{
  "schema_version": 2,
  "id": "integrate/amazon-bedrock/create-knowledge-base",
  "title": "Create a Bedrock knowledge base",
  "url": "https://redis.io/docs/latest/integrate/amazon-bedrock/create-knowledge-base/",
  "summary": "Shows how to set up your Knowledge base in Amazon Bedrock.",
  "aliases": [
    "/integrate/aws-bedrock/create-knowledge-base/"
  ],
  "tags": [
    "docs",
    "integrate",
    "oss",
    "rs",
    "rc"
  ],
  "last_updated": "2026-10-02T14:54:03+01:00",
  "page_type": "content",
  "content_hash": "0aff1b57b05a365d6897aebe7588dd92f4b82a6905f71ef554d1bbc8c460e51b",
  "sections": [
    {
      "id": "overview",
      "title": "Overview",
      "role": "overview",
      "text": "After you have set up a vector database with Redis Cloud, you can use it to create a knowledge base for your models.\n\nBefore you begin this guide, you will need:\n\n- An [AWS S3 Bucket](https://docs.aws.amazon.com/AmazonS3/latest/userguide/creating-buckets-s3.html) with text data that you want to use to train your models.\n\n- An [AWS IAM Role](https://docs.aws.amazon.com/IAM/latest/UserGuide/id_roles_create_for-service.html) with permissions for the Bedrock knowledge base.\n\n- A Redis database that is [set up for Amazon Bedrock](https://redis.io/docs/latest/integrate/amazon-bedrock/set-up-redis)"
    },
    {
      "id": "create-knowledge-base",
      "title": "Create knowledge base",
      "role": "content",
      "text": "To use your Redis database to create a knowledge base on Amazon Bedrock:\n\n1. Sign in to the [AWS console](https://console.aws.amazon.com/). \n\n1. Use the **Services** menu to locate and select **Machine Learning** > **Amazon Bedrock**.  This takes you to the Amazon Bedrock admin panel.\n\n1. Select **Knowledge base** > **Create knowledge base** to create your knowledge base.\n\n    ![The Create knowledge base button.](https://redis.io/docs/latest/images/rc/bedrock-aws-button-create-knowledge-base.png)\n\n1. In the **Knowledge base details** section, enter a name and description for your knowledge base. \n\n1. Select the IAM role for the Bedrock knowledge base in the **IAM Permissions** section. Select **Next** to add the data source.\n\n1. Enter a name for the data source and connect your S3 bucket in the **Data source** section.\n\n1. In the **Vector database** section, select **Redis Cloud** and select the checkbox to agree with the legal disclaimer.\n\n    ![The Redis Cloud selection for your vector database.](https://redis.io/docs/latest/images/rc/bedrock-aws-select-redis-vector-db.png)\n\n    Fill in the fields with the following information:\n\n    - **Endpoint URL**: Public endpoint of your database. This can be found in the [Redis Cloud console](https://cloud.redis.io/) from the database list or from the **General** section of the **Configuration** tab for the source database.\n    - **Credentials Secret ARN**: [Amazon Resource Name (ARN)](https://docs.aws.amazon.com/secretsmanager/latest/userguide/reference_iam-permissions.html#iam-resources) of your [database credentials secret](https://redis.io/docs/latest/integrate/amazon-bedrock/set-up-redis#store-secret).\n    - **Vector Index name**: Name of the [vector index](https://redis.io/docs/latest/integrate/amazon-bedrock/set-up-redis#create-vector-index) \n    - **Vector field**: Name of the [vector field](https://redis.io/docs/latest/integrate/amazon-bedrock/set-up-redis#create-vector-index) of the vector index\n    - **Text field**: Name of the [text field](https://redis.io/docs/latest/integrate/amazon-bedrock/set-up-redis#create-vector-index) of the vector index\n    - **Metadata field**: Name of the [metadata field](https://redis.io/docs/latest/integrate/amazon-bedrock/set-up-redis#create-vector-index) of the vector index\n\n    Select **Next** to review your settings.\n\n1. Review your knowledge base before you create it. Select **Create knowledge base** to finish creation.\n\n    ![The Create knowledge base button.](https://redis.io/docs/latest/images/rc/bedrock-aws-button-create-knowledge-base.png)\n\nAmazon Bedrock will sync the data from the S3 bucket and load it into your Redis database. This will take some time.\n\nYour knowledge base will have a status of **Ready** when it is ready to be connected to an Agent.\n\n![A Bedrock knowledge base with a Ready status.](https://redis.io/docs/latest/images/rc/bedrock-aws-status-knowledge-base-ready.png)\n\nSelect the name of your knowledge base to view the syncing status of your data sources. The data source will have a status of **Ready** when it is synced to the vector database.\n\n![A Bedrock data source with a Ready status.](https://redis.io/docs/latest/images/rc/bedrock-aws-status-data-source-ready.png)\n\nAfter the knowledge base is ready, you can use it to [Create an agent](https://redis.io/docs/latest/integrate/amazon-bedrock/create-agent)."
    }
  ],
  "examples": []
}