Amazon Bedrock Launches Managed Knowledge Base for RAG

Daniel Abib· June 17, 2026 View original

Summary

Amazon Bedrock introduces a new Fully Managed Knowledge Base to simplify the creation of enterprise Retrieval Augmented Generation (RAG) pipelines. It offers native data connectors, Smart Parsing for multi-format data, and an Agentic Retriever for complex queries, all integrated with AgentCore Gateway, allowing developers to focus on business outcomes.

Amazon Bedrock has unveiled a new Fully Managed Knowledge Base, a significant addition aimed at streamlining the development of enterprise-grade Retrieval Augmented Generation (RAG) pipelines. This new service is designed to abstract away much of the underlying infrastructure management, allowing developers to concentrate more on achieving specific business objectives. The Managed Knowledge Base comes equipped with several key features, including native data connectors for seamless integration with various data sources. It also incorporates Smart Parsing technology, which automatically prepares data from multiple formats, and an advanced Agentic Retriever capable of handling complex, multi-step queries. All these components are tightly integrated with AgentCore Gateway, providing a cohesive environment for building more accurate and efficient AI applications.

Why it matters

This launch significantly simplifies the development of RAG-based AI applications, which are crucial for enterprises needing accurate, context-aware AI. Professionals can build more sophisticated AI solutions faster and with less operational overhead.

How to implement this in your domain

  1. 1Evaluate the new Managed Knowledge Base for building or enhancing RAG pipelines.
  2. 2Utilize native data connectors to integrate enterprise data sources efficiently.
  3. 3Leverage Smart Parsing for automated preparation of diverse data formats.
  4. 4Experiment with the Agentic Retriever for handling complex, multi-step queries in AI agents.

Who benefits

Enterprise ITAI DevelopmentData ManagementCustomer ServiceLegal

Key takeaways

  • Amazon Bedrock introduces a Fully Managed Knowledge Base for RAG pipelines.
  • It simplifies enterprise AI application development by handling infrastructure.
  • Features include native connectors, Smart Parsing, and an Agentic Retriever.
  • Integration with AgentCore Gateway allows focus on business outcomes.

Original post by Daniel Abib

"Amazon Bedrock's new Fully Managed Knowledge Bases simplifies building enterprise RAG pipelines by providing native data connectors Smart Parsing for automatic multi-format data preparation, and an Agentic Retriever for complex multi-step queries—all integrated with AgentCore Gat…"

View on X

Originally posted by Daniel Abib on X · view source

Want to go deeper?

Turn these trends into skills with Learnijoy's hands-on AI & tech courses.

Explore courses