Skip to main content

Interface: AiAgentChatOptions

The options for the AI chat method.

Properties​

agentContext​

• Optional agentContext: Record<string, unknown>

Global context passed to the agent and all AI functions of the agent.

chatId​

• Optional chatId: string

A unique chat ID, if the same chat ID is used again and history is not disabled, it will continue the conversation.

connectedAgents​

• Optional connectedAgents: AiConnectedAgentMetadata[]

List of connected AI agents can be called by the current agent. Overrides the stored value.

connectedIntegrations​

• Optional connectedIntegrations: AiConnectedIntegrationMetadata[]

List of connected AI agents can be called by the current agent. Overrides the stored value.

contextMetadataFilter​

• Optional contextMetadataFilter: AiContextMetadataFilter

A set of filters that will limit the context the AI can access.

disableContext​

• Optional disableContext: boolean

Whether to disable the whole context for the request. Default to false.

disableHistory​

• Optional disableHistory: boolean

Disables history for the agent, so each question is answered as if it were the first question in the conversation. Default to false.

fileUrls​

• Optional fileUrls: AiFileUrl[]

File URLs (only images supported at the moment).

functions​

• Optional functions: (string | FunctionNameWithContext)[]

Functions to expose to the AI. Either a function name or a name with an extra function context passed only to this function. The parameter values must be valid serializable JSON values. Overrides the stored value.

groundingWithWebSearch​

• Optional groundingWithWebSearch: boolean

Enables grounding with real-time web search to enhance AI responses with up-to-date information. Currently supported only for gemini-2.0-flash.

includeMetadata​

• Optional includeMetadata: boolean

Include metadata in the context

includeReference​

• Optional includeReference: boolean

Whether to include references from the source context in the response. Default to false.

instructions​

• Optional instructions: string[]

A list of instructions to include with the prompt.

maxTokens​

• Optional maxTokens: number

The maximum number of tokens to use when making the request to the AI model. Default to the max tokens the model can accept.

overrideModel​

• Optional overrideModel: "gpt-4o" | "gpt-4o-mini" | "o1" | "o1-mini" | "o3-mini" | "gemini-1.5-pro" | "gemini-2.0-flash" | "claude-3-5-haiku-latest" | "claude-3-5-sonnet-latest"

The model to use for this chat. If not provided, the profile model will be used.

quotas​

• Optional quotas: AiChatPromptQuotas

Current budget for nested or recursive AI chat calls per single prompt.

reasoningEffort​

• Optional reasoningEffort: "low" | "medium" | "high"

Constrains effort on reasoning for reasoning models. o1 models only.

responseFormat​

• Optional responseFormat: OpenAiResponseFormat

The format of the response from the AI model. Note that not all models support JSON format. Default to 'text'.

smoothTyping​

• Optional smoothTyping: boolean

Whether to response in a "smooth typing" way, beneficial when the chat result is displayed in a UI. Default to true.

temperature​

• Optional temperature: number

The temperature to use when sampling from the model. Default to 0.5.

topP​

• Optional topP: number

The top P value to use when sampling from the model. Default to 1.

voiceOptions​

• Optional voiceOptions: OpenAiCreateSpeechOptions

The options to use for the response in voice.