BedrockModelOptions
Defined in: src/models/bedrock.ts:298
Options for creating a BedrockModel instance.
Extends
Section titled “Extends”Properties
Section titled “Properties”maxTokens?
Section titled “maxTokens?”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
Inherited from
Section titled “Inherited from”temperature?
Section titled “temperature?”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
Inherited from
Section titled “Inherited from”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
Inherited from
Section titled “Inherited from”stopSequences?
Section titled “stopSequences?”optional stopSequences?: string[];Defined in: src/models/bedrock.ts:236
Array of sequences that will stop generation when encountered.
Inherited from
Section titled “Inherited from”BedrockModelConfig.stopSequences
cacheConfig?
Section titled “cacheConfig?”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
Inherited from
Section titled “Inherited from”BedrockModelConfig.cacheConfig
additionalRequestFields?
Section titled “additionalRequestFields?”optional additionalRequestFields?: JSONValue;Defined in: src/models/bedrock.ts:248
Additional fields to include in the Bedrock request.
Inherited from
Section titled “Inherited from”BedrockModelConfig.additionalRequestFields
additionalResponseFieldPaths?
Section titled “additionalResponseFieldPaths?”optional additionalResponseFieldPaths?: string[];Defined in: src/models/bedrock.ts:253
Additional response field paths to extract from the Bedrock response.
Inherited from
Section titled “Inherited from”BedrockModelConfig.additionalResponseFieldPaths
additionalArgs?
Section titled “additionalArgs?”optional additionalArgs?: JSONValue;Defined in: src/models/bedrock.ts:259
Additional arguments to pass through to the Bedrock Converse API.
Inherited from
Section titled “Inherited from”BedrockModelConfig.additionalArgs
stream?
Section titled “stream?”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.
- https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_Converse.html
- https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_ConverseStream.html
Inherited from
Section titled “Inherited from”includeToolResultStatus?
Section titled “includeToolResultStatus?”optional includeToolResultStatus?: boolean | "auto";Defined in: src/models/bedrock.ts:277
Flag to include status field in tool results.
true: Always include status fieldfalse: Never include status field'auto': Automatically determine based on model ID (default)
Inherited from
Section titled “Inherited from”BedrockModelConfig.includeToolResultStatus
guardrailConfig?
Section titled “guardrailConfig?”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
Inherited from
Section titled “Inherited from”BedrockModelConfig.guardrailConfig
useNativeTokenCount?
Section titled “useNativeTokenCount?”optional useNativeTokenCount?: boolean;Defined in: src/models/bedrock.ts:292
Whether to use the native Bedrock CountTokens API.
When true (default), countTokens() calls the Bedrock CountTokens API for
accurate counts. When false, skips the API call and uses the character-based
heuristic estimator.
Inherited from
Section titled “Inherited from”BedrockModelConfig.useNativeTokenCount
region?
Section titled “region?”optional region?: string;Defined in: src/models/bedrock.ts:302
AWS region to use for the Bedrock service.
clientConfig?
Section titled “clientConfig?”optional clientConfig?: BedrockRuntimeClientConfig;Defined in: src/models/bedrock.ts:307
Configuration for the Bedrock Runtime client.
apiKey?
Section titled “apiKey?”optional apiKey?: string;Defined in: src/models/bedrock.ts:314
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
modelId?
Section titled “modelId?”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.
Inherited from
Section titled “Inherited from”contextWindowLimit?
Section titled “contextWindowLimit?”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.