To adjust the length of the response from your Knowledge Base (KB), you can modify the 'Max Tokens' setting. This setting determines the total number of tokens you want to use when completing your prompt. The maximum number of tokens available per response is 512, and this includes your prompt and settings. Please note that a higher number of max tokens might result in longer response times.
You can find this setting in the KB Settings modal, which you can access from the 'Configuration' icon in the header to the left of 'Preview' and 'Add Data Source' buttons.
Remember, a token is determined by the AI model you use. For example, OpenAI (GPT models) and Anthropic (Claude models) consider a token as around 3-4 characters. Different AI models have different costs, represented by multipliers in Voiceflow. More accurate models use more tokens.
Keep in mind that tokens are used by both the input (what is being sent to the AI model) and output (what is being received from the AI model). The 'token' slider on the AI steps only controls the output message. Depending on your design, there may be a large amount of information that is sent to the AI model as part of your prompt.
Lastly, it's important to preview your Knowledge Base to ensure the accuracy and relevance of your Agent's responses before they reach your users. You can do this by locating the 'Preview' button positioned in the header of your Knowledge Base CMS interface.