Iterate: LLM
To provide the user a way to ask questions that can be answered by an LLM
The Iterate: LLM node can be applied in similar way to the Iterate: Iterate node. This means it is most often used as a form of main menu in your Smart App: "What can I do for you today?".
Large language models (LLMs) are great at understanding user questions and provide sensible answers based on the information stored in the common knowledge of the language model. The LLM Flows skill adds this Flow node to your Flow designer.
The difference from the default Iterate node is that it will use the LLM to provide an answer to the user if none of the links are triggered. If the LLM doesn't have an answer, it will still trigger the __unknown__ dialog trigger, which you can configure on this node to handle this event.
How to use?
As explained above, the Iterate: LLM node is used in the same way the default Iterate node is used. The Iterate: LLM node will work as a main menu. It can either respond using one of the labelled links, by triggering dialog triggers, or by formulating a response from the LLM.
In the above example, the Iterate: LLM node will match the intents associated with the two labelled links "Talk to a human" and "Done". If the user doesn't appear to be asking for either of these intents, it will use the LLM to generate an answer.
The LLM can use a specific instruction from you (as the Smart App designer) to guide the generation of the answer. This instruction is given in the form of a Prompt. The prompt can be configured in the AI section of the platform. Besides instructions, the prompt will also contain content that the LLM can use on top of its own dataset to generate answers, like information regarding your address, opening hours, parking instructions, etc. See the Prompts page for more information on this topic.
Node properties
Question
The initial question
Repeat (1)
The text to use when re-prompting the user after a turn
optional
Repeat (2)
The next text to use when re-prompting the user after a turn. The system will keep on iterating this step the third and all other turns
Prompt
The prompt which contains the instructions and content the LLM can use when generating a response
Hold message
The message spoken to the user while the LLM is generating its answer
Only on phone channel
Hold message interval
The time between repeating the hold message in seconds
Only on phone channel
Resources
Last updated
Was this helpful?