langchain.js
    Preparing search index...

    Interface ChatBedrockConverseCallOptions

    interface ChatBedrockConverseCallOptions {
        additionalModelRequestFields?: DocumentType;
        guardrailConfig?: GuardrailConfiguration;
        performanceConfig?: PerformanceConfiguration;
        requestMetadata?: Record<string, string>;
        stop?: string[];
        streamUsage?: boolean;
        tool_choice?: BedrockConverseToolChoice;
        tools?: any[];
    }

    Hierarchy (View Summary)

    Index

    Properties

    additionalModelRequestFields?: DocumentType

    Additional inference parameters that the model supports, beyond the base set of inference parameters that the Converse API supports in the inferenceConfig field. For more information, see the model parameters link below.

    guardrailConfig?: GuardrailConfiguration

    Configuration information for a guardrail that you want to use in the request.

    performanceConfig?: PerformanceConfiguration
    requestMetadata?: Record<string, string>

    Key-value pairs that you can use to filter invocation logs.

    stop?: string[]

    A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response.

    streamUsage?: boolean

    Whether or not to include usage data, like token counts in the streamed response chunks. Passing as a call option will take precedence over the class-level setting.

    true
    
    tool_choice?: BedrockConverseToolChoice

    Tool choice for the model. If passing a string, it must be "any", "auto" or the name of the tool to use. Or, pass a BedrockToolChoice object.

    If "any" is passed, the model must request at least one tool. If "auto" is passed, the model automatically decides if a tool should be called or whether to generate text instead. If a tool name is passed, it will force the model to call that specific tool.

    tools?: any[]