Skip to content

BedrockModelOptions

Defined in: src/models/bedrock.ts:289

Options for creating a BedrockModel instance.

optional maxTokens?: number;

Defined in: src/models/bedrock.ts:217

Maximum number of tokens to generate in the response.

https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_InferenceConfiguration.html

BedrockModelConfig.maxTokens


optional temperature?: number;

Defined in: src/models/bedrock.ts:224

Controls randomness in generation.

https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_InferenceConfiguration.html

BedrockModelConfig.temperature


optional topP?: number;

Defined in: src/models/bedrock.ts:231

Controls diversity via nucleus sampling.

https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_InferenceConfiguration.html

BedrockModelConfig.topP


optional stopSequences?: string[];

Defined in: src/models/bedrock.ts:236

Array of sequences that will stop generation when encountered.

BedrockModelConfig.stopSequences


optional cacheConfig?: CacheConfig;

Defined in: src/models/bedrock.ts:243

Configuration for prompt caching.

https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html

BedrockModelConfig.cacheConfig


optional additionalRequestFields?: JSONValue;

Defined in: src/models/bedrock.ts:248

Additional fields to include in the Bedrock request.

BedrockModelConfig.additionalRequestFields


optional additionalResponseFieldPaths?: string[];

Defined in: src/models/bedrock.ts:253

Additional response field paths to extract from the Bedrock response.

BedrockModelConfig.additionalResponseFieldPaths


optional additionalArgs?: JSONValue;

Defined in: src/models/bedrock.ts:259

Additional arguments to pass through to the Bedrock Converse API.

https://docs.aws.amazon.com/AWSJavaScriptSDK/v3/latest/client/bedrock-runtime/command/ConverseStreamCommand/

BedrockModelConfig.additionalArgs


optional stream?: boolean;

Defined in: src/models/bedrock.ts:269

Whether or not to stream responses from the model.

This will use the ConverseStream API instead of the Converse API.

BedrockModelConfig.stream


optional includeToolResultStatus?: boolean | "auto";

Defined in: src/models/bedrock.ts:277

Flag to include status field in tool results.

  • true: Always include status field
  • false: Never include status field
  • 'auto': Automatically determine based on model ID (default)

BedrockModelConfig.includeToolResultStatus


optional guardrailConfig?: BedrockGuardrailConfig;

Defined in: src/models/bedrock.ts:283

Guardrail configuration for content filtering and safety controls.

https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails.html

BedrockModelConfig.guardrailConfig


optional region?: string;

Defined in: src/models/bedrock.ts:293

AWS region to use for the Bedrock service.


optional clientConfig?: BedrockRuntimeClientConfig;

Defined in: src/models/bedrock.ts:298

Configuration for the Bedrock Runtime client.


optional apiKey?: string;

Defined in: src/models/bedrock.ts:305

Amazon Bedrock API key for bearer token authentication. When provided, requests use the API key instead of SigV4 signing.

https://docs.aws.amazon.com/bedrock/latest/userguide/api-keys.html


optional modelId?: string;

Defined in: src/models/model.ts:91

The model identifier. This typically specifies which model to use from the provider’s catalog.

BedrockModelConfig.modelId


optional contextWindowLimit?: number;

Defined in: src/models/model.ts:124

Maximum context window size in tokens for the model.

This value represents the total token capacity shared between input and output. When not provided, it is automatically resolved from a built-in lookup table based on the configured model ID. An explicit value always takes precedence.

When modelId is changed via updateConfig(), this value is automatically re-resolved if it was initially auto-populated. Explicitly set values are preserved.

BedrockModelConfig.contextWindowLimit