• Reference links

  • https://github.com/ollama/ollama/blob/main/docs/api.md#generate-a-chat-completion
  • https://github.com/elbruno/semantickernel-localLLMs/blob/main/src/sk-customllm/CustomChatCompletionService.cs
  • https://learn.microsoft.com/en-us/dotnet/api/microsoft.semantickernel.chatcompletion.ichatcompletionservice.getstreamingchatmessagecontentsasync?view=semantic-kernel-dotnet

• pending

  • textcompletion - streaming
  • chat completion - streaming and non-streamming
  • embeddings