Amazon Bedrock Managed Knowledge Base now supports Confluence Data Center as a native data source connector

Amazon Bedrock Managed Knowledge Base

AWS introduces the Confluence Data Center data source connector for Amazon Bedrock Managed Knowledge Base, a fully managed retrieval-augmented generation (RAG) service. This new feature allows customers with self-hosted Confluence Data Center instances to crawl blogs and pages directly into their managed knowledge base.

Previously, integrating Confluence Data Center content into Bedrock Knowledge Bases required custom ingestion pipelines. Now, by providing your instance credentials, the connector automates data crawling, metadata extraction, and incremental sync.

The Confluence Data Center connector enables AI agents to access institutional knowledge maintained in Confluence, including wiki pages and blog posts across spaces. Filters can be applied to scope crawls to specific spaces or content types, ensuring only relevant content is ingested.

What to do

• Provide your Confluence Data Center instance credentials to the connector.
• Use filters to scope crawls to specific spaces or content types.
• Ensure your knowledge base remains focused and cost-efficient.

Source: AWS release notes

If you need further guidance on AWS, our experts are available at AWS@westloop.io. You may also reach us by submitting the Contact Us form.