> For the complete documentation index, see [llms.txt](https://karini-ai.gitbook.io/karini-ai-documentation/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://karini-ai.gitbook.io/karini-ai-documentation/amazon-q-data-accessor-integration.md).

# Amazon Q Data Accessor Integration

### Overview

Karini AI integrates seamlessly with Amazon Q Business, enabling users to leverage the Amazon Q Index to build Agentic RAG applications. With this integration, you can build an agentic application using a variety of knowledgebases such as Amazon Q Index Retriever, Amazon Bedrock Knowledgebases and Karini’s Native Knowledgebase. The setup involves creating agent prompts, integrating them with Amazon Q Accessor Retriever tool, and publishing the final recipe for use in your chat application.

### Prerequisites

* An active AWS account.
* Amazon Q Business application created.
* IAM Identity Center (IDC) configured.
* Access to Karini AI platform.

To initiate the integration, ensure that your Amazon Q Business application is provisioned and configured.

### In the AWS Management Console

Create and configure an Amazon Q Business application by following the official [Amazon Q Business documentation](https://docs.aws.amazon.com/amazonq/latest/qbusiness-ug/setting-up.html).

After configuring Amazon Q Business, integrate it within Karini AI to enable intelligent agents with secure, context-aware data access.

*Note: Use your External Id from your Karini Organization page as Tenant Id while creating Karini AI Data Accessor in Amazon Q Business*

### In Karini AI

1. **Configure Agent Prompt** :Define the agent’s objective, query input, and execution parameters.
   * Navigate to **Prompt > Add New**.
   * Set the following:
     * **Name** (unique identifier)
     * **Task**: Agent
     * **Max State Updates**: 10 ( 3 default)
     * **Prompt**: Instruction defining the agent’s purpose
     * **Agent Input**: Sample query
     * Click **Save.**
   * After saving the prompt, the **Tool** tab will appear. 

<figure><img src="/files/IqKTZmBsrHpJtRWrNl3V" alt=""><figcaption></figcaption></figure>

2. **Add Amazon Q Accessor Retriever Tool**: Add the Amazon Q Accessor Retriever tool within the agent prompt.
   * In the **Tool Configuration** tab, set:
     * **Name**: Provide a unique identifier for the tool configuration.
     * **Description**: Add a brief summary that outlines the tool’s purpose and how it supports the agent's behavior.
     * **Tool Type**: Select **Amazon Q Accessor Retriever**.
     * **Application ID**: Enter the Amazon Q Business Application ID associated with your deployment.
     * **Retriever ID**: Enter the unique Amazon Q Business retriever ID.
     * **Application Region**: Specify the AWS region where the Amazon Q Business application is hosted.
     * **IDC Application ARN**: Provide the ARN for the IAM Identity Center (IDC) client integrated with Amazon Q Business.
     * **IDC Region**: Enter the AWS region where the IAM Identity Center is configured.
     * **Max Results**: Set the maximum number of results to be retrieved per query.
     * **Save** the configuration.
3. **Test and Publish:** Validate the agent’s performance across models and publish the optimal configuration.
   * Navigate to **Test and Compare**.
   * Evaluate responses across models.
   * Select the best-performing answer.
   * **Save** and **Publish** the prompt. &#x20;

{% hint style="info" %}
Note: Currently you will be unable to establish a connection to the Amazon Q Business application via prompt playground.
{% endhint %}

2. **Create Recipe**: Design the conversational workflow by linking agent logic with interaction nodes.
   * Go to **Recipes > Add New**.
   * Set **Runtime: Agent 2.0.**
   * Enter **Name** and **Description**.
   * Add and connect the following nodes:
     * **Chat Node** (enable Citations and Follow-up Questions)
     * **Start Node**
     * **Agent Node** (select published prompt)
     * **End Node**

* Click **Save**, then **Publish.**

&#x20;Refer to the [Karini AI Recipe Documentation](https://karini-ai.gitbook.io/karini-ai-documentation/recipes) for detailed flow guidance.

<figure><img src="/files/CyBYspeWFG4W8eDMwgsK" alt=""><figcaption></figcaption></figure>

5. **Export and Integrate with Copilot( Chat Assistant)**
   * Export the recipe for Copilot integration. Refer to the[ Export Recipe](https://app.gitbook.com/o/tlujIankJrglU1kO6KjI/s/7ZrVuiAUMyuYVvrK5KaB/~/changes/178/recipes/qna-recipe/export-recipe) documentation for interface design details.
   * Navigate to **Copilot.**
   * Click **Authorize Amazon Q Index button.**
     * The action redirects your **AWS OIDC Provider via AWS Console**.&#x20;

<figure><img src="/files/smvbIo9EC7KsT0gtbGE9" alt=""><figcaption></figcaption></figure>

Upon successful authentication, c**opilot** is fully configured to retrieve data from **Amazon Q Business** . Users can submit queries related to Amazon Q Business data, and Copilot will efficiently process the requests and return relevant results. Additionally, the system displays detailed source information, ensuring transparency and context for each response.&#x20;

Refer to detailed set up walkthrough in the following video.

{% embed url="<https://youtu.be/l7a111f0U2g>" %}

<br>