|
11 | 11 | "GetAgentMemory": "<p>Gets the sessions stored in the memory of the agent.</p>", |
12 | 12 | "GetInvocationStep": "<p>Retrieves the details of a specific invocation step within an invocation in a session. For more information about sessions, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/sessions.html\">Store and retrieve conversation history and context with Amazon Bedrock sessions</a>.</p>", |
13 | 13 | "GetSession": "<p>Retrieves details about a specific session. For more information about sessions, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/sessions.html\">Store and retrieve conversation history and context with Amazon Bedrock sessions</a>.</p>", |
14 | | - "InvokeAgent": "<note> </note> <p>Sends a prompt for the agent to process and respond to. Note the following fields for the request:</p> <ul> <li> <p>To continue the same conversation with an agent, use the same <code>sessionId</code> value in the request.</p> </li> <li> <p>To activate trace enablement, turn <code>enableTrace</code> to <code>true</code>. Trace enablement helps you follow the agent's reasoning process that led it to the information it processed, the actions it took, and the final result it yielded. For more information, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/agents-test.html#trace-events\">Trace enablement</a>.</p> </li> <li> <p>To stream agent responses, make sure that only orchestration prompt is enabled. Agent streaming is not supported for the following steps: </p> <ul> <li> <p> <code>Pre-processing</code> </p> </li> <li> <p> <code>Post-processing</code> </p> </li> <li> <p>Agent with 1 Knowledge base and <code>User Input</code> not enabled</p> </li> </ul> </li> <li> <p>End a conversation by setting <code>endSession</code> to <code>true</code>.</p> </li> <li> <p>In the <code>sessionState</code> object, you can include attributes for the session or prompt or, if you configured an action group to return control, results from invocation of the action group.</p> </li> </ul> <p>The response contains both <b>chunk</b> and <b>trace</b> attributes.</p> <p>The final response is returned in the <code>bytes</code> field of the <code>chunk</code> object. The <code>InvokeAgent</code> returns one chunk for the entire interaction.</p> <ul> <li> <p>The <code>attribution</code> object contains citations for parts of the response.</p> </li> <li> <p>If you set <code>enableTrace</code> to <code>true</code> in the request, you can trace the agent's steps and reasoning process that led it to the response.</p> </li> <li> <p>If the action predicted was configured to return control, the response returns parameters for the action, elicited from the user, in the <code>returnControl</code> field.</p> </li> <li> <p>Errors are also surfaced in the response.</p> </li> </ul>", |
| 14 | + "InvokeAgent": "<note> </note> <p>Sends a prompt for the agent to process and respond to. Note the following fields for the request:</p> <ul> <li> <p>To continue the same conversation with an agent, use the same <code>sessionId</code> value in the request.</p> </li> <li> <p>To activate trace enablement, turn <code>enableTrace</code> to <code>true</code>. Trace enablement helps you follow the agent's reasoning process that led it to the information it processed, the actions it took, and the final result it yielded. For more information, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/agents-test.html#trace-events\">Trace enablement</a>.</p> </li> <li> <p>End a conversation by setting <code>endSession</code> to <code>true</code>.</p> </li> <li> <p>In the <code>sessionState</code> object, you can include attributes for the session or prompt or, if you configured an action group to return control, results from invocation of the action group.</p> </li> </ul> <p>The response contains both <b>chunk</b> and <b>trace</b> attributes.</p> <p>The final response is returned in the <code>bytes</code> field of the <code>chunk</code> object. The <code>InvokeAgent</code> returns one chunk for the entire interaction.</p> <ul> <li> <p>The <code>attribution</code> object contains citations for parts of the response.</p> </li> <li> <p>If you set <code>enableTrace</code> to <code>true</code> in the request, you can trace the agent's steps and reasoning process that led it to the response.</p> </li> <li> <p>If the action predicted was configured to return control, the response returns parameters for the action, elicited from the user, in the <code>returnControl</code> field.</p> </li> <li> <p>Errors are also surfaced in the response.</p> </li> </ul>", |
15 | 15 | "InvokeFlow": "<p>Invokes an alias of a flow to run the inputs that you specify and return the output of each node as a stream. If there's an error, the error is returned. For more information, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/flows-test.html\">Test a flow in Amazon Bedrock</a> in the <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/what-is-service.html\">Amazon Bedrock User Guide</a>.</p> <note> <p>The CLI doesn't support streaming operations in Amazon Bedrock, including <code>InvokeFlow</code>.</p> </note>", |
16 | 16 | "InvokeInlineAgent": "<p> Invokes an inline Amazon Bedrock agent using the configurations you provide with the request. </p> <ul> <li> <p>Specify the following fields for security purposes.</p> <ul> <li> <p>(Optional) <code>customerEncryptionKeyArn</code> – The Amazon Resource Name (ARN) of a KMS key to encrypt the creation of the agent.</p> </li> <li> <p>(Optional) <code>idleSessionTTLinSeconds</code> – Specify the number of seconds for which the agent should maintain session information. After this time expires, the subsequent <code>InvokeInlineAgent</code> request begins a new session.</p> </li> </ul> </li> <li> <p>To override the default prompt behavior for agent orchestration and to use advanced prompts, include a <code>promptOverrideConfiguration</code> object. For more information, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/advanced-prompts.html\">Advanced prompts</a>.</p> </li> <li> <p>The agent instructions will not be honored if your agent has only one knowledge base, uses default prompts, has no action group, and user input is disabled.</p> </li> </ul> <note> </note>", |
17 | 17 | "ListInvocationSteps": "<p>Lists all invocation steps associated with a session and optionally, an invocation within the session. For more information about sessions, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/sessions.html\">Store and retrieve conversation history and context with Amazon Bedrock sessions</a>.</p>", |
|
580 | 580 | "CreateInvocationResponse$createdAt": "<p>The timestamp for when the invocation was created.</p>", |
581 | 581 | "CreateSessionResponse$createdAt": "<p>The timestamp for when the session was created.</p>", |
582 | 582 | "FlowTraceConditionNodeResultEvent$timestamp": "<p>The date and time that the trace was returned.</p>", |
| 583 | + "FlowTraceNodeActionEvent$timestamp": "<p>The date and time that the operation was called.</p>", |
583 | 584 | "FlowTraceNodeInputEvent$timestamp": "<p>The date and time that the trace was returned.</p>", |
584 | 585 | "FlowTraceNodeOutputEvent$timestamp": "<p>The date and time that the trace was returned.</p>", |
585 | 586 | "GetSessionResponse$createdAt": "<p>The timestamp for when the session was created.</p>", |
|
913 | 914 | "FlowResponseStream$flowTraceEvent": "<p>Contains information about a trace, which tracks an input or output for a node in the flow.</p>" |
914 | 915 | } |
915 | 916 | }, |
| 917 | + "FlowTraceNodeActionEvent": { |
| 918 | + "base": "<p>Contains information about an action (operation) called by a node in an Amazon Bedrock flow. The service generates action events for calls made by prompt nodes, agent nodes, and Amazon Web Services Lambda nodes. </p>", |
| 919 | + "refs": { |
| 920 | + "FlowTrace$nodeActionTrace": "<p>Contains information about an action (operation) called by a node. For more information, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/flows-trace.html\">Track each step in your prompt flow by viewing its trace in Amazon Bedrock</a>.</p>" |
| 921 | + } |
| 922 | + }, |
916 | 923 | "FlowTraceNodeInputContent": { |
917 | 924 | "base": "<p>Contains the content of the node input. For more information, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/flows-trace.html\">Track each step in your prompt flow by viewing its trace in Amazon Bedrock</a>.</p>", |
918 | 925 | "refs": { |
|
1967 | 1974 | "FlowMultiTurnInputRequestEvent$nodeName": "<p>The name of the node in the flow that is requesting the input.</p>", |
1968 | 1975 | "FlowOutputEvent$nodeName": "<p>The name of the flow output node that the output is from.</p>", |
1969 | 1976 | "FlowTraceConditionNodeResultEvent$nodeName": "<p>The name of the condition node.</p>", |
| 1977 | + "FlowTraceNodeActionEvent$nodeName": "<p>The name of the node that called the operation.</p>", |
1970 | 1978 | "FlowTraceNodeInputEvent$nodeName": "<p>The name of the node that received the input.</p>", |
1971 | 1979 | "FlowTraceNodeOutputEvent$nodeName": "<p>The name of the node that yielded the output.</p>" |
1972 | 1980 | } |
|
2983 | 2991 | } |
2984 | 2992 | }, |
2985 | 2993 | "StreamingConfigurations": { |
2986 | | - "base": "<p> Configurations for streaming.</p>", |
| 2994 | + "base": "<p>Configurations for streaming.</p>", |
2987 | 2995 | "refs": { |
2988 | 2996 | "InvokeAgentRequest$streamingConfigurations": "<p> Specifies the configurations for streaming. </p> <note> <p>To use agent streaming, you need permissions to perform the <code>bedrock:InvokeModelWithResponseStream</code> action.</p> </note>", |
2989 | 2997 | "InvokeInlineAgentRequest$streamingConfigurations": "<p> Specifies the configurations for streaming. </p> <note> <p>To use agent streaming, you need permissions to perform the <code>bedrock:InvokeModelWithResponseStream</code> action.</p> </note>" |
|
2992 | 3000 | "StreamingConfigurationsApplyGuardrailIntervalInteger": { |
2993 | 3001 | "base": null, |
2994 | 3002 | "refs": { |
2995 | | - "StreamingConfigurations$applyGuardrailInterval": "<p> The guardrail interval to apply as response is generated. </p>" |
| 3003 | + "StreamingConfigurations$applyGuardrailInterval": "<p> The guardrail interval to apply as response is generated. By default, the guardrail interval is set to 50 characters. If a larger interval is specified, the response will be generated in larger chunks with fewer <code>ApplyGuardrail</code> calls. The following examples show the response generated for <i>Hello, I am an agent</i> input string.</p> <p> <b>Example response in chunks: Interval set to 3 characters</b> </p> <p> <code>'Hel', 'lo, ','I am', ' an', ' Age', 'nt'</code> </p> <p>Each chunk has at least 3 characters except for the last chunk</p> <p> <b>Example response in chunks: Interval set to 20 or more characters</b> </p> <p> <code>Hello, I am an Agent</code> </p>" |
2996 | 3004 | } |
2997 | 3005 | }, |
2998 | 3006 | "String": { |
|
3021 | 3029 | "CustomOrchestrationTraceEvent$text": "<p> The text that prompted the event at this step. </p>", |
3022 | 3030 | "Files$member": null, |
3023 | 3031 | "FlowTraceCondition$conditionName": "<p>The name of the condition.</p>", |
| 3032 | + "FlowTraceNodeActionEvent$operationName": "<p>The name of the operation that the node called.</p>", |
| 3033 | + "FlowTraceNodeActionEvent$requestId": "<p>The ID of the request that the node made to the operation.</p>", |
| 3034 | + "FlowTraceNodeActionEvent$serviceName": "<p>The name of the service that the node called.</p>", |
3024 | 3035 | "FunctionInvocationInput$actionGroup": "<p>The action group that the function belongs to.</p>", |
3025 | 3036 | "FunctionInvocationInput$agentId": "<p>The agent's ID.</p>", |
3026 | 3037 | "FunctionInvocationInput$function": "<p>The name of the function.</p>", |
|
0 commit comments