SubmitChatOptions

The system prompt. Default: "You are a very enthusiastic company representative who loves to help people!".

Context to use for template variable replacements in the system prompt. Default: {}.

The OpenAI model to use. Default: "gpt-4-turbo-preview".

Options for the use of policies.

Options for retrieval.

The output format of the response. Default: "markdown".

If true, output the response in JSON format. Default: false.

Remove PII from chat messages. Default: false.

The model temperature. Default: 0.1.

The model top P. Default: 1.

The model frequency penalty. Default: 0.

The model present penalty. Default: 0.

The max number of tokens to include in the response. Default: 500.

The number of sections to include in the prompt context. Default: 10.

The similarity threshold between the input question and selected sections. Default: 0.5.

Thread ID. Returned with the first, and every subsequent, chat response. Used to continue a thread.

A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for.

Controls which (if any) function is called by the model. none means the model will not call a function and instead generates a message. auto means the model can pick between generating a message or calling a function. Specifying a particular function via {"type: "function", "function": {"name": "my_function"}} forces the model to call that function. none is the default when no functions are present. auto is the default if functions are present.

Whether or not to inject context relevant to the query. Default: false.

If true, the bot may encourage the user to ask a follow-up question, for instance to gather additional information. Default: true.

Whether or not to include message in insights. Default: false.

AbortController signal.

Enabled debug mode. This will log debug and error information to the console. Default: false.

Disable streaming and return the entire response at once.