The InvokeLLM integration, as it's currently implemented, returns the complete answer at once,Therefore, the response time feels longer from the users. Please review and design for the invokeLLM responding method for "true streaming (displaying parts of the answer as they are generated)", so that users can see the responding on their question answer as they are generated. This will makes them experience much better.
Please authenticate to join the conversation.
In Review
Feature Request
5 months ago

ηζι
Get notified by email when there are changes.
In Review
Feature Request
5 months ago

ηζι
Get notified by email when there are changes.