Function generateText

Parameters

• model: CallSettings & Prompt & {
      _internal?: { currentDate?: () => Date; generateId?: IDGenerator };
      experimental_activeTools?: (keyof TOOLS)[];
      experimental_continueSteps?: boolean;
      experimental_generateMessageId?: IDGenerator;
      experimental_output?: Output<OUTPUT, OUTPUT_PARTIAL>;
      experimental_prepareStep?: (
          options: {
              maxSteps: number;
              model: LanguageModelV1;
              stepNumber: number;
              steps: StepResult<TOOLS>[];
          },
      ) => PromiseLike<
          {
              experimental_activeTools?: (keyof TOOLS)[];
              model?: LanguageModelV1;
              toolChoice?: ToolChoice<TOOLS>;
          },
      >;
      experimental_providerMetadata?: ProviderMetadata;
      experimental_repairToolCall?: ToolCallRepairFunction<TOOLS>;
      experimental_telemetry?: TelemetrySettings;
      maxSteps?: number;
      model: LanguageModelV1;
      onStepFinish?: GenerateTextOnStepFinishCallback<TOOLS>;
      providerOptions?: ProviderOptions;
      toolChoice?: ToolChoice<TOOLS>;
      tools?: TOOLS;
  }

  The language model to use.

  • Optional_internal?: { currentDate?: () => Date; generateId?: IDGenerator }

    Internal. For test use only. May change without notice.

  • Optionalexperimental_activeTools?: (keyof TOOLS)[]

    Limits the tools that are available for the model to call without changing the tool call and result types in the result.

  • Optionalexperimental_continueSteps?: boolean

    When enabled, the model will perform additional steps if the finish reason is "length" (experimental).

    By default, it's set to false.

  • Optionalexperimental_generateMessageId?: IDGenerator

    Generate a unique ID for each message.

  • Optionalexperimental_output?: Output<OUTPUT, OUTPUT_PARTIAL>

    Optional specification for parsing structured outputs from the LLM response.

  • Optionalexperimental_prepareStep?: (
        options: {
            maxSteps: number;
            model: LanguageModelV1;
            stepNumber: number;
            steps: StepResult<TOOLS>[];
        },
    ) => PromiseLike<
        {
            experimental_activeTools?: (keyof TOOLS)[];
            model?: LanguageModelV1;
            toolChoice?: ToolChoice<TOOLS>;
        },
    >

    Optional function that you can use to provide different settings for a step.

  • Optionalexperimental_providerMetadata?: ProviderMetadata

    Deprecated

    Use providerOptions instead.

  • Optionalexperimental_repairToolCall?: ToolCallRepairFunction<TOOLS>

    A function that attempts to repair a tool call that failed to parse.

  • Optionalexperimental_telemetry?: TelemetrySettings

    Optional telemetry configuration (experimental).

  • OptionalmaxSteps?: number

    Maximum number of sequential LLM calls (steps), e.g. when you use tool calls. Must be at least 1.

    A maximum number is required to prevent infinite loops in the case of misconfigured tools.

    By default, it's set to 1, which means that only a single LLM call is made.

  • model: LanguageModelV1

    The language model to use.

  • OptionalonStepFinish?: GenerateTextOnStepFinishCallback<TOOLS>

    Callback that is called when each step (LLM call) is finished, including intermediate steps.

  • OptionalproviderOptions?: ProviderOptions

    Additional provider-specific options. They are passed through to the provider from the AI SDK and enable provider-specific functionality that can be fully encapsulated in the provider.

  • OptionaltoolChoice?: ToolChoice<TOOLS>

    The tool choice strategy. Default: 'auto'.

  • Optionaltools?: TOOLS

    The tools that the model can call. The model needs to support calling tools.