend?
Hi folks, currently semantic kernel only allows us to use either OpenAI or Azure OpenAI as TextCompletion or Embedding backends. Is it possible for your team to add support for a customized TextCompletion backend? It will be helpful for developers who host their own GPT or AICG service.
use case
// my customized semantic backend
ITextCompletionClient myGossipTextClientInstance
IBackendConfig myGossipTextClientConfig
// suggested API to add config to kernel
kernel.Config.AddTextCompletionBackend(myGossipTextClientConfig, myGossipTextClientInstance)
Hi @LittleLittleCloud , thanks for sending feedback. We are actively working on better multi-model and multi-modal support and will have an update on this shortly.
@timlaverty Thanks, looking forward to having this functionality in semantic kernel.
@LittleLittleCloud as @timlaverty we're actively working on this.
In the meantime, just in case you are blocked, by the design the kernel allows to plug in any function that implements the ISKFunction interface. So, only if this is urgent, this is one available path to integrate any model not yet supported.
@dluc This is now supported as of this PR https://github.com/microsoft/semantic-kernel/pull/161 right?
This is now in the main branch, @LittleLittleCloud thanks for the feedback!