Amazon Bedrock

Before you begin

Before starting, you'll need:

• An AWS account.

• An AWS Identity and Access Management role with permissions for AWS Bedrock.

• Access to the Foundation Models you'll use.

Configure the AI integration

1. Click AI Platforms from the main menu.

2. Select AWS Bedrock.

AWS Bedrock Card

1. Enter the name, access key, secret key, and select your region using the AWS Bedrock Parameters table below as a guide, then click Create AWS Bedrock Integration.

AWS Bedrock Configuration

Amazon Bedrock Parameters

Field	Description	Required
Name	A descriptive name to identify the integration within Vectorize.	Yes
Access key	Your Amazon access key.	Yes
Secret key	Your Amazon secret key.	Yes
Region	The Amazon region to use.	Yes

Configuring the Amazon Bedrock integration in a RAG Pipeline

You can think of the Amazon Bedrock integration as having two parts to it. The first is authorization for your region. This part is re-usable across pipelines and allows you to connect to this same integration in different pipelines without providing the credentials and specifying the region every time.

The second part is the configuration that's specific to your RAG Pipeline, which allows you to specify which foundation model to use.

AWS Bedrock Configuration

What's next?

• If you haven't yet built a connector to your source database, go to configure a source connector and select your source data platform.

  OR

• If you're ready to start creating pipelines for vectorizing data, head to Pipeline Basics.