Interface OpenAiAssistantNodeParameters

Source

interface OpenAiAssistantNodeParameters {
    assistantId?: string;
    instructions?: string;
    mode?: "new" | "existing";
    model?: string;
    name?: string;
    nativeTools?: ("code_interpreter" | "retrieval")[];
    options?: {
        baseURL?: string;
        maxRetries?: number;
        timeout?: number;
    };
    text?: string;
}

Properties§

Source§

readonly assistantId?: string

The assistant to use. Learn more. Type options: {"loadOptions":{"routing":{"request":{"method":"GET","headers":{"OpenAI-Beta":"assistants=v1"},"url":"={{ $parameter.options?.baseURL?.split("/").slice(-1).pop() || "v1" }}/assistants"},"output":{"postReceive":[{"type":"rootProperty","properties":{"property":"data"}},{"type":"setKeyValue","properties":{"name":"={{$responseItem.name}}","value":"={{$responseItem.id}}","description":"={{$responseItem.model}}"}},{"type":"sort","properties":{"key":"name"}}]}}}}

Source§

readonly instructions?: string

How the Assistant and model should behave or respond Type options: {"rows":5}

Source§

readonly mode?: "new" | "existing"

Default: "existing"

Source§

readonly model?: string

The model which will be used to power the assistant. Learn more. The Retrieval tool requires gpt-3.5-turbo-1106 and gpt-4-1106-preview models. Default: "gpt-3.5-turbo-1106" Type options: {"loadOptions":{"routing":{"request":{"method":"GET","url":"={{ $parameter.options?.baseURL?.split("/").slice(-1).pop() || "v1" }}/models"},"output":{"postReceive":[{"type":"rootProperty","properties":{"property":"data"}},{"type":"filter","properties":{"pass":"={{ $responseItem.id.startsWith('gpt-') && !$responseItem.id.includes('instruct') }}"}},{"type":"setKeyValue","properties":{"name":"={{$responseItem.id}}","value":"={{$responseItem.id}}"}},{"type":"sort","properties":{"key":"name"}}]}}}}

Source§