Converse Stream

bedrockruntime_converse_stream

R Documentation

Sends messages to the specified Amazon Bedrock model and returns the response in a stream

Description

Sends messages to the specified Amazon Bedrock model and returns the response in a stream. converse_stream provides a consistent API that works with all Amazon Bedrock models that support messages. This allows you to write code once and use it with different models. Should a model have unique inference parameters, you can also pass those unique parameters to the model.

To find out if a model supports streaming, call GetFoundationModel and check the responseStreamingSupported field in the response.

The CLI doesn't support streaming operations in Amazon Bedrock, including converse_stream.

Amazon Bedrock doesn't store any text, images, or documents that you provide as content. The data is only used to generate the response.

You can submit a prompt by including it in the messages field, specifying the modelId of a foundation model or inference profile to run inference on it, and including any other fields that are relevant to your use case.

You can also submit a prompt from Prompt management by specifying the ARN of the prompt version and including a map of variables to values in the promptVariables field. You can append more messages to the prompt by using the messages field. If you use a prompt from Prompt management, you can't include the following fields in the request: additionalModelRequestFields, inferenceConfig, system, or toolConfig. Instead, these fields must be defined through Prompt management. For more information, see Use a prompt from Prompt management.

For information about the Converse API, see Use the Converse API in the Amazon Bedrock User Guide. To use a guardrail, see Use a guardrail with the Converse API in the Amazon Bedrock User Guide. To use a tool with a model, see Tool use (Function calling) in the Amazon Bedrock User Guide

For example code, see Conversation streaming example in the Amazon Bedrock User Guide.

This operation requires permission for the bedrock:InvokeModelWithResponseStream action.

To deny all inference access to resources that you specify in the modelId field, you need to deny access to the bedrock:InvokeModel and bedrock:InvokeModelWithResponseStream actions. Doing this also denies access to the resource through the base inference actions (invoke_model and invoke_model_with_response_stream). For more information see Deny access for inference on specific models.

For troubleshooting some of the common errors you might encounter when using the converse_stream API, see Troubleshooting Amazon Bedrock API Error Codes in the Amazon Bedrock User Guide

Usage

bedrockruntime_converse_stream(modelId, messages, system,
  inferenceConfig, toolConfig, guardrailConfig,
  additionalModelRequestFields, promptVariables,
  additionalModelResponseFieldPaths, requestMetadata, performanceConfig)

Arguments

modelId

[required] Specifies the model or throughput with which to run inference, or the prompt resource to use in inference. The value depends on the resource that you use:

• If you use a base model, specify the model ID or its ARN. For a list of model IDs for base models, see Amazon Bedrock base model IDs (on-demand throughput) in the Amazon Bedrock User Guide.

• If you use an inference profile, specify the inference profile ID or its ARN. For a list of inference profile IDs, see Supported Regions and models for cross-region inference in the Amazon Bedrock User Guide.

• If you use a provisioned model, specify the ARN of the Provisioned Throughput. For more information, see Run inference using a Provisioned Throughput in the Amazon Bedrock User Guide.

• If you use a custom model, first purchase Provisioned Throughput for it. Then specify the ARN of the resulting provisioned model. For more information, see Use a custom model in Amazon Bedrock in the Amazon Bedrock User Guide.

• To include a prompt that was defined in Prompt management, specify the ARN of the prompt version to use.

The Converse API doesn't support imported models.

messages

The messages that you want to send to the model.

system

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

inferenceConfig

Inference parameters to pass to the model. converse and converse_stream support a base set of inference parameters. If you need to pass additional parameters that the model supports, use the additionalModelRequestFields request field.

toolConfig

Configuration information for the tools that the model can use when generating a response.

For information about models that support streaming tool use, see Supported models and model features.

guardrailConfig

Configuration information for a guardrail that you want to use in the request. If you include guardContent blocks in the content field in the messages field, the guardrail operates only on those messages. If you include no guardContent blocks, the guardrail operates on all messages in the request body and in any included prompt resource.

additionalModelRequestFields

Additional inference parameters that the model supports, beyond the base set of inference parameters that converse and converse_stream support in the inferenceConfig field. For more information, see Model parameters.

promptVariables

Contains a map of variables in a prompt from Prompt management to objects containing the values to fill in for them when running model invocation. This field is ignored if you don't specify a prompt resource in the modelId field.

additionalModelResponseFieldPaths

Additional model parameters field paths to return in the response. converse and converse_stream return the requested fields as a JSON Pointer object in the additionalModelResponseFields field. The following is example JSON for additionalModelResponseFieldPaths.

⁠[ "/stop_sequence" ]⁠

For information about the JSON Pointer syntax, see the Internet Engineering Task Force (IETF) documentation.

converse and converse_stream reject an empty JSON Pointer or incorrectly structured JSON Pointer with a 400 error code. if the JSON Pointer is valid, but the requested field is not in the model response, it is ignored by converse.

requestMetadata

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

performanceConfig

Model performance settings for the request.

Value

A list with the following syntax:

list(
  stream = list(
    messageStart = list(
      role = "user"|"assistant"
    ),
    contentBlockStart = list(
      start = list(
        toolUse = list(
          toolUseId = "string",
          name = "string"
        )
      ),
      contentBlockIndex = 123
    ),
    contentBlockDelta = list(
      delta = list(
        text = "string",
        toolUse = list(
          input = "string"
        )
      ),
      contentBlockIndex = 123
    ),
    contentBlockStop = list(
      contentBlockIndex = 123
    ),
    messageStop = list(
      stopReason = "end_turn"|"tool_use"|"max_tokens"|"stop_sequence"|"guardrail_intervened"|"content_filtered",
      additionalModelResponseFields = list()
    ),
    metadata = list(
      usage = list(
        inputTokens = 123,
        outputTokens = 123,
        totalTokens = 123
      ),
      metrics = list(
        latencyMs = 123
      ),
      trace = list(
        guardrail = list(
          modelOutput = list(
            "string"
          ),
          inputAssessment = list(
            list(
              topicPolicy = list(
                topics = list(
                  list(
                    name = "string",
                    type = "DENY",
                    action = "BLOCKED"
                  )
                )
              ),
              contentPolicy = list(
                filters = list(
                  list(
                    type = "INSULTS"|"HATE"|"SEXUAL"|"VIOLENCE"|"MISCONDUCT"|"PROMPT_ATTACK",
                    confidence = "NONE"|"LOW"|"MEDIUM"|"HIGH",
                    filterStrength = "NONE"|"LOW"|"MEDIUM"|"HIGH",
                    action = "BLOCKED"
                  )
                )
              ),
              wordPolicy = list(
                customWords = list(
                  list(
                    match = "string",
                    action = "BLOCKED"
                  )
                ),
                managedWordLists = list(
                  list(
                    match = "string",
                    type = "PROFANITY",
                    action = "BLOCKED"
                  )
                )
              ),
              sensitiveInformationPolicy = list(
                piiEntities = list(
                  list(
                    match = "string",
                    type = "ADDRESS"|"AGE"|"AWS_ACCESS_KEY"|"AWS_SECRET_KEY"|"CA_HEALTH_NUMBER"|"CA_SOCIAL_INSURANCE_NUMBER"|"CREDIT_DEBIT_CARD_CVV"|"CREDIT_DEBIT_CARD_EXPIRY"|"CREDIT_DEBIT_CARD_NUMBER"|"DRIVER_ID"|"EMAIL"|"INTERNATIONAL_BANK_ACCOUNT_NUMBER"|"IP_ADDRESS"|"LICENSE_PLATE"|"MAC_ADDRESS"|"NAME"|"PASSWORD"|"PHONE"|"PIN"|"SWIFT_CODE"|"UK_NATIONAL_HEALTH_SERVICE_NUMBER"|"UK_NATIONAL_INSURANCE_NUMBER"|"UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER"|"URL"|"USERNAME"|"US_BANK_ACCOUNT_NUMBER"|"US_BANK_ROUTING_NUMBER"|"US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER"|"US_PASSPORT_NUMBER"|"US_SOCIAL_SECURITY_NUMBER"|"VEHICLE_IDENTIFICATION_NUMBER",
                    action = "ANONYMIZED"|"BLOCKED"
                  )
                ),
                regexes = list(
                  list(
                    name = "string",
                    match = "string",
                    regex = "string",
                    action = "ANONYMIZED"|"BLOCKED"
                  )
                )
              ),
              contextualGroundingPolicy = list(
                filters = list(
                  list(
                    type = "GROUNDING"|"RELEVANCE",
                    threshold = 123.0,
                    score = 123.0,
                    action = "BLOCKED"|"NONE"
                  )
                )
              ),
              invocationMetrics = list(
                guardrailProcessingLatency = 123,
                usage = list(
                  topicPolicyUnits = 123,
                  contentPolicyUnits = 123,
                  wordPolicyUnits = 123,
                  sensitiveInformationPolicyUnits = 123,
                  sensitiveInformationPolicyFreeUnits = 123,
                  contextualGroundingPolicyUnits = 123
                ),
                guardrailCoverage = list(
                  textCharacters = list(
                    guarded = 123,
                    total = 123
                  ),
                  images = list(
                    guarded = 123,
                    total = 123
                  )
                )
              )
            )
          ),
          outputAssessments = list(
            list(
              list(
                topicPolicy = list(
                  topics = list(
                    list(
                      name = "string",
                      type = "DENY",
                      action = "BLOCKED"
                    )
                  )
                ),
                contentPolicy = list(
                  filters = list(
                    list(
                      type = "INSULTS"|"HATE"|"SEXUAL"|"VIOLENCE"|"MISCONDUCT"|"PROMPT_ATTACK",
                      confidence = "NONE"|"LOW"|"MEDIUM"|"HIGH",
                      filterStrength = "NONE"|"LOW"|"MEDIUM"|"HIGH",
                      action = "BLOCKED"
                    )
                  )
                ),
                wordPolicy = list(
                  customWords = list(
                    list(
                      match = "string",
                      action = "BLOCKED"
                    )
                  ),
                  managedWordLists = list(
                    list(
                      match = "string",
                      type = "PROFANITY",
                      action = "BLOCKED"
                    )
                  )
                ),
                sensitiveInformationPolicy = list(
                  piiEntities = list(
                    list(
                      match = "string",
                      type = "ADDRESS"|"AGE"|"AWS_ACCESS_KEY"|"AWS_SECRET_KEY"|"CA_HEALTH_NUMBER"|"CA_SOCIAL_INSURANCE_NUMBER"|"CREDIT_DEBIT_CARD_CVV"|"CREDIT_DEBIT_CARD_EXPIRY"|"CREDIT_DEBIT_CARD_NUMBER"|"DRIVER_ID"|"EMAIL"|"INTERNATIONAL_BANK_ACCOUNT_NUMBER"|"IP_ADDRESS"|"LICENSE_PLATE"|"MAC_ADDRESS"|"NAME"|"PASSWORD"|"PHONE"|"PIN"|"SWIFT_CODE"|"UK_NATIONAL_HEALTH_SERVICE_NUMBER"|"UK_NATIONAL_INSURANCE_NUMBER"|"UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER"|"URL"|"USERNAME"|"US_BANK_ACCOUNT_NUMBER"|"US_BANK_ROUTING_NUMBER"|"US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER"|"US_PASSPORT_NUMBER"|"US_SOCIAL_SECURITY_NUMBER"|"VEHICLE_IDENTIFICATION_NUMBER",
                      action = "ANONYMIZED"|"BLOCKED"
                    )
                  ),
                  regexes = list(
                    list(
                      name = "string",
                      match = "string",
                      regex = "string",
                      action = "ANONYMIZED"|"BLOCKED"
                    )
                  )
                ),
                contextualGroundingPolicy = list(
                  filters = list(
                    list(
                      type = "GROUNDING"|"RELEVANCE",
                      threshold = 123.0,
                      score = 123.0,
                      action = "BLOCKED"|"NONE"
                    )
                  )
                ),
                invocationMetrics = list(
                  guardrailProcessingLatency = 123,
                  usage = list(
                    topicPolicyUnits = 123,
                    contentPolicyUnits = 123,
                    wordPolicyUnits = 123,
                    sensitiveInformationPolicyUnits = 123,
                    sensitiveInformationPolicyFreeUnits = 123,
                    contextualGroundingPolicyUnits = 123
                  ),
                  guardrailCoverage = list(
                    textCharacters = list(
                      guarded = 123,
                      total = 123
                    ),
                    images = list(
                      guarded = 123,
                      total = 123
                    )
                  )
                )
              )
            )
          )
        ),
        promptRouter = list(
          invokedModelId = "string"
        )
      ),
      performanceConfig = list(
        latency = "standard"|"optimized"
      )
    ),
    internalServerException = list(
      message = "string"
    ),
    modelStreamErrorException = list(
      message = "string",
      originalStatusCode = 123,
      originalMessage = "string"
    ),
    validationException = list(
      message = "string"
    ),
    throttlingException = list(
      message = "string"
    ),
    serviceUnavailableException = list(
      message = "string"
    )
  )
)

Request syntax

svc$converse_stream(
  modelId = "string",
  messages = list(
    list(
      role = "user"|"assistant",
      content = list(
        list(
          text = "string",
          image = list(
            format = "png"|"jpeg"|"gif"|"webp",
            source = list(
              bytes = raw
            )
          ),
          document = list(
            format = "pdf"|"csv"|"doc"|"docx"|"xls"|"xlsx"|"html"|"txt"|"md",
            name = "string",
            source = list(
              bytes = raw
            )
          ),
          video = list(
            format = "mkv"|"mov"|"mp4"|"webm"|"flv"|"mpeg"|"mpg"|"wmv"|"three_gp",
            source = list(
              bytes = raw,
              s3Location = list(
                uri = "string",
                bucketOwner = "string"
              )
            )
          ),
          toolUse = list(
            toolUseId = "string",
            name = "string",
            input = list()
          ),
          toolResult = list(
            toolUseId = "string",
            content = list(
              list(
                json = list(),
                text = "string",
                image = list(
                  format = "png"|"jpeg"|"gif"|"webp",
                  source = list(
                    bytes = raw
                  )
                ),
                document = list(
                  format = "pdf"|"csv"|"doc"|"docx"|"xls"|"xlsx"|"html"|"txt"|"md",
                  name = "string",
                  source = list(
                    bytes = raw
                  )
                ),
                video = list(
                  format = "mkv"|"mov"|"mp4"|"webm"|"flv"|"mpeg"|"mpg"|"wmv"|"three_gp",
                  source = list(
                    bytes = raw,
                    s3Location = list(
                      uri = "string",
                      bucketOwner = "string"
                    )
                  )
                )
              )
            ),
            status = "success"|"error"
          ),
          guardContent = list(
            text = list(
              text = "string",
              qualifiers = list(
                "grounding_source"|"query"|"guard_content"
              )
            ),
            image = list(
              format = "png"|"jpeg",
              source = list(
                bytes = raw
              )
            )
          )
        )
      )
    )
  ),
  system = list(
    list(
      text = "string",
      guardContent = list(
        text = list(
          text = "string",
          qualifiers = list(
            "grounding_source"|"query"|"guard_content"
          )
        ),
        image = list(
          format = "png"|"jpeg",
          source = list(
            bytes = raw
          )
        )
      )
    )
  ),
  inferenceConfig = list(
    maxTokens = 123,
    temperature = 123.0,
    topP = 123.0,
    stopSequences = list(
      "string"
    )
  ),
  toolConfig = list(
    tools = list(
      list(
        toolSpec = list(
          name = "string",
          description = "string",
          inputSchema = list(
            json = list()
          )
        )
      )
    ),
    toolChoice = list(
      auto = list(),
      any = list(),
      tool = list(
        name = "string"
      )
    )
  ),
  guardrailConfig = list(
    guardrailIdentifier = "string",
    guardrailVersion = "string",
    trace = "enabled"|"disabled",
    streamProcessingMode = "sync"|"async"
  ),
  additionalModelRequestFields = list(),
  promptVariables = list(
    list(
      text = "string"
    )
  ),
  additionalModelResponseFieldPaths = list(
    "string"
  ),
  requestMetadata = list(
    "string"
  ),
  performanceConfig = list(
    latency = "standard"|"optimized"
  )
)