AWSBedrockLLM
AWS Bedrock LLM provider (Converse API). Streams text generation and function/tool calling from any Bedrock-hosted model (Amazon Nova, Anthropic Claude, Meta Llama, Mistral, Google Gemma).Constructor
Bedrock model id or inference profile ARN. Falls back to
BEDROCK_INFERENCE_PROFILE_ARN. Default: 'amazon.nova-lite-v1:0'.AWS region for Bedrock Runtime. Falls back to
AWS_DEFAULT_REGION / AWS_REGION, then 'us-east-1'.Falls back to the
AWS_ACCESS_KEY_ID env var.Falls back to the
AWS_SECRET_ACCESS_KEY env var.Falls back to the
AWS_SESSION_TOKEN env var.Sampling temperature. Default:
0.7.Max tokens generated per response. Default:
1024. (Legacy maxTokens/max_tokens also accepted.)Nucleus sampling probability mass. Default:
null.Top-K tokens considered (sent via additional request fields; model support varies). Default:
null.Sequences that stop generation; a string or list. Default:
null.'auto', 'required', 'none', or a tool name. Default: 'auto'.Add a prompt-cache checkpoint after the system prompt. Default:
null.Add a prompt-cache checkpoint after the tool definitions. Default:
null.Remove
<thinking>...</thinking> spans from the streamed text. Default: null (provider default).Parse function calls a model prints as plain text instead of native Converse tool use. Default:
null (auto).Extra
additionalModelRequestFields merged into the Converse request. Default: null.