Skip to main content

Generate Assistant Message

After creating a user message, you can request the assistant to generate a response based on the user message.

Generation Options​

Generation Options

TaskingAI provides several options for generating assistant messages. These options are:

  1. Stream: When turned on, the assistant will generate messages in real-time token by token. This is useful when you want to see the assistant's response as soon as possible. This is only available to assistants whose model supports Streaming.
  2. Debug: When turned on, the assistant will generate messages with additional debug information. This is useful when you want to see the assistant's internal state, including how they retrieve information from retrieval collections, and how they trigger function calls.
  3. Markdown: Sometimes, the assistant's response may contain markdown syntax. When turned on, the assistant will render the markdown syntax in the response message. This is useful when the response include images or you want to see the assistant's response in a formatted way.