IAM Policy Using Request and Session Attributes as Filters Using the Search Response Using a Lambda Function to Manage the Request and Response

AMAZON.KendraSearchIntent

To search documents that you have indexed with Amazon Kendra, use the AMAZON.KendraSearchIntent intent. When Amazon Lex V2 can't determine the next action in a conversation with the user, it triggers the search intent.

The AMAZON.KendraSearchIntent is available only in the English (US) (en-US) locale and in the US East (N. Virginia), US West (Oregon) and Europe (Ireland) Regions.

Amazon Kendra is a machine-learning-based search service that indexes natural language documents such as PDF documents or Microsoft Word files. It can search indexed documents and return the following types of responses to a question:

An answer
An entry from a FAQ that might answer the question
A document that is related to the question

For an example of using the AMAZON.KendraSearchIntent, see Example: Creating a FAQ Bot for an Amazon Kendra Index.

If you configure an AMAZON.KendraSearchIntent intent for your bot, Amazon Lex V2 calls the intent whenever it can't determine the user utterance for an intent. If there is no response from Amazon Kendra, the conversation continues as configured in the bot.

Note

Amazon Lex V2 currently does not support the AMAZON.KendraSearchIntent during slot elicitation. If Amazon Lex V2 can't determine the user utterance for a slot, it calls the AMAZON.FallbackIntent.

When you use the AMAZON.KendraSearchIntent with the AMAZON.FallbackIntent in the same bot, Amazon Lex V2 uses the intents as follows:

Amazon Lex V2 calls the AMAZON.KendraSearchIntent. The intent calls the Amazon Kendra Query operation.
If Amazon Kendra returns a response, Amazon Lex V2 displays the result to the user.
If there is no response from Amazon Kendra, Amazon Lex V2 re-prompts the user. The next action depends on response from the user.
- If the response from the user contains an utterance that Amazon Lex V2 recognizes, such as filling a slot value or confirming an intent, the conversation with the user proceeds as configured for the bot.
- If the response from the user does not contain an utterance that Amazon Lex V2 recognizes, Amazon Lex V2 makes another call to the Query operation.
If there is no response after the configured number of retries, Amazon Lex V2 calls the AMAZON.FallbackIntent and ends the conversation with the user.

There are three ways to use the AMAZON.KendraSearchIntent to make a request to Amazon Kendra:

Let the search intent make the request for you. Amazon Lex V2 calls Amazon Kendra with the user's utterance as the search string. When you create the intent, you can define a query filter string that limits the number of responses that Amazon Kendra returns. Amazon Lex V2 uses the filter in the query request.
Add additional query parameters to the request to narrow the search results using your Lambda function. You add a kendraQueryFilterString field that contains Amazon Kendra query parameters to the delegate dialog action. When you add query parameters to the request with the Lambda function, they take precedence over the query filter that you defined when you created the intent.
Create a new query using the Lambda function. You can create a complete Amazon Kendra query request that Amazon Lex V2 sends. You specify the query in the kendraQueryRequestPayload field in the delegate dialog action. The kendraQueryRequestPayload field takes precedence over the kendraQueryFilterString field.

To specify the queryFilterString parameter when you create a bot, or to specify the kendraQueryFilterString field when you call the delegate action in a dialog Lambda function, you specify a string that is used as the attribute filter for the Amazon Kendra query. If the string isn't a valid attribute filter, you'll get an InvalidBotConfigException exception at runtime. For more information about attribute filters, see Using document attributes to filter queries in the Amazon Kendra Developer Guide.

To have control over the query that Amazon Lex V2 sends to Amazon Kendra, you can specify a query in the kendraQueryRequestPayloadfield in your Lambda function. If the query isn't valid, Amazon Lex V2 returns an InvalidLambdaResponseException exception. For more information, see the Query operation in the Amazon Kendra Developer Guide.

For an example of how to use the AMAZON.KendraSearchIntent, see Example: Creating a FAQ Bot for an Amazon Kendra Index.

IAM Policy for Amazon Kendra Search

To use the AMAZON.KendraSearchIntent intent, you must use a role that provides AWS Identity and Access Management (IAM) policies that enable Amazon Lex V2 to assume a runtime role that has permission to call the Amazon Kendra Query intent. The IAM settings that you use depend on whether you create the AMAZON.KendraSearchIntent using the Amazon Lex V2 console, or using an AWS SDK or the AWS Command Line Interface (AWS CLI). When you use the console, you can choose between adding permission to call Amazon Kendra to the Amazon Lex V2 service-linked role or using a role specifically for calling the Amazon Kendra Query operation. When you use the AWS CLI or an SDK to create the intent, you must use a role specifically for calling the Query operation.

Attaching Permissions

You can use the console to attach permissions to access the Amazon Kendra Query operation to the default Amazon Lex V2 service-linked role. When you attach permissions to the service-linked role, you don't have to create and manage a runtime role specifically to connect to the Amazon Kendra index.

The user, role, or group that you use to access the Amazon Lex V2 console must have permissions to manage role policies. Attach the following IAM policy to the console access role. When you grant these permissions, the role has permissions to change the existing service-linked role policy.


{
"Version": "2012-10-17",
"Statement": [
    {
        "Effect": "Allow",
        "Action": [
            "iam:AttachRolePolicy",
            "iam:PutRolePolicy",
            "iam:GetRolePolicy"
        ],
        "Resource": "arn:aws:iam::*:role/aws-service-role/lexv2.amazonaws.com/AWSServiceRoleForLexBots*"
    },
    {
        "Effect": "Allow",
        "Action": "iam:ListRoles",
        "Resource": "*"
    }
]
}

Specifying a Role

You can use the console, the AWS CLI, or the API to specify a runtime role to use when calling the Amazon Kendra Query operation.

The user, role, or group that you use to specify the runtime role must have the iam:PassRole permission. The following policy defines the permission. You can use the iam:AssociatedResourceArn and iam:PassedToService condition context keys to further limit the scope of the permissions. For more information, see IAM and AWS STS Condition Context Keys in the AWS Identity and Access Management User Guide.


{
"Version": "2012-10-17",
"Statement": [
    {
        "Effect": "Allow",
        "Action": "iam:PassRole",
        "Resource": "arn:aws:iam::account:role/role"
    }
]
}

The runtime role that Amazon Lex V2 needs to use to call Amazon Kendra must have the kendra:Query permissions. When you use an existing IAM role for permission to call the Amazon Kendra Query operation, the role must have the following policy attached.

You can use the IAM console, the IAM API, or the AWS CLI to create a policy and attach it to a role. These instructions use the AWS CLI to create the role and policies.

Note

The following code is formatted for Linux and MacOS. For Windows, replace the Linux line continuation character (\) with a caret (^).

To add Query operation permission to a role

Create a document called KendraQueryPolicy.json in the current directory, add the following code to it, and save it


{
"Version": "2012-10-17",
"Statement": [
    {
        "Effect": "Allow",
        "Action": [
            "kendra:Query"
        ],
        "Resource": [
            "arn:aws:kendra:region:account:index/index ID"
        ]
    }
]
}

In the AWS CLI, run the following command to create the IAM policy for running the Amazon Kendra Query operation.
```
aws iam create-policy \
--policy-name query-policy-name \
--policy-document file://KendraQueryPolicy.json
```

Attach the policy to the IAM role that you are using to call the Query operation.


aws iam attach-role-policy \
--policy-arn arn:aws:iam::account-id:policy/query-policy-name
--role-name role-name

You can choose to update the Amazon Lex V2 service-linked role or to use a role that you created when you create the AMAZON.KendraSearchIntent for your bot. The following procedure shows how to choose the IAM role to use.

To specify the runtime role for AMAZON.KendraSearchIntent

Sign in to the AWS Management Console and open the Amazon Lex console at https://console.aws.amazon.com/lex/.
Choose the bot that you want to add the AMAZON.KendraSearchIntent to.
Choose the plus (+) next to Intents.
In Add intent, choose Search existing intents.
In Search intents, enter AMAZON.KendraSearchIntent and then choose Add.
In Copy built-in intent, enter a name for the intent, such as KendraSearchIntent, and then choose Add.
Open the Amazon Kendra query section.
For IAM role choose one of the following options:
- To update the Amazon Lex V2 service-linked role to enable your bot to query Amazon Kendra indexes, choose Add Amazon Kendra permissions.
- To use a role that has permission to call the Amazon Kendra Query operation, choose Use an existing role.

To filter the response from Amazon Kendra to items related to current conversation, use session and request attributes as filters by adding the queryFilterString parameter when you create your bot. You specify a placeholder for the attribute when you create the intent, and then Amazon Lex V2 substitutes a value before it calls Amazon Kendra. For more information about request attributes, see Setting request attributes for your Lex V2 bot. For more information about session attributes, see Setting session attributes for your Lex V2 bot.

The following is a example of a queryFilterString parameter that uses a string to filter the Amazon Kendra query.


"{"equalsTo": {"key": "City", "value": {"stringValue": "Seattle"}}}"

The following is an example of a queryFilterString parameter that uses a session attribute called "SourceURI" to filter the Amazon Kendra query.


"{"equalsTo": {"key": "SourceURI","value": {"stringValue": "[FileURL]"}}}"

The following is an example of a queryFilterString parameter that uses a request attribute called "DepartmentName" to filter the Amazon Kendra query.


"{"equalsTo": {"key": "Department","value": {"stringValue": "((DepartmentName))"}}}"

The AMAZON.KendraSearchInteng filters use the same format as the Amazon Kendra search filters. For more information, see Using document attributes to filter search results in the Amazon Kendra developer guide.

The query filter string used with the AMAZON.KendraSearchIntent must use lower-case letters for the first letter of each filter. For example, the following is a valid query filter for the AMAZON.KendraSearchIntent.


{
"andAllFilters": [
    {
        "equalsTo": {
            "key": "City",
            "value": {
                "stringValue": "Seattle"
            }
        }
    },
    {
        "equalsTo": {
            "key": "State",
            "value": {
                "stringValue": "Washington"
            }
        }
    }
]
}

Using the Search Response

Amazon Kendra returns the response to a search in a response from the intent's IntentClosingSetting statement. The intent must have a closingResponse statement unless a Lambda function produces a closing response message.

Amazon Kendra has five types of responses.

The following two responses require an FAQ to be set up for your Amazon Kendra index. For more details, see Adding questions and answers directly to a index.
- x-amz-lex:kendra-search-response-question_answer-question-<N> – The question from a FAQ that matches the search.
- x-amz-lex:kendra-search-response-question_answer-answer-<N> – The answer from a FAQ that matches the search.
The following three responses require a data source to be set up for your Amazon Kendra index. For more details, see Creating a data source.
- x-amz-lex:kendra-search-response-document-<N> – An excerpt from a document in the index that is related to the text of the utterance.
- x-amz-lex:kendra-search-response-document-link-<N> – The URL of a document in the index that is related to the text of the utterance.
- x-amz-lex:kendra-search-response-answer-<N> – An excerpt from a document in the index that answers the question.

The responses are returned in request attributes. There can be up to five responses for each attribute, numbered 1 through 5. For more information about responses, see Types of response in the Amazon Kendra Developer Guide.

The closingResponse statement must have one or more message groups. Each message group contains one or more messages. Each message can contain one or more placeholder variables that are replaced by request attributes in the response from Amazon Kendra. There must be at least one message in the message group where all of the variables in the message are replaced by request attribute values in the runtime response, or there must be a message in the group with no placeholder variables. The request attributes are set off with double parentheses ("((" "))"). The following message group messages match any response from Amazon Kendra:

“I found a FAQ question for you: ((x-amz-lex:kendra-search-response-question_answer-question-1)), and the answer is ((x-amz-lex:kendra-search-response-question_answer-answer-1))”
“I found an excerpt from a helpful document: ((x-amz-lex:kendra-search-response-document-1))”
“I think the answer to your questions is ((x-amz-lex:kendra-search-response-answer-1))”

Using a Lambda Function to Manage the Request and Response

The AMAZON.KendraSearchIntent intent can use your dialog code hook and fulfillment code hook to manage the request to Amazon Kendra and the response. Use the dialog code hook Lambda function when you want to modify the query that you send to Amazon Kendra, and the fulfillment code hook Lambda function when you want to modify the response.

Creating a Query with the Dialog Code Hook

You can use the dialog code hook to create a query to send to Amazon Kendra. Using the dialog code hook is optional. If you don't specify a dialog code hook, Amazon Lex V2 constructs a query from the user utterance and uses the queryFilterString that you provided when you configured the intent, if you provided one.

You can use two fields in the dialog code hook response to modify the request to Amazon Kendra:

kendraQueryFilterString – Use this string to specify attribute filters for the Amazon Kendra request. You can filter the query using any of the index fields defined in your index. For the structure of the filter string, see Using document attributes to filter queries in the Amazon Kendra Developer Guide. If the specified filter string isn't valid, you will get an InvalidLambdaResponseException exception. The kendraQueryFilterString string overrides any query string specified in the queryFilterString configured for the intent.
kendraQueryRequestPayload – Use this string to specify an Amazon Kendra query. Your query can use any of the features of Amazon Kendra. If you don't specify a valid query, you get a InvalidLambdaResponseException exception. For more information, see Query in the Amazon Kendra Developer Guide.

After you have created the filter or query string, you send the response to Amazon Lex V2 with the dialogAction field of the response set to delegate. Amazon Lex V2 sends the query to Amazon Kendra and then returns the query response to the fulfillment code hook.

Using the Fulfillment Code Hook for the Response

After Amazon Lex V2 sends a query to Amazon Kendra, the query response is returned to the AMAZON.KendraSearchIntent fulfillment Lambda function. The input event to the code hook contains the complete response from Amazon Kendra. The query data is in the same structure as the one returned by the Amazon Kendra Query operation. For more information, see Query response syntax in the Amazon Kendra Developer Guide.

The fulfillment code hook is optional. If one does not exist, or if the code hook doesn't return a message in the response, Amazon Lex V2 uses the closingResponse statement for responses.

Warning Javascript is disabled or is unavailable in your browser.

To use the Amazon Web Services Documentation, Javascript must be enabled. Please refer to your browser's Help pages for instructions.

Document Conventions

AMAZON.HelpIntent

Example: Creating a FAQ Bot for an Amazon Kendra Index