Request Syntax URI Request Parameters Request Body Response Syntax Response Elements Errors Examples See Also

ConverseStream

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

Note

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

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. To use a guardrail, see Use a guardrail with the Converse API. To use a tool with a model, see Tool use (Function calling).

For example code, see Conversation streaming example.

This operation requires permission for the bedrock:InvokeModelWithResponseStream action.

Important

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 (InvokeModel and InvokeModelWithResponseStream). For more information see Deny access for inference on specific models.

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

Request Syntax


POST /model/modelId/converse-stream HTTP/1.1
Content-type: application/json

{
   "additionalModelRequestFields": JSON value,
   "additionalModelResponseFieldPaths": [ "string" ],
   "guardrailConfig": { 
      "guardrailIdentifier": "string",
      "guardrailVersion": "string",
      "streamProcessingMode": "string",
      "trace": "string"
   },
   "inferenceConfig": { 
      "maxTokens": number,
      "stopSequences": [ "string" ],
      "temperature": number,
      "topP": number
   },
   "messages": [ 
      { 
         "content": [ 
            { ... }
         ],
         "role": "string"
      }
   ],
   "promptVariables": { 
      "string" : { ... }
   },
   "system": [ 
      { ... }
   ],
   "toolConfig": { 
      "toolChoice": { ... },
      "tools": [ 
         { ... }
      ]
   }
}

URI Request Parameters

The request uses the following URI parameters.

modelId

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.

Length Constraints: Minimum length of 1. Maximum length of 2048.

Pattern: ^(arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:(([0-9]{12}:custom-model/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}/[a-z0-9]{12})|(:foundation-model/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.:]?[a-z0-9-]{1,63}))|([0-9]{12}:imported-model/[a-z0-9]{12})|([0-9]{12}:provisioned-model/[a-z0-9]{12})|([0-9]{12}:(inference-profile|application-inference-profile)/[a-zA-Z0-9-:.]+)))|([a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.:]?[a-z0-9-]{1,63}))|(([0-9a-zA-Z][_-]?)+)|([a-zA-Z0-9-:.]+)|(^(arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:[0-9]{12}:prompt/[0-9a-zA-Z]{10}(?::[0-9]{1,5})?))$

Required: Yes

Request Body

The request accepts the following data in JSON format.

additionalModelRequestFields

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

Type: JSON value

Required: No

additionalModelResponseFieldPaths

Additional model parameters field paths to return in the response. Converse and ConverseStream 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 ConverseStream 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.

Type: Array of strings

Array Members: Minimum number of 0 items. Maximum number of 10 items.

Length Constraints: Minimum length of 1. Maximum length of 256.

Required: No

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.

Type: GuardrailStreamConfiguration object

Required: No

inferenceConfig

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

Type: InferenceConfiguration object

Required: No

messages

The messages that you want to send to the model.

Type: Array of Message objects

Required: No

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.

Type: String to PromptVariableValues object map

Required: No

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.

Type: Array of SystemContentBlock objects

Required: No

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.

Type: ToolConfiguration object

Required: No

Response Syntax


HTTP/1.1 200
Content-type: application/json

{
   "contentBlockDelta": { 
      "contentBlockIndex": number,
      "delta": { ... }
   },
   "contentBlockStart": { 
      "contentBlockIndex": number,
      "start": { ... }
   },
   "contentBlockStop": { 
      "contentBlockIndex": number
   },
   "internalServerException": { 
   },
   "messageStart": { 
      "role": "string"
   },
   "messageStop": { 
      "additionalModelResponseFields": JSON value,
      "stopReason": "string"
   },
   "metadata": { 
      "metrics": { 
         "latencyMs": number
      },
      "trace": { 
         "guardrail": { 
            "inputAssessment": { 
               "string" : { 
                  "contentPolicy": { 
                     "filters": [ 
                        { 
                           "action": "string",
                           "confidence": "string",
                           "filterStrength": "string",
                           "type": "string"
                        }
                     ]
                  },
                  "contextualGroundingPolicy": { 
                     "filters": [ 
                        { 
                           "action": "string",
                           "score": number,
                           "threshold": number,
                           "type": "string"
                        }
                     ]
                  },
                  "invocationMetrics": { 
                     "guardrailCoverage": { 
                        "textCharacters": { 
                           "guarded": number,
                           "total": number
                        }
                     },
                     "guardrailProcessingLatency": number,
                     "usage": { 
                        "contentPolicyUnits": number,
                        "contextualGroundingPolicyUnits": number,
                        "sensitiveInformationPolicyFreeUnits": number,
                        "sensitiveInformationPolicyUnits": number,
                        "topicPolicyUnits": number,
                        "wordPolicyUnits": number
                     }
                  },
                  "sensitiveInformationPolicy": { 
                     "piiEntities": [ 
                        { 
                           "action": "string",
                           "match": "string",
                           "type": "string"
                        }
                     ],
                     "regexes": [ 
                        { 
                           "action": "string",
                           "match": "string",
                           "name": "string",
                           "regex": "string"
                        }
                     ]
                  },
                  "topicPolicy": { 
                     "topics": [ 
                        { 
                           "action": "string",
                           "name": "string",
                           "type": "string"
                        }
                     ]
                  },
                  "wordPolicy": { 
                     "customWords": [ 
                        { 
                           "action": "string",
                           "match": "string"
                        }
                     ],
                     "managedWordLists": [ 
                        { 
                           "action": "string",
                           "match": "string",
                           "type": "string"
                        }
                     ]
                  }
               }
            },
            "modelOutput": [ "string" ],
            "outputAssessments": { 
               "string" : [ 
                  { 
                     "contentPolicy": { 
                        "filters": [ 
                           { 
                              "action": "string",
                              "confidence": "string",
                              "filterStrength": "string",
                              "type": "string"
                           }
                        ]
                     },
                     "contextualGroundingPolicy": { 
                        "filters": [ 
                           { 
                              "action": "string",
                              "score": number,
                              "threshold": number,
                              "type": "string"
                           }
                        ]
                     },
                     "invocationMetrics": { 
                        "guardrailCoverage": { 
                           "textCharacters": { 
                              "guarded": number,
                              "total": number
                           }
                        },
                        "guardrailProcessingLatency": number,
                        "usage": { 
                           "contentPolicyUnits": number,
                           "contextualGroundingPolicyUnits": number,
                           "sensitiveInformationPolicyFreeUnits": number,
                           "sensitiveInformationPolicyUnits": number,
                           "topicPolicyUnits": number,
                           "wordPolicyUnits": number
                        }
                     },
                     "sensitiveInformationPolicy": { 
                        "piiEntities": [ 
                           { 
                              "action": "string",
                              "match": "string",
                              "type": "string"
                           }
                        ],
                        "regexes": [ 
                           { 
                              "action": "string",
                              "match": "string",
                              "name": "string",
                              "regex": "string"
                           }
                        ]
                     },
                     "topicPolicy": { 
                        "topics": [ 
                           { 
                              "action": "string",
                              "name": "string",
                              "type": "string"
                           }
                        ]
                     },
                     "wordPolicy": { 
                        "customWords": [ 
                           { 
                              "action": "string",
                              "match": "string"
                           }
                        ],
                        "managedWordLists": [ 
                           { 
                              "action": "string",
                              "match": "string",
                              "type": "string"
                           }
                        ]
                     }
                  }
               ]
            }
         }
      },
      "usage": { 
         "inputTokens": number,
         "outputTokens": number,
         "totalTokens": number
      }
   },
   "modelStreamErrorException": { 
   },
   "serviceUnavailableException": { 
   },
   "throttlingException": { 
   },
   "validationException": { 
   }
}

Response Elements

If the action is successful, the service sends back an HTTP 200 response.

The following data is returned in JSON format by the service.

contentBlockDelta

The messages output content block delta.

Type: ContentBlockDeltaEvent object

contentBlockStart

Start information for a content block.

Type: ContentBlockStartEvent object

contentBlockStop

Stop information for a content block.

Type: ContentBlockStopEvent object

internalServerException

An internal server error occurred. Retry your request.

Type: Exception

HTTP Status Code: 500

messageStart

Message start information.

Type: MessageStartEvent object

messageStop

Message stop information.

Type: MessageStopEvent object

metadata

Metadata for the converse output stream.

Type: ConverseStreamMetadataEvent object

modelStreamErrorException

A streaming error occurred. Retry your request.

Type: Exception

HTTP Status Code: 424

serviceUnavailableException

The service isn't currently available. For troubleshooting this error, see ServiceUnavailable in the Amazon Bedrock User Guide

Type: Exception

HTTP Status Code: 503

throttlingException

Your request was denied due to exceeding the account quotas for Amazon Bedrock. For troubleshooting this error, see ThrottlingException in the Amazon Bedrock User Guide

Type: Exception

HTTP Status Code: 429

validationException

The input fails to satisfy the constraints specified by Amazon Bedrock. For troubleshooting this error, see ValidationError in the Amazon Bedrock User Guide

Type: Exception

HTTP Status Code: 400

Errors

For information about the errors that are common to all actions, see Common Errors.

AccessDeniedException

The request is denied because you do not have sufficient permissions to perform the requested action. For troubleshooting this error, see AccessDeniedException in the Amazon Bedrock User Guide

HTTP Status Code: 403

InternalServerException

An internal server error occurred. For troubleshooting this error, see InternalFailure in the Amazon Bedrock User Guide

HTTP Status Code: 500

ModelErrorException

The request failed due to an error while processing the model.

HTTP Status Code: 424

ModelNotReadyException

The model specified in the request is not ready to serve inference requests. The AWS SDK will automatically retry the operation up to 5 times. For information about configuring automatic retries, see Retry behavior in the AWS SDKs and Tools reference guide.

HTTP Status Code: 429

ModelTimeoutException

The request took too long to process. Processing time exceeded the model timeout length.

HTTP Status Code: 408

ResourceNotFoundException

The specified resource ARN was not found. For troubleshooting this error, see ResourceNotFound in the Amazon Bedrock User Guide

HTTP Status Code: 404

ServiceUnavailableException

The service isn't currently available. For troubleshooting this error, see ServiceUnavailable in the Amazon Bedrock User Guide

HTTP Status Code: 503

ThrottlingException

Your request was denied due to exceeding the account quotas for Amazon Bedrock. For troubleshooting this error, see ThrottlingException in the Amazon Bedrock User Guide

HTTP Status Code: 429

ValidationException

The input fails to satisfy the constraints specified by Amazon Bedrock. For troubleshooting this error, see ValidationError in the Amazon Bedrock User Guide

HTTP Status Code: 400

Examples

Send a message to a model and stream the response.

Send a message to Anthropic Claude Sonnet with ConverseStream and stream the response.

Sample Request


POST /model/anthropic.claude-3-sonnet-20240229-v1:0/converse-stream HTTP/1.1
{
    "messages": [
        {
            "role": "user",
            "content": [
                {
                    "text": "Write an article about impact of high inflation to GDP of a country"
                }
            ]
        }
    ],
    "system": [{"text" : "You are an economist with access to lots of data"}],
    "inferenceConfig": {
        "maxTokens": 1000,
        "temperature": 0.5
    }
}