kernel-memory
kernel-memory copied to clipboard
WithAzureOpenAITextGeneration but for summarizaion only
I think we can use one model for summarization (when we build data for vector db) like gpt3.5 and anoter like gpt4 for actual text writeng
That's correct. Currently the service uses the same model for questions and summarization. You can use a different handler for summarization though, with you custom settings. Plugging in custom handlers is the best way to customize pipelines.
note to team: we need to provide concrete examples showing how to use custom handlers and how to use custom models
Yes please 🙏