aws bedrock-runtime converse-stream

Sends messages to the specified Amazon Bedrock model and returns the response in a stream. AWS CLI reference

13 options Its page in the AWS CLI reference

Options

13 in the AWS CLI reference

--additional-model-request-fieldsAdditional inference parameters that the model supports, beyond the base set of inference parameters that Converse and ConverseStream support in the inferenceConfig field.

--additional-model-response-field-pathsAdditional model parameters field paths to return in the response.

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

--inference-configInference parameters to pass to the model.

--messagesThe messages that you want to send to the model.

--model-idSpecifies the model or throughput with which to run inference, or the prompt resource to use in inference.

--output-configOutput configuration for a model response.

--performance-configModel performance settings for the request.

--prompt-variablesContains a map of variables in a prompt from Prompt management to objects containing the values to fill in for them when running model invocation.

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

--service-tierSpecifies the processing tier configuration used for serving the request.

--systemA prompt that provides instructions or context to the model about the task it should perform, or the persona it should adopt during the conversation.

--tool-configConfiguration information for the tools that the model can use when generating a response.