2024/12/03 - Amazon Bedrock Runtime - 4 updated api methods
Changes Add an API parameter that allows customers to set performance configuration for invoking a model.
{'performanceConfig': {'latency': 'standard | optimized'}}
Sends messages to the specified Amazon Bedrock model. Converse provides a consistent interface that works with all models that support messages. This allows you to write code once and use it with different models. If a model has unique inference parameters, you can also pass those unique parameters to the model.
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 Converse API examples in the Amazon Bedrock User Guide.
This operation requires permission for the bedrock:InvokeModel action.
For troubleshooting some of the common errors you might encounter when using the Converse API, see Troubleshooting Amazon Bedrock API Error Codes in the Amazon Bedrock User Guide
See also: AWS API Documentation
Request Syntax
client.converse(
modelId='string',
messages=[
{
'role': 'user'|'assistant',
'content': [
{
'text': 'string',
'image': {
'format': 'png'|'jpeg'|'gif'|'webp',
'source': {
'bytes': b'bytes'
}
},
'document': {
'format': 'pdf'|'csv'|'doc'|'docx'|'xls'|'xlsx'|'html'|'txt'|'md',
'name': 'string',
'source': {
'bytes': b'bytes'
}
},
'toolUse': {
'toolUseId': 'string',
'name': 'string',
'input': {...}|[...]|123|123.4|'string'|True|None
},
'toolResult': {
'toolUseId': 'string',
'content': [
{
'json': {...}|[...]|123|123.4|'string'|True|None,
'text': 'string',
'image': {
'format': 'png'|'jpeg'|'gif'|'webp',
'source': {
'bytes': b'bytes'
}
},
'document': {
'format': 'pdf'|'csv'|'doc'|'docx'|'xls'|'xlsx'|'html'|'txt'|'md',
'name': 'string',
'source': {
'bytes': b'bytes'
}
}
},
],
'status': 'success'|'error'
},
'guardContent': {
'text': {
'text': 'string',
'qualifiers': [
'grounding_source'|'query'|'guard_content',
]
}
}
},
]
},
],
system=[
{
'text': 'string',
'guardContent': {
'text': {
'text': 'string',
'qualifiers': [
'grounding_source'|'query'|'guard_content',
]
}
}
},
],
inferenceConfig={
'maxTokens': 123,
'temperature': ...,
'topP': ...,
'stopSequences': [
'string',
]
},
toolConfig={
'tools': [
{
'toolSpec': {
'name': 'string',
'description': 'string',
'inputSchema': {
'json': {...}|[...]|123|123.4|'string'|True|None
}
}
},
],
'toolChoice': {
'auto': {}
,
'any': {}
,
'tool': {
'name': 'string'
}
}
},
guardrailConfig={
'guardrailIdentifier': 'string',
'guardrailVersion': 'string',
'trace': 'enabled'|'disabled'
},
additionalModelRequestFields={...}|[...]|123|123.4|'string'|True|None,
promptVariables={
'string': {
'text': 'string'
}
},
additionalModelResponseFieldPaths=[
'string',
],
performanceConfig={
'latency': 'standard'|'optimized'
}
)
string
[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.
list
The messages that you want to send to the model.
(dict) --
A message input, or returned from, a call to Converse or ConverseStream.
role (string) -- [REQUIRED]
The role that the message plays in the message.
content (list) -- [REQUIRED]
The message content. Note the following restrictions:
You can include up to 20 images. Each image's size, height, and width must be no more than 3.75 MB, 8000 px, and 8000 px, respectively.
You can include up to five documents. Each document's size must be no more than 4.5 MB.
If you include a ContentBlock with a document field in the array, you must also include a ContentBlock with a text field.
You can only include images and documents if the role is user.
(dict) --
A block of content for a message that you pass to, or receive from, a model with the Converse or ConverseStream API operations.
text (string) --
Text to include in the message.
image (dict) --
Image to include in the message.
format (string) -- [REQUIRED]
The format of the image.
source (dict) -- [REQUIRED]
The source for the image.
bytes (bytes) --
The raw image bytes for the image. If you use an AWS SDK, you don't need to encode the image bytes in base64.
document (dict) --
A document to include in the message.
format (string) -- [REQUIRED]
The format of a document, or its extension.
name (string) -- [REQUIRED]
A name for the document. The name can only contain the following characters:
Alphanumeric characters
Whitespace characters (no more than one in a row)
Hyphens
Parentheses
Square brackets
source (dict) -- [REQUIRED]
Contains the content of the document.
bytes (bytes) --
The raw bytes for the document. If you use an Amazon Web Services SDK, you don't need to encode the bytes in base64.
toolUse (dict) --
Information about a tool use request from a model.
toolUseId (string) -- [REQUIRED]
The ID for the tool request.
name (string) -- [REQUIRED]
The name of the tool that the model wants to use.
input (:ref:`document<document>`) -- [REQUIRED]
The input to pass to the tool.
toolResult (dict) --
The result for a tool request that a model makes.
toolUseId (string) -- [REQUIRED]
The ID of the tool request that this is the result for.
content (list) -- [REQUIRED]
The content for tool result content block.
(dict) --
The tool result content block.
json (:ref:`document<document>`) --
A tool result that is JSON format data.
text (string) --
A tool result that is text.
image (dict) --
A tool result that is an image.
format (string) -- [REQUIRED]
The format of the image.
source (dict) -- [REQUIRED]
The source for the image.
bytes (bytes) --
The raw image bytes for the image. If you use an AWS SDK, you don't need to encode the image bytes in base64.
document (dict) --
A tool result that is a document.
format (string) -- [REQUIRED]
The format of a document, or its extension.
name (string) -- [REQUIRED]
A name for the document. The name can only contain the following characters:
Alphanumeric characters
Whitespace characters (no more than one in a row)
Hyphens
Parentheses
Square brackets
source (dict) -- [REQUIRED]
Contains the content of the document.
bytes (bytes) --
The raw bytes for the document. If you use an Amazon Web Services SDK, you don't need to encode the bytes in base64.
status (string) --
The status for the tool result content block.
guardContent (dict) --
Contains the content to assess with the guardrail. If you don't specify guardContent in a call to the Converse API, the guardrail (if passed in the Converse API) assesses the entire message.
For more information, see Use a guardrail with the Converse API in the Amazon Bedrock User Guide. </p>
text (dict) --
The text to guard.
text (string) -- [REQUIRED]
The text that you want to guard.
qualifiers (list) --
The qualifier details for the guardrails contextual grounding filter.
(string) --
list
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.
(dict) --
A system content block.
text (string) --
A system prompt for the model.
guardContent (dict) --
A content block to assess with the guardrail. Use with the Converse or ConverseStream API operations.
For more information, see Use a guardrail with the Converse API in the Amazon Bedrock User Guide.
text (dict) --
The text to guard.
text (string) -- [REQUIRED]
The text that you want to guard.
qualifiers (list) --
The qualifier details for the guardrails contextual grounding filter.
(string) --
dict
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.
maxTokens (integer) --
The maximum number of tokens to allow in the generated response. The default value is the maximum allowed value for the model that you are using. For more information, see Inference parameters for foundation models.
temperature (float) --
The likelihood of the model selecting higher-probability options while generating a response. A lower value makes the model more likely to choose higher-probability options, while a higher value makes the model more likely to choose lower-probability options.
The default value is the default value for the model that you are using. For more information, see Inference parameters for foundation models.
topP (float) --
The percentage of most-likely candidates that the model considers for the next token. For example, if you choose a value of 0.8 for topP, the model selects from the top 80% of the probability distribution of tokens that could be next in the sequence.
The default value is the default value for the model that you are using. For more information, see Inference parameters for foundation models.
stopSequences (list) --
A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response.
(string) --
dict
Configuration information for the tools that the model can use when generating a response.
tools (list) -- [REQUIRED]
An array of tools that you want to pass to a model.
(dict) --
Information about a tool that you can use with the Converse API. For more information, see Tool use (function calling) in the Amazon Bedrock User Guide.
toolSpec (dict) --
The specfication for the tool.
name (string) -- [REQUIRED]
The name for the tool.
description (string) --
The description for the tool.
inputSchema (dict) -- [REQUIRED]
The input schema for the tool in JSON format.
json (:ref:`document<document>`) --
The JSON schema for the tool. For more information, see JSON Schema Reference.
toolChoice (dict) --
If supported by model, forces the model to request a tool.
auto (dict) --
(Default). The Model automatically decides if a tool should be called or whether to generate text instead.
any (dict) --
The model must request at least one tool (no text is generated).
tool (dict) --
The Model must request the specified tool. Only supported by Anthropic Claude 3 models.
name (string) -- [REQUIRED]
The name of the tool that the model must request.
dict
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.
guardrailIdentifier (string) -- [REQUIRED]
The identifier for the guardrail.
guardrailVersion (string) -- [REQUIRED]
The version of the guardrail.
trace (string) --
The trace behavior for the guardrail.
:ref:`document<document>`
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.
dict
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.
(string) --
(dict) --
Contains a map of variables in a prompt from Prompt management to an object containing the values to fill in for them when running model invocation. For more information, see How Prompt management works.
text (string) --
The text value that the variable maps to.
list
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.
(string) --
dict
Model performance settings for the request.
latency (string) --
To use a latency-optimized version of the model, set to optimized.
dict
Response Syntax
{
'output': {
'message': {
'role': 'user'|'assistant',
'content': [
{
'text': 'string',
'image': {
'format': 'png'|'jpeg'|'gif'|'webp',
'source': {
'bytes': b'bytes'
}
},
'document': {
'format': 'pdf'|'csv'|'doc'|'docx'|'xls'|'xlsx'|'html'|'txt'|'md',
'name': 'string',
'source': {
'bytes': b'bytes'
}
},
'toolUse': {
'toolUseId': 'string',
'name': 'string',
'input': {...}|[...]|123|123.4|'string'|True|None
},
'toolResult': {
'toolUseId': 'string',
'content': [
{
'json': {...}|[...]|123|123.4|'string'|True|None,
'text': 'string',
'image': {
'format': 'png'|'jpeg'|'gif'|'webp',
'source': {
'bytes': b'bytes'
}
},
'document': {
'format': 'pdf'|'csv'|'doc'|'docx'|'xls'|'xlsx'|'html'|'txt'|'md',
'name': 'string',
'source': {
'bytes': b'bytes'
}
}
},
],
'status': 'success'|'error'
},
'guardContent': {
'text': {
'text': 'string',
'qualifiers': [
'grounding_source'|'query'|'guard_content',
]
}
}
},
]
}
},
'stopReason': 'end_turn'|'tool_use'|'max_tokens'|'stop_sequence'|'guardrail_intervened'|'content_filtered',
'usage': {
'inputTokens': 123,
'outputTokens': 123,
'totalTokens': 123
},
'metrics': {
'latencyMs': 123
},
'additionalModelResponseFields': {...}|[...]|123|123.4|'string'|True|None,
'trace': {
'guardrail': {
'modelOutput': [
'string',
],
'inputAssessment': {
'string': {
'topicPolicy': {
'topics': [
{
'name': 'string',
'type': 'DENY',
'action': 'BLOCKED'
},
]
},
'contentPolicy': {
'filters': [
{
'type': 'INSULTS'|'HATE'|'SEXUAL'|'VIOLENCE'|'MISCONDUCT'|'PROMPT_ATTACK',
'confidence': 'NONE'|'LOW'|'MEDIUM'|'HIGH',
'filterStrength': 'NONE'|'LOW'|'MEDIUM'|'HIGH',
'action': 'BLOCKED'
},
]
},
'wordPolicy': {
'customWords': [
{
'match': 'string',
'action': 'BLOCKED'
},
],
'managedWordLists': [
{
'match': 'string',
'type': 'PROFANITY',
'action': 'BLOCKED'
},
]
},
'sensitiveInformationPolicy': {
'piiEntities': [
{
'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': [
{
'name': 'string',
'match': 'string',
'regex': 'string',
'action': 'ANONYMIZED'|'BLOCKED'
},
]
},
'contextualGroundingPolicy': {
'filters': [
{
'type': 'GROUNDING'|'RELEVANCE',
'threshold': 123.0,
'score': 123.0,
'action': 'BLOCKED'|'NONE'
},
]
},
'invocationMetrics': {
'guardrailProcessingLatency': 123,
'usage': {
'topicPolicyUnits': 123,
'contentPolicyUnits': 123,
'wordPolicyUnits': 123,
'sensitiveInformationPolicyUnits': 123,
'sensitiveInformationPolicyFreeUnits': 123,
'contextualGroundingPolicyUnits': 123
},
'guardrailCoverage': {
'textCharacters': {
'guarded': 123,
'total': 123
}
}
}
}
},
'outputAssessments': {
'string': [
{
'topicPolicy': {
'topics': [
{
'name': 'string',
'type': 'DENY',
'action': 'BLOCKED'
},
]
},
'contentPolicy': {
'filters': [
{
'type': 'INSULTS'|'HATE'|'SEXUAL'|'VIOLENCE'|'MISCONDUCT'|'PROMPT_ATTACK',
'confidence': 'NONE'|'LOW'|'MEDIUM'|'HIGH',
'filterStrength': 'NONE'|'LOW'|'MEDIUM'|'HIGH',
'action': 'BLOCKED'
},
]
},
'wordPolicy': {
'customWords': [
{
'match': 'string',
'action': 'BLOCKED'
},
],
'managedWordLists': [
{
'match': 'string',
'type': 'PROFANITY',
'action': 'BLOCKED'
},
]
},
'sensitiveInformationPolicy': {
'piiEntities': [
{
'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': [
{
'name': 'string',
'match': 'string',
'regex': 'string',
'action': 'ANONYMIZED'|'BLOCKED'
},
]
},
'contextualGroundingPolicy': {
'filters': [
{
'type': 'GROUNDING'|'RELEVANCE',
'threshold': 123.0,
'score': 123.0,
'action': 'BLOCKED'|'NONE'
},
]
},
'invocationMetrics': {
'guardrailProcessingLatency': 123,
'usage': {
'topicPolicyUnits': 123,
'contentPolicyUnits': 123,
'wordPolicyUnits': 123,
'sensitiveInformationPolicyUnits': 123,
'sensitiveInformationPolicyFreeUnits': 123,
'contextualGroundingPolicyUnits': 123
},
'guardrailCoverage': {
'textCharacters': {
'guarded': 123,
'total': 123
}
}
}
},
]
}
}
},
'performanceConfig': {
'latency': 'standard'|'optimized'
}
}
Response Structure
(dict) --
output (dict) --
The result from the call to Converse.
message (dict) --
The message that the model generates.
role (string) --
The role that the message plays in the message.
content (list) --
The message content. Note the following restrictions:
You can include up to 20 images. Each image's size, height, and width must be no more than 3.75 MB, 8000 px, and 8000 px, respectively.
You can include up to five documents. Each document's size must be no more than 4.5 MB.
If you include a ContentBlock with a document field in the array, you must also include a ContentBlock with a text field.
You can only include images and documents if the role is user.
(dict) --
A block of content for a message that you pass to, or receive from, a model with the Converse or ConverseStream API operations.
text (string) --
Text to include in the message.
image (dict) --
Image to include in the message.
format (string) --
The format of the image.
source (dict) --
The source for the image.
bytes (bytes) --
The raw image bytes for the image. If you use an AWS SDK, you don't need to encode the image bytes in base64.
document (dict) --
A document to include in the message.
format (string) --
The format of a document, or its extension.
name (string) --
A name for the document. The name can only contain the following characters:
Alphanumeric characters
Whitespace characters (no more than one in a row)
Hyphens
Parentheses
Square brackets
source (dict) --
Contains the content of the document.
bytes (bytes) --
The raw bytes for the document. If you use an Amazon Web Services SDK, you don't need to encode the bytes in base64.
toolUse (dict) --
Information about a tool use request from a model.
toolUseId (string) --
The ID for the tool request.
name (string) --
The name of the tool that the model wants to use.
input (:ref:`document<document>`) --
The input to pass to the tool.
toolResult (dict) --
The result for a tool request that a model makes.
toolUseId (string) --
The ID of the tool request that this is the result for.
content (list) --
The content for tool result content block.
(dict) --
The tool result content block.
json (:ref:`document<document>`) --
A tool result that is JSON format data.
text (string) --
A tool result that is text.
image (dict) --
A tool result that is an image.
format (string) --
The format of the image.
source (dict) --
The source for the image.
bytes (bytes) --
The raw image bytes for the image. If you use an AWS SDK, you don't need to encode the image bytes in base64.
document (dict) --
A tool result that is a document.
format (string) --
The format of a document, or its extension.
name (string) --
A name for the document. The name can only contain the following characters:
Alphanumeric characters
Whitespace characters (no more than one in a row)
Hyphens
Parentheses
Square brackets
source (dict) --
Contains the content of the document.
bytes (bytes) --
The raw bytes for the document. If you use an Amazon Web Services SDK, you don't need to encode the bytes in base64.
status (string) --
The status for the tool result content block.
guardContent (dict) --
Contains the content to assess with the guardrail. If you don't specify guardContent in a call to the Converse API, the guardrail (if passed in the Converse API) assesses the entire message.
For more information, see Use a guardrail with the Converse API in the Amazon Bedrock User Guide. </p>
text (dict) --
The text to guard.
text (string) --
The text that you want to guard.
qualifiers (list) --
The qualifier details for the guardrails contextual grounding filter.
(string) --
stopReason (string) --
The reason why the model stopped generating output.
usage (dict) --
The total number of tokens used in the call to Converse. The total includes the tokens input to the model and the tokens generated by the model.
inputTokens (integer) --
The number of tokens sent in the request to the model.
outputTokens (integer) --
The number of tokens that the model generated for the request.
totalTokens (integer) --
The total of input tokens and tokens generated by the model.
metrics (dict) --
Metrics for the call to Converse.
latencyMs (integer) --
The latency of the call to Converse, in milliseconds.
additionalModelResponseFields (:ref:`document<document>`) --
Additional fields in the response that are unique to the model.
trace (dict) --
A trace object that contains information about the Guardrail behavior.
guardrail (dict) --
The guardrail trace object.
modelOutput (list) --
The output from the model.
(string) --
inputAssessment (dict) --
The input assessment.
(string) --
(dict) --
A behavior assessment of the guardrail policies used in a call to the Converse API.
topicPolicy (dict) --
The topic policy.
topics (list) --
The topics in the assessment.
(dict) --
Information about a topic guardrail.
name (string) --
The name for the guardrail.
type (string) --
The type behavior that the guardrail should perform when the model detects the topic.
action (string) --
The action the guardrail should take when it intervenes on a topic.
contentPolicy (dict) --
The content policy.
filters (list) --
The content policy filters.
(dict) --
The content filter for a guardrail.
type (string) --
The guardrail type.
confidence (string) --
The guardrail confidence.
filterStrength (string) --
The filter strength setting for the guardrail content filter.
action (string) --
The guardrail action.
wordPolicy (dict) --
The word policy.
customWords (list) --
Custom words in the assessment.
(dict) --
A custom word configured in a guardrail.
match (string) --
The match for the custom word.
action (string) --
The action for the custom word.
managedWordLists (list) --
Managed word lists in the assessment.
(dict) --
A managed word configured in a guardrail.
match (string) --
The match for the managed word.
type (string) --
The type for the managed word.
action (string) --
The action for the managed word.
sensitiveInformationPolicy (dict) --
The sensitive information policy.
piiEntities (list) --
The PII entities in the assessment.
(dict) --
A Personally Identifiable Information (PII) entity configured in a guardrail.
match (string) --
The PII entity filter match.
type (string) --
The PII entity filter type.
action (string) --
The PII entity filter action.
regexes (list) --
The regex queries in the assessment.
(dict) --
A Regex filter configured in a guardrail.
name (string) --
The regex filter name.
match (string) --
The regesx filter match.
regex (string) --
The regex query.
action (string) --
The region filter action.
contextualGroundingPolicy (dict) --
The contextual grounding policy used for the guardrail assessment.
filters (list) --
The filter details for the guardrails contextual grounding filter.
(dict) --
The details for the guardrails contextual grounding filter.
type (string) --
The contextual grounding filter type.
threshold (float) --
The threshold used by contextual grounding filter to determine whether the content is grounded or not.
score (float) --
The score generated by contextual grounding filter.
action (string) --
The action performed by the guardrails contextual grounding filter.
invocationMetrics (dict) --
The invocation metrics for the guardrail assessment.
guardrailProcessingLatency (integer) --
The processing latency details for the guardrail invocation metrics.
usage (dict) --
The usage details for the guardrail invocation metrics.
topicPolicyUnits (integer) --
The topic policy units processed by the guardrail.
contentPolicyUnits (integer) --
The content policy units processed by the guardrail.
wordPolicyUnits (integer) --
The word policy units processed by the guardrail.
sensitiveInformationPolicyUnits (integer) --
The sensitive information policy units processed by the guardrail.
sensitiveInformationPolicyFreeUnits (integer) --
The sensitive information policy free units processed by the guardrail.
contextualGroundingPolicyUnits (integer) --
The contextual grounding policy units processed by the guardrail.
guardrailCoverage (dict) --
The coverage details for the guardrail invocation metrics.
textCharacters (dict) --
The text characters of the guardrail coverage details.
guarded (integer) --
The text characters that were guarded by the guardrail coverage.
total (integer) --
The total text characters by the guardrail coverage.
outputAssessments (dict) --
the output assessments.
(string) --
(list) --
(dict) --
A behavior assessment of the guardrail policies used in a call to the Converse API.
topicPolicy (dict) --
The topic policy.
topics (list) --
The topics in the assessment.
(dict) --
Information about a topic guardrail.
name (string) --
The name for the guardrail.
type (string) --
The type behavior that the guardrail should perform when the model detects the topic.
action (string) --
The action the guardrail should take when it intervenes on a topic.
contentPolicy (dict) --
The content policy.
filters (list) --
The content policy filters.
(dict) --
The content filter for a guardrail.
type (string) --
The guardrail type.
confidence (string) --
The guardrail confidence.
filterStrength (string) --
The filter strength setting for the guardrail content filter.
action (string) --
The guardrail action.
wordPolicy (dict) --
The word policy.
customWords (list) --
Custom words in the assessment.
(dict) --
A custom word configured in a guardrail.
match (string) --
The match for the custom word.
action (string) --
The action for the custom word.
managedWordLists (list) --
Managed word lists in the assessment.
(dict) --
A managed word configured in a guardrail.
match (string) --
The match for the managed word.
type (string) --
The type for the managed word.
action (string) --
The action for the managed word.
sensitiveInformationPolicy (dict) --
The sensitive information policy.
piiEntities (list) --
The PII entities in the assessment.
(dict) --
A Personally Identifiable Information (PII) entity configured in a guardrail.
match (string) --
The PII entity filter match.
type (string) --
The PII entity filter type.
action (string) --
The PII entity filter action.
regexes (list) --
The regex queries in the assessment.
(dict) --
A Regex filter configured in a guardrail.
name (string) --
The regex filter name.
match (string) --
The regesx filter match.
regex (string) --
The regex query.
action (string) --
The region filter action.
contextualGroundingPolicy (dict) --
The contextual grounding policy used for the guardrail assessment.
filters (list) --
The filter details for the guardrails contextual grounding filter.
(dict) --
The details for the guardrails contextual grounding filter.
type (string) --
The contextual grounding filter type.
threshold (float) --
The threshold used by contextual grounding filter to determine whether the content is grounded or not.
score (float) --
The score generated by contextual grounding filter.
action (string) --
The action performed by the guardrails contextual grounding filter.
invocationMetrics (dict) --
The invocation metrics for the guardrail assessment.
guardrailProcessingLatency (integer) --
The processing latency details for the guardrail invocation metrics.
usage (dict) --
The usage details for the guardrail invocation metrics.
topicPolicyUnits (integer) --
The topic policy units processed by the guardrail.
contentPolicyUnits (integer) --
The content policy units processed by the guardrail.
wordPolicyUnits (integer) --
The word policy units processed by the guardrail.
sensitiveInformationPolicyUnits (integer) --
The sensitive information policy units processed by the guardrail.
sensitiveInformationPolicyFreeUnits (integer) --
The sensitive information policy free units processed by the guardrail.
contextualGroundingPolicyUnits (integer) --
The contextual grounding policy units processed by the guardrail.
guardrailCoverage (dict) --
The coverage details for the guardrail invocation metrics.
textCharacters (dict) --
The text characters of the guardrail coverage details.
guarded (integer) --
The text characters that were guarded by the guardrail coverage.
total (integer) --
The total text characters by the guardrail coverage.
performanceConfig (dict) --
Model performance settings for the request.
latency (string) --
To use a latency-optimized version of the model, set to optimized.
{'performanceConfig': {'latency': 'standard | optimized'}}
Response {'stream': {'metadata': {'performanceConfig': {'latency': 'standard | '
'optimized'}}}}
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.
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.
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
See also: AWS API Documentation
Request Syntax
client.converse_stream(
modelId='string',
messages=[
{
'role': 'user'|'assistant',
'content': [
{
'text': 'string',
'image': {
'format': 'png'|'jpeg'|'gif'|'webp',
'source': {
'bytes': b'bytes'
}
},
'document': {
'format': 'pdf'|'csv'|'doc'|'docx'|'xls'|'xlsx'|'html'|'txt'|'md',
'name': 'string',
'source': {
'bytes': b'bytes'
}
},
'toolUse': {
'toolUseId': 'string',
'name': 'string',
'input': {...}|[...]|123|123.4|'string'|True|None
},
'toolResult': {
'toolUseId': 'string',
'content': [
{
'json': {...}|[...]|123|123.4|'string'|True|None,
'text': 'string',
'image': {
'format': 'png'|'jpeg'|'gif'|'webp',
'source': {
'bytes': b'bytes'
}
},
'document': {
'format': 'pdf'|'csv'|'doc'|'docx'|'xls'|'xlsx'|'html'|'txt'|'md',
'name': 'string',
'source': {
'bytes': b'bytes'
}
}
},
],
'status': 'success'|'error'
},
'guardContent': {
'text': {
'text': 'string',
'qualifiers': [
'grounding_source'|'query'|'guard_content',
]
}
}
},
]
},
],
system=[
{
'text': 'string',
'guardContent': {
'text': {
'text': 'string',
'qualifiers': [
'grounding_source'|'query'|'guard_content',
]
}
}
},
],
inferenceConfig={
'maxTokens': 123,
'temperature': ...,
'topP': ...,
'stopSequences': [
'string',
]
},
toolConfig={
'tools': [
{
'toolSpec': {
'name': 'string',
'description': 'string',
'inputSchema': {
'json': {...}|[...]|123|123.4|'string'|True|None
}
}
},
],
'toolChoice': {
'auto': {}
,
'any': {}
,
'tool': {
'name': 'string'
}
}
},
guardrailConfig={
'guardrailIdentifier': 'string',
'guardrailVersion': 'string',
'trace': 'enabled'|'disabled',
'streamProcessingMode': 'sync'|'async'
},
additionalModelRequestFields={...}|[...]|123|123.4|'string'|True|None,
promptVariables={
'string': {
'text': 'string'
}
},
additionalModelResponseFieldPaths=[
'string',
],
performanceConfig={
'latency': 'standard'|'optimized'
}
)
string
[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.
list
The messages that you want to send to the model.
(dict) --
A message input, or returned from, a call to Converse or ConverseStream.
role (string) -- [REQUIRED]
The role that the message plays in the message.
content (list) -- [REQUIRED]
The message content. Note the following restrictions:
You can include up to 20 images. Each image's size, height, and width must be no more than 3.75 MB, 8000 px, and 8000 px, respectively.
You can include up to five documents. Each document's size must be no more than 4.5 MB.
If you include a ContentBlock with a document field in the array, you must also include a ContentBlock with a text field.
You can only include images and documents if the role is user.
(dict) --
A block of content for a message that you pass to, or receive from, a model with the Converse or ConverseStream API operations.
text (string) --
Text to include in the message.
image (dict) --
Image to include in the message.
format (string) -- [REQUIRED]
The format of the image.
source (dict) -- [REQUIRED]
The source for the image.
bytes (bytes) --
The raw image bytes for the image. If you use an AWS SDK, you don't need to encode the image bytes in base64.
document (dict) --
A document to include in the message.
format (string) -- [REQUIRED]
The format of a document, or its extension.
name (string) -- [REQUIRED]
A name for the document. The name can only contain the following characters:
Alphanumeric characters
Whitespace characters (no more than one in a row)
Hyphens
Parentheses
Square brackets
source (dict) -- [REQUIRED]
Contains the content of the document.
bytes (bytes) --
The raw bytes for the document. If you use an Amazon Web Services SDK, you don't need to encode the bytes in base64.
toolUse (dict) --
Information about a tool use request from a model.
toolUseId (string) -- [REQUIRED]
The ID for the tool request.
name (string) -- [REQUIRED]
The name of the tool that the model wants to use.
input (:ref:`document<document>`) -- [REQUIRED]
The input to pass to the tool.
toolResult (dict) --
The result for a tool request that a model makes.
toolUseId (string) -- [REQUIRED]
The ID of the tool request that this is the result for.
content (list) -- [REQUIRED]
The content for tool result content block.
(dict) --
The tool result content block.
json (:ref:`document<document>`) --
A tool result that is JSON format data.
text (string) --
A tool result that is text.
image (dict) --
A tool result that is an image.
format (string) -- [REQUIRED]
The format of the image.
source (dict) -- [REQUIRED]
The source for the image.
bytes (bytes) --
The raw image bytes for the image. If you use an AWS SDK, you don't need to encode the image bytes in base64.
document (dict) --
A tool result that is a document.
format (string) -- [REQUIRED]
The format of a document, or its extension.
name (string) -- [REQUIRED]
A name for the document. The name can only contain the following characters:
Alphanumeric characters
Whitespace characters (no more than one in a row)
Hyphens
Parentheses
Square brackets
source (dict) -- [REQUIRED]
Contains the content of the document.
bytes (bytes) --
The raw bytes for the document. If you use an Amazon Web Services SDK, you don't need to encode the bytes in base64.
status (string) --
The status for the tool result content block.
guardContent (dict) --
Contains the content to assess with the guardrail. If you don't specify guardContent in a call to the Converse API, the guardrail (if passed in the Converse API) assesses the entire message.
For more information, see Use a guardrail with the Converse API in the Amazon Bedrock User Guide. </p>
text (dict) --
The text to guard.
text (string) -- [REQUIRED]
The text that you want to guard.
qualifiers (list) --
The qualifier details for the guardrails contextual grounding filter.
(string) --
list
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.
(dict) --
A system content block.
text (string) --
A system prompt for the model.
guardContent (dict) --
A content block to assess with the guardrail. Use with the Converse or ConverseStream API operations.
For more information, see Use a guardrail with the Converse API in the Amazon Bedrock User Guide.
text (dict) --
The text to guard.
text (string) -- [REQUIRED]
The text that you want to guard.
qualifiers (list) --
The qualifier details for the guardrails contextual grounding filter.
(string) --
dict
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.
maxTokens (integer) --
The maximum number of tokens to allow in the generated response. The default value is the maximum allowed value for the model that you are using. For more information, see Inference parameters for foundation models.
temperature (float) --
The likelihood of the model selecting higher-probability options while generating a response. A lower value makes the model more likely to choose higher-probability options, while a higher value makes the model more likely to choose lower-probability options.
The default value is the default value for the model that you are using. For more information, see Inference parameters for foundation models.
topP (float) --
The percentage of most-likely candidates that the model considers for the next token. For example, if you choose a value of 0.8 for topP, the model selects from the top 80% of the probability distribution of tokens that could be next in the sequence.
The default value is the default value for the model that you are using. For more information, see Inference parameters for foundation models.
stopSequences (list) --
A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response.
(string) --
dict
Configuration information for the tools that the model can use when generating a response.
tools (list) -- [REQUIRED]
An array of tools that you want to pass to a model.
(dict) --
Information about a tool that you can use with the Converse API. For more information, see Tool use (function calling) in the Amazon Bedrock User Guide.
toolSpec (dict) --
The specfication for the tool.
name (string) -- [REQUIRED]
The name for the tool.
description (string) --
The description for the tool.
inputSchema (dict) -- [REQUIRED]
The input schema for the tool in JSON format.
json (:ref:`document<document>`) --
The JSON schema for the tool. For more information, see JSON Schema Reference.
toolChoice (dict) --
If supported by model, forces the model to request a tool.
auto (:class:`.EventStream`) --
(Default). The Model automatically decides if a tool should be called or whether to generate text instead.
any (:class:`.EventStream`) --
The model must request at least one tool (no text is generated).
tool (dict) --
The Model must request the specified tool. Only supported by Anthropic Claude 3 models.
name (string) -- [REQUIRED]
The name of the tool that the model must request.
dict
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.
guardrailIdentifier (string) -- [REQUIRED]
The identifier for the guardrail.
guardrailVersion (string) -- [REQUIRED]
The version of the guardrail.
trace (string) --
The trace behavior for the guardrail.
streamProcessingMode (string) --
The processing mode.
The processing mode. For more information, see Configure streaming response behavior in the Amazon Bedrock User Guide.
:ref:`document<document>`
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.
dict
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.
(string) --
(dict) --
Contains a map of variables in a prompt from Prompt management to an object containing the values to fill in for them when running model invocation. For more information, see How Prompt management works.
text (string) --
The text value that the variable maps to.
list
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.
(string) --
dict
Model performance settings for the request.
latency (string) --
To use a latency-optimized version of the model, set to optimized.
dict
The response of this operation contains an :class:`.EventStream` member. When iterated the :class:`.EventStream` will yield events based on the structure below, where only one of the top level keys will be present for any given event.
Response Syntax
{
'stream': EventStream({
'messageStart': {
'role': 'user'|'assistant'
},
'contentBlockStart': {
'start': {
'toolUse': {
'toolUseId': 'string',
'name': 'string'
}
},
'contentBlockIndex': 123
},
'contentBlockDelta': {
'delta': {
'text': 'string',
'toolUse': {
'input': 'string'
}
},
'contentBlockIndex': 123
},
'contentBlockStop': {
'contentBlockIndex': 123
},
'messageStop': {
'stopReason': 'end_turn'|'tool_use'|'max_tokens'|'stop_sequence'|'guardrail_intervened'|'content_filtered',
'additionalModelResponseFields': {...}|[...]|123|123.4|'string'|True|None
},
'metadata': {
'usage': {
'inputTokens': 123,
'outputTokens': 123,
'totalTokens': 123
},
'metrics': {
'latencyMs': 123
},
'trace': {
'guardrail': {
'modelOutput': [
'string',
],
'inputAssessment': {
'string': {
'topicPolicy': {
'topics': [
{
'name': 'string',
'type': 'DENY',
'action': 'BLOCKED'
},
]
},
'contentPolicy': {
'filters': [
{
'type': 'INSULTS'|'HATE'|'SEXUAL'|'VIOLENCE'|'MISCONDUCT'|'PROMPT_ATTACK',
'confidence': 'NONE'|'LOW'|'MEDIUM'|'HIGH',
'filterStrength': 'NONE'|'LOW'|'MEDIUM'|'HIGH',
'action': 'BLOCKED'
},
]
},
'wordPolicy': {
'customWords': [
{
'match': 'string',
'action': 'BLOCKED'
},
],
'managedWordLists': [
{
'match': 'string',
'type': 'PROFANITY',
'action': 'BLOCKED'
},
]
},
'sensitiveInformationPolicy': {
'piiEntities': [
{
'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': [
{
'name': 'string',
'match': 'string',
'regex': 'string',
'action': 'ANONYMIZED'|'BLOCKED'
},
]
},
'contextualGroundingPolicy': {
'filters': [
{
'type': 'GROUNDING'|'RELEVANCE',
'threshold': 123.0,
'score': 123.0,
'action': 'BLOCKED'|'NONE'
},
]
},
'invocationMetrics': {
'guardrailProcessingLatency': 123,
'usage': {
'topicPolicyUnits': 123,
'contentPolicyUnits': 123,
'wordPolicyUnits': 123,
'sensitiveInformationPolicyUnits': 123,
'sensitiveInformationPolicyFreeUnits': 123,
'contextualGroundingPolicyUnits': 123
},
'guardrailCoverage': {
'textCharacters': {
'guarded': 123,
'total': 123
}
}
}
}
},
'outputAssessments': {
'string': [
{
'topicPolicy': {
'topics': [
{
'name': 'string',
'type': 'DENY',
'action': 'BLOCKED'
},
]
},
'contentPolicy': {
'filters': [
{
'type': 'INSULTS'|'HATE'|'SEXUAL'|'VIOLENCE'|'MISCONDUCT'|'PROMPT_ATTACK',
'confidence': 'NONE'|'LOW'|'MEDIUM'|'HIGH',
'filterStrength': 'NONE'|'LOW'|'MEDIUM'|'HIGH',
'action': 'BLOCKED'
},
]
},
'wordPolicy': {
'customWords': [
{
'match': 'string',
'action': 'BLOCKED'
},
],
'managedWordLists': [
{
'match': 'string',
'type': 'PROFANITY',
'action': 'BLOCKED'
},
]
},
'sensitiveInformationPolicy': {
'piiEntities': [
{
'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': [
{
'name': 'string',
'match': 'string',
'regex': 'string',
'action': 'ANONYMIZED'|'BLOCKED'
},
]
},
'contextualGroundingPolicy': {
'filters': [
{
'type': 'GROUNDING'|'RELEVANCE',
'threshold': 123.0,
'score': 123.0,
'action': 'BLOCKED'|'NONE'
},
]
},
'invocationMetrics': {
'guardrailProcessingLatency': 123,
'usage': {
'topicPolicyUnits': 123,
'contentPolicyUnits': 123,
'wordPolicyUnits': 123,
'sensitiveInformationPolicyUnits': 123,
'sensitiveInformationPolicyFreeUnits': 123,
'contextualGroundingPolicyUnits': 123
},
'guardrailCoverage': {
'textCharacters': {
'guarded': 123,
'total': 123
}
}
}
},
]
}
}
},
'performanceConfig': {
'latency': 'standard'|'optimized'
}
},
'internalServerException': {
'message': 'string'
},
'modelStreamErrorException': {
'message': 'string',
'originalStatusCode': 123,
'originalMessage': 'string'
},
'validationException': {
'message': 'string'
},
'throttlingException': {
'message': 'string'
},
'serviceUnavailableException': {
'message': 'string'
}
})
}
Response Structure
(dict) --
stream (:class:`.EventStream`) --
The output stream that the model generated.
messageStart (dict) --
Message start information.
role (string) --
The role for the message.
contentBlockStart (dict) --
Start information for a content block.
start (dict) --
Start information about a content block start event.
toolUse (dict) --
Information about a tool that the model is requesting to use.
toolUseId (string) --
The ID for the tool request.
name (string) --
The name of the tool that the model is requesting to use.
contentBlockIndex (integer) --
The index for a content block start event.
contentBlockDelta (dict) --
The messages output content block delta.
delta (dict) --
The delta for a content block delta event.
text (string) --
The content text.
toolUse (dict) --
Information about a tool that the model is requesting to use.
input (string) --
The input for a requested tool.
contentBlockIndex (integer) --
The block index for a content block delta event.
contentBlockStop (dict) --
Stop information for a content block.
contentBlockIndex (integer) --
The index for a content block.
messageStop (dict) --
Message stop information.
stopReason (string) --
The reason why the model stopped generating output.
additionalModelResponseFields (:ref:`document<document>`) --
The additional model response fields.
metadata (dict) --
Metadata for the converse output stream.
usage (dict) --
Usage information for the conversation stream event.
inputTokens (integer) --
The number of tokens sent in the request to the model.
outputTokens (integer) --
The number of tokens that the model generated for the request.
totalTokens (integer) --
The total of input tokens and tokens generated by the model.
metrics (dict) --
The metrics for the conversation stream metadata event.
latencyMs (integer) --
The latency for the streaming request, in milliseconds.
trace (dict) --
The trace object in the response from ConverseStream that contains information about the guardrail behavior.
guardrail (dict) --
The guardrail trace object.
modelOutput (list) --
The output from the model.
(string) --
inputAssessment (dict) --
The input assessment.
(string) --
(dict) --
A behavior assessment of the guardrail policies used in a call to the Converse API.
topicPolicy (dict) --
The topic policy.
topics (list) --
The topics in the assessment.
(dict) --
Information about a topic guardrail.
name (string) --
The name for the guardrail.
type (string) --
The type behavior that the guardrail should perform when the model detects the topic.
action (string) --
The action the guardrail should take when it intervenes on a topic.
contentPolicy (dict) --
The content policy.
filters (list) --
The content policy filters.
(dict) --
The content filter for a guardrail.
type (string) --
The guardrail type.
confidence (string) --
The guardrail confidence.
filterStrength (string) --
The filter strength setting for the guardrail content filter.
action (string) --
The guardrail action.
wordPolicy (dict) --
The word policy.
customWords (list) --
Custom words in the assessment.
(dict) --
A custom word configured in a guardrail.
match (string) --
The match for the custom word.
action (string) --
The action for the custom word.
managedWordLists (list) --
Managed word lists in the assessment.
(dict) --
A managed word configured in a guardrail.
match (string) --
The match for the managed word.
type (string) --
The type for the managed word.
action (string) --
The action for the managed word.
sensitiveInformationPolicy (dict) --
The sensitive information policy.
piiEntities (list) --
The PII entities in the assessment.
(dict) --
A Personally Identifiable Information (PII) entity configured in a guardrail.
match (string) --
The PII entity filter match.
type (string) --
The PII entity filter type.
action (string) --
The PII entity filter action.
regexes (list) --
The regex queries in the assessment.
(dict) --
A Regex filter configured in a guardrail.
name (string) --
The regex filter name.
match (string) --
The regesx filter match.
regex (string) --
The regex query.
action (string) --
The region filter action.
contextualGroundingPolicy (dict) --
The contextual grounding policy used for the guardrail assessment.
filters (list) --
The filter details for the guardrails contextual grounding filter.
(dict) --
The details for the guardrails contextual grounding filter.
type (string) --
The contextual grounding filter type.
threshold (float) --
The threshold used by contextual grounding filter to determine whether the content is grounded or not.
score (float) --
The score generated by contextual grounding filter.
action (string) --
The action performed by the guardrails contextual grounding filter.
invocationMetrics (dict) --
The invocation metrics for the guardrail assessment.
guardrailProcessingLatency (integer) --
The processing latency details for the guardrail invocation metrics.
usage (dict) --
The usage details for the guardrail invocation metrics.
topicPolicyUnits (integer) --
The topic policy units processed by the guardrail.
contentPolicyUnits (integer) --
The content policy units processed by the guardrail.
wordPolicyUnits (integer) --
The word policy units processed by the guardrail.
sensitiveInformationPolicyUnits (integer) --
The sensitive information policy units processed by the guardrail.
sensitiveInformationPolicyFreeUnits (integer) --
The sensitive information policy free units processed by the guardrail.
contextualGroundingPolicyUnits (integer) --
The contextual grounding policy units processed by the guardrail.
guardrailCoverage (dict) --
The coverage details for the guardrail invocation metrics.
textCharacters (dict) --
The text characters of the guardrail coverage details.
guarded (integer) --
The text characters that were guarded by the guardrail coverage.
total (integer) --
The total text characters by the guardrail coverage.
outputAssessments (dict) --
the output assessments.
(string) --
(list) --
(dict) --
A behavior assessment of the guardrail policies used in a call to the Converse API.
topicPolicy (dict) --
The topic policy.
topics (list) --
The topics in the assessment.
(dict) --
Information about a topic guardrail.
name (string) --
The name for the guardrail.
type (string) --
The type behavior that the guardrail should perform when the model detects the topic.
action (string) --
The action the guardrail should take when it intervenes on a topic.
contentPolicy (dict) --
The content policy.
filters (list) --
The content policy filters.
(dict) --
The content filter for a guardrail.
type (string) --
The guardrail type.
confidence (string) --
The guardrail confidence.
filterStrength (string) --
The filter strength setting for the guardrail content filter.
action (string) --
The guardrail action.
wordPolicy (dict) --
The word policy.
customWords (list) --
Custom words in the assessment.
(dict) --
A custom word configured in a guardrail.
match (string) --
The match for the custom word.
action (string) --
The action for the custom word.
managedWordLists (list) --
Managed word lists in the assessment.
(dict) --
A managed word configured in a guardrail.
match (string) --
The match for the managed word.
type (string) --
The type for the managed word.
action (string) --
The action for the managed word.
sensitiveInformationPolicy (dict) --
The sensitive information policy.
piiEntities (list) --
The PII entities in the assessment.
(dict) --
A Personally Identifiable Information (PII) entity configured in a guardrail.
match (string) --
The PII entity filter match.
type (string) --
The PII entity filter type.
action (string) --
The PII entity filter action.
regexes (list) --
The regex queries in the assessment.
(dict) --
A Regex filter configured in a guardrail.
name (string) --
The regex filter name.
match (string) --
The regesx filter match.
regex (string) --
The regex query.
action (string) --
The region filter action.
contextualGroundingPolicy (dict) --
The contextual grounding policy used for the guardrail assessment.
filters (list) --
The filter details for the guardrails contextual grounding filter.
(dict) --
The details for the guardrails contextual grounding filter.
type (string) --
The contextual grounding filter type.
threshold (float) --
The threshold used by contextual grounding filter to determine whether the content is grounded or not.
score (float) --
The score generated by contextual grounding filter.
action (string) --
The action performed by the guardrails contextual grounding filter.
invocationMetrics (dict) --
The invocation metrics for the guardrail assessment.
guardrailProcessingLatency (integer) --
The processing latency details for the guardrail invocation metrics.
usage (dict) --
The usage details for the guardrail invocation metrics.
topicPolicyUnits (integer) --
The topic policy units processed by the guardrail.
contentPolicyUnits (integer) --
The content policy units processed by the guardrail.
wordPolicyUnits (integer) --
The word policy units processed by the guardrail.
sensitiveInformationPolicyUnits (integer) --
The sensitive information policy units processed by the guardrail.
sensitiveInformationPolicyFreeUnits (integer) --
The sensitive information policy free units processed by the guardrail.
contextualGroundingPolicyUnits (integer) --
The contextual grounding policy units processed by the guardrail.
guardrailCoverage (dict) --
The coverage details for the guardrail invocation metrics.
textCharacters (dict) --
The text characters of the guardrail coverage details.
guarded (integer) --
The text characters that were guarded by the guardrail coverage.
total (integer) --
The total text characters by the guardrail coverage.
performanceConfig (dict) --
Model performance configuration metadata for the conversation stream event.
latency (string) --
To use a latency-optimized version of the model, set to optimized.
internalServerException (dict) --
An internal server error occurred. Retry your request.
message (string) --
modelStreamErrorException (dict) --
A streaming error occurred. Retry your request.
message (string) --
originalStatusCode (integer) --
The original status code.
originalMessage (string) --
The original message.
validationException (dict) --
Input validation failed. Check your request parameters and retry the request.
message (string) --
throttlingException (dict) --
The number of requests exceeds the limit. Resubmit your request later.
message (string) --
serviceUnavailableException (dict) --
The service isn't currently available. For troubleshooting this error, see ServiceUnavailable in the Amazon Bedrock User Guide
message (string) --
{'performanceConfigLatency': 'standard | optimized'}
Invokes the specified Amazon Bedrock model to run inference using the prompt and inference parameters provided in the request body. You use model inference to generate text, images, and embeddings.
For example code, see Invoke model code examples in the Amazon Bedrock User Guide.
This operation requires permission for the bedrock:InvokeModel action.
For troubleshooting some of the common errors you might encounter when using the InvokeModel API, see Troubleshooting Amazon Bedrock API Error Codes in the Amazon Bedrock User Guide
See also: AWS API Documentation
Request Syntax
client.invoke_model(
body=b'bytes'|file,
contentType='string',
accept='string',
modelId='string',
trace='ENABLED'|'DISABLED',
guardrailIdentifier='string',
guardrailVersion='string',
performanceConfigLatency='standard'|'optimized'
)
bytes or seekable file-like object
The prompt and inference parameters in the format specified in the contentType in the header. You must provide the body in JSON format. To see the format and content of the request and response bodies for different models, refer to Inference parameters. For more information, see Run inference in the Bedrock User Guide.
string
The MIME type of the input data in the request. You must specify application/json.
string
The desired MIME type of the inference body in the response. The default value is application/json.
string
[REQUIRED]
The unique identifier of the model to invoke to run inference.
The modelId to provide depends on the type of model or throughput 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.
If you use an imported model, specify the ARN of the imported model. You can get the model ARN from a successful call to CreateModelImportJob or from the Imported models page in the Amazon Bedrock console.
string
Specifies whether to enable or disable the Bedrock trace. If enabled, you can see the full Bedrock trace.
string
The unique identifier of the guardrail that you want to use. If you don't provide a value, no guardrail is applied to the invocation.
An error will be thrown in the following situations.
You don't provide a guardrail identifier but you specify the amazon-bedrock-guardrailConfig field in the request body.
You enable the guardrail but the contentType isn't application/json.
You provide a guardrail identifier, but guardrailVersion isn't specified.
string
The version number for the guardrail. The value can also be DRAFT.
string
Model performance settings for the request.
dict
Response Syntax
{
'body': b'bytes'|file,
'contentType': 'string',
'performanceConfigLatency': 'standard'|'optimized'
}
Response Structure
(dict) --
body (bytes or seekable file-like object) --
Inference response from the model in the format specified in the contentType header. To see the format and content of the request and response bodies for different models, refer to Inference parameters.
contentType (string) --
The MIME type of the inference result.
performanceConfigLatency (string) --
Model performance settings for the request.
{'performanceConfigLatency': 'standard | optimized'}
Invoke the specified Amazon Bedrock model to run inference using the prompt and inference parameters provided in the request body. The response is returned in a stream.
To see if a model supports streaming, call GetFoundationModel and check the responseStreamingSupported field in the response.
For example code, see Invoke model with streaming code example in the Amazon Bedrock User Guide.
This operation requires permissions to perform the bedrock:InvokeModelWithResponseStream action.
For troubleshooting some of the common errors you might encounter when using the InvokeModelWithResponseStream API, see Troubleshooting Amazon Bedrock API Error Codes in the Amazon Bedrock User Guide
See also: AWS API Documentation
Request Syntax
client.invoke_model_with_response_stream(
body=b'bytes'|file,
contentType='string',
accept='string',
modelId='string',
trace='ENABLED'|'DISABLED',
guardrailIdentifier='string',
guardrailVersion='string',
performanceConfigLatency='standard'|'optimized'
)
bytes or seekable file-like object
The prompt and inference parameters in the format specified in the contentType in the header. You must provide the body in JSON format. To see the format and content of the request and response bodies for different models, refer to Inference parameters. For more information, see Run inference in the Bedrock User Guide.
string
The MIME type of the input data in the request. You must specify application/json.
string
The desired MIME type of the inference body in the response. The default value is application/json.
string
[REQUIRED]
The unique identifier of the model to invoke to run inference.
The modelId to provide depends on the type of model or throughput 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.
If you use an imported model, specify the ARN of the imported model. You can get the model ARN from a successful call to CreateModelImportJob or from the Imported models page in the Amazon Bedrock console.
string
Specifies whether to enable or disable the Bedrock trace. If enabled, you can see the full Bedrock trace.
string
The unique identifier of the guardrail that you want to use. If you don't provide a value, no guardrail is applied to the invocation.
An error is thrown in the following situations.
You don't provide a guardrail identifier but you specify the amazon-bedrock-guardrailConfig field in the request body.
You enable the guardrail but the contentType isn't application/json.
You provide a guardrail identifier, but guardrailVersion isn't specified.
string
The version number for the guardrail. The value can also be DRAFT.
string
Model performance settings for the request.
dict
The response of this operation contains an :class:`.EventStream` member. When iterated the :class:`.EventStream` will yield events based on the structure below, where only one of the top level keys will be present for any given event.
Response Syntax
{
'body': EventStream({
'chunk': {
'bytes': b'bytes'
},
'internalServerException': {
'message': 'string'
},
'modelStreamErrorException': {
'message': 'string',
'originalStatusCode': 123,
'originalMessage': 'string'
},
'validationException': {
'message': 'string'
},
'throttlingException': {
'message': 'string'
},
'modelTimeoutException': {
'message': 'string'
},
'serviceUnavailableException': {
'message': 'string'
}
}),
'contentType': 'string',
'performanceConfigLatency': 'standard'|'optimized'
}
Response Structure
(dict) --
body (:class:`.EventStream`) --
Inference response from the model in the format specified by the contentType header. To see the format and content of this field for different models, refer to Inference parameters.
chunk (dict) --
Content included in the response.
bytes (bytes) --
Base64-encoded bytes of payload data.
internalServerException (dict) --
An internal server error occurred. Retry your request.
message (string) --
modelStreamErrorException (dict) --
An error occurred while streaming the response. Retry your request.
message (string) --
originalStatusCode (integer) --
The original status code.
originalMessage (string) --
The original message.
validationException (dict) --
Input validation failed. Check your request parameters and retry the request.
message (string) --
throttlingException (dict) --
Your request was throttled because of service-wide limitations. Resubmit your request later or in a different region. You can also purchase Provisioned Throughput to increase the rate or number of tokens you can process.
message (string) --
modelTimeoutException (dict) --
The request took too long to process. Processing time exceeded the model timeout length.
message (string) --
serviceUnavailableException (dict) --
The service isn't available. Try again later.
message (string) --
contentType (string) --
The MIME type of the inference result.
performanceConfigLatency (string) --
Model performance settings for the request.