The GPT API supports streaming chat completions before the model has fully finished generating them (like the chatGPT website). This would effectively speed up the summarizing process since users will be able to read the summaries before it has finished being generated.
The GPT API supports streaming chat completions before the model has fully finished generating them (like the chatGPT website). This would effectively speed up the summarizing process since users will be able to read the summaries before it has finished being generated.