Using Aurora PostgreSQL as a Knowledge Base for Amazon Bedrock - Amazon Aurora
PrerequisitesPreparing Aurora PostgreSQL to be a Knowledge BaseCreating a knowledge base in the Bedrock console
Services or capabilities described in Amazon Web Services documentation might vary by Region. To see the differences applicable to the China Regions, see Getting Started with Amazon Web Services in China (PDF).

Using Aurora PostgreSQL as a Knowledge Base for Amazon Bedrock

From Aurora PostgreSQL 15.4, 14.9, 13.12, 12.16 versions, you can use the Aurora PostgreSQL DB cluster as a Knowledge Base for Amazon Bedrock. For more information, see Create a vector store in Amazon Aurora. A Knowledge Base automatically takes unstructured text data stored in a Amazon S3 bucket, converts it to text chunks and vectors, and stores it in a PostgreSQL database. With the generative AI applications, you can use Agents for Amazon Bedrock to query the data stored in the Knowledge Base and use the results of those queries to augment answers provided by foundational models. This workflow is called Retrieval Augmented Generation (RAG). For more information on RAG, see Retrieval Augmented Generation (RAG).

Prerequisites

Familiarize yourself with the following prerequisites to use Aurora PostgreSQL cluster as a Knowledge Base for Amazon Bedrock. At a high-level, you need to configure the following services for use with Bedrock:

Preparing Aurora PostgreSQL to be used as a Knowledge Base for Amazon Bedrock

You need to follow the steps below to create and configure an Aurora PostgreSQL DB cluster to use it as a Knowledge Base for Amazon Bedrock.

  1. Create an Aurora PostgreSQL DB cluster. For more information, see Creating and connecting to an Aurora PostgreSQL DB cluster

  2. Enable Data API while creating Aurora PostgreSQL DB cluster. For more information on the versions supported, see Using RDS Data API.

  3. Note the Aurora PostgreSQL DB cluster Amazon Resource Names (ARN) to use it in the Amazon Bedrock. For more information, see Amazon Resource Names (ARNs)

  4. Log in to the database with your master user and setup pgvector. Use the following command if the extension is not installed:

    CREATE EXTENSION IF NOT EXISTS vector;

    Use pgvector 0.5.0 and higher version that supports HNSW indexing. For more information, see pgvector v0.5.0 with HNSW indexing.

    Use the following command to check the version of the pg_vector installed:

    postgres=>SELECT extversion FROM pg_extension WHERE extname='vector';

  5. Create a specific schema that Bedrock can use to query the data. Use the following command to create a schema:

    CREATE SCHEMA bedrock_integration;

  6. Create a new role that Bedrock can use to query the database. Use the following command to create a new role:

    CREATE ROLE bedrock_user WITH PASSWORD password LOGIN;
    Note

    Make a note of this password as you would be using the same to create a Secrets Manager password.

  7. To grant the bedrock_user permission to manage the bedrock_integration schema, so they can create tables or indexes in it.

    GRANT ALL ON SCHEMA bedrock_integration to bedrock_user;

  8. Login as the bedrock_user and create a table in the bedrock_integration schema.

    CREATE TABLE bedrock_integration.bedrock_kb (id uuid PRIMARY KEY, embedding vector(1536), chunks text, metadata json);

  9. We recommend you to create an index with the cosine operator which the bedrock can use to query the data.

    CREATE INDEX on bedrock_integration.bedrock_kb USING hnsw (embedding vector_cosine_ops);

  10. Create an Amazon Secrets Manager database secret. For more information, see Amazon Secrets Manager database secret.

Creating a knowledge base in the Bedrock console

While preparing Aurora PostgreSQL to be used as the vector store for a Knowledge Base, gather the following details that you need to supply to Amazon Bedrock console.

  • Amazon Aurora DB cluster ARN

  • Secret ARN

  • Database name (e.g. postgres)

  • Table name - Advise to provide a schema qualified name, ie. CREATE TABLE bedrock_integration.bedrock_kb; which will create the bedrock_kb table in the bedrock_integration schema

  • Table fields:

    ID: (id)

    Text chunks (chunks)

    Vector embedding (embedding)

    Metadata (metadata)

With these details you can create a knowledge base in the Bedrock console. For more information, see Create a vector store in Amazon Aurora.

Once Aurora is added as a knowledge base, you ingest the data sources into it. For more information, see Ingest your data sources into the knowledge base.