Control session context

For greater control of session context, you can modify the SessionState object in your agent. The SessionState object contains information that can be maintained across turns (separate InvokeAgent request and responses). You can use this information to provide conversational context for the agent during user conversations.

The general format of the SessionState object is as follows.

{
    "sessionAttributes": {
        "<attributeName1>": "<attributeValue1>",
        "<attributeName2>": "<attributeValue2>",
        ...
    },
    "promptSessionAttributes": {
        "<attributeName3>": "<attributeValue3>",
        "<attributeName4>": "<attributeValue4>",
        ...
    },
    "invocationId": "string",
    "returnControlInvocationResults": [
        ApiResult or FunctionResult,
        ...
    ]
}

Select a topic to learn more about fields in the SessionState object.

Action group invocation results

If you configured an action group to return control in an InvokeAgent response, you can send the results from invoking the action group in the sessionState of a subsequent InvokeAgent response by including the following fields:

• invocationId – This ID must match the invocationId returned in the ReturnControlPayload object in the returnControl field of the InvokeAgent response.

• returnControlInvocationResults – Includes results that you obtain from invoking the action. You can set up your application to pass the ReturnControlPayload object to perform an API request or call a function that you define. You can then provide the results of that action here. Each member of the returnControlInvocationResults list is one of the following:

  • An ApiResult object containing the API operation that the agent predicted should be called in a previous InvokeAgent sequence and the results from invoking the action in your systems. The general format is as follows:

    {
        "actionGroup": "string",
        "apiPath": "string",
        "httpMethod": "string",
        "httpStatusCode": integer,
        "responseBody": {
            "TEXT": {
                "body": "string"
            }
        }
    }

  • A FunctionResult object containing the function that the agent predicted should be called in a previous InvokeAgent sequence and the results from invoking the action in your systems. The general format is as follows:

    {
        "actionGroup": "string",
        "function": "string",
        "responseBody": {
            "TEXT": {
                "body": "string"
            }
        }
    }

The results that are provided can be used as context for further orchestration, sent to post-processing for the agent to format a response, or used directly in the agent's response to the user.

Session and prompt session attributes

Agents for Amazon Bedrock allows you to define the following types of contextual attributes that persist over parts of a session:

• sessionAttributes – Attributes that persist over a session between a user and agent. All InvokeAgent requests made with the same sessionId belong to the same session, as long as the session time limit (the idleSessionTTLinSeconds) has not been surpassed.

• promptSessionAttributes – Attributes that persist over a single turn (one InvokeAgent call). You can use the $prompt_session_attributes$ placeholder when you edit the orchestration base prompt template. This placeholder will be populated at runtime with the attributes that you specify in the promptSessionAttributes field.

You can define the session state attributes at two different steps:

• When you set up an action group and write the Lambda function, include sessionAttributes or promptSessionAttributes in the response event that is returned to Amazon Bedrock.

• During runtime, when you send an InvokeAgent request, include a sessionState object in the request body to dynamically change the session state attributes in the middle of the conversation.

Session attribute example

The following example uses a session attribute to personalize a message to your user.

1. Write your application code to ask the user to provide their first name and the request they want to make to the agent and to store the answers as the variables <first_name> and <request>.

2. Write your application code to send an InvokeAgent request with the following body:

   {
       "inputText": "<request>",
       "sessionState": {
           "sessionAttributes": {
               "firstName": "<first_name>"
           }
       }
   }

3. When a user uses your application and provides their first name, your code will send the first name as a session attribute and the agent will store their first name for the duration of the session.

4. Because session attributes are sent in the Lambda input event, you can refer to these session attributes in a Lambda function for an action group. For example, if the action API schema requires a first name in the request body, you can use the firstName session attribute when writing the Lambda function for an action group to automatically populate that field when sending the API request.

Prompt session attribute example

The following general example uses a prompt session attribute to provide temporal context for the agent.

1. Write your application code to store the user request in a variable called <request>.

2. Write your application code to retrieve the time zone at the user's location if the user uses a word indicating relative time (such as "tomorrow") in the <request>, and store in a variable called <timezone>.

3. Write your application to send an InvokeAgent request with the following body:

   {
       "inputText": "<request>",
       "sessionState": {
           "promptSessionAttributes": {
               "timeZone": "<timezone>"
           }
       }
   }

4. If a user uses a word indicating relative time, your code will send the timeZone prompt session attribute and the agent will store it for the duration of the turn.

5. For example, if a user asks I need to book a hotel for tomorrow, your code sends the user's time zone to the agent and the agent can determine the exact date that "tomorrow" refers to.

6. The prompt session attribute can be used at the following steps.

   • If you include the $prompt_session_attributes$ placeholder in the orchestration prompt template, the orchestration prompt to the FM includes the prompt session attributes.

   • Prompt session attributes are sent in the Lambda input event and can be used to help populate API requests or returned in the response.