Amazon Bedrock has launched a fully managed agentic retrieval solution called Managed Knowledge Base, designed to simplify the creation of enterprise search systems for agents and generative AI applications. This service handles scaling, high-accuracy retrieval, and document access control automatically, allowing users to connect their enterprise data sources or crawl the web to start ingesting data. Getting started through the AWS Management Console requires no model selection, with sensible defaults enabling users to create their first retrieval in minutes, compared to the days or weeks typically needed to assemble a comparable pipeline from scratch. The service also allows customization of embedding models, rerankers, chunking strategies, and more. In this post, we walk through the three pillars that make this possible: simplified setup, smarter retrieval, and production readiness. We also show you code examples for setting up a knowledge base and retrieving from it.
Managed Knowledge Base abstracts the complexity of building data ingestion pipelines, vector or graph storage, and retrieval infrastructure. Users configure a knowledge base, and the service handles everything downstream, from ingesting enterprise data through native connectors to managing vector stores on their behalf. It includes six native connectors for sources like Amazon S3, Microsoft SharePoint, Atlassian Confluence, Google Drive, Microsoft OneDrive, and a Web Crawler. The service also includes a direct ingestion API for documents not in supported sources. On subsequent syncs, it processes only modified or new documents, reducing time, cost, and staleness. Real-time access control list (ACL) checks are used as an additional layer of security on top of existing pre-retrieval ACL filtering. Pre-filtered documents are transient for the life of the API call and are not visible to large language models (LLMs) or users. This maintains current access controls by checking permissions directly with the authoritative source at query time, rather than relying on potentially stale or incorrectly mapped ACL data.
Syngenta Group uses Bedrock Managed Knowledge Bases to enable employees to create knowledge bases on demand, syncing data from SharePoint and Confluence for internal knowledge search and agentic RAG applications. – Jason Krohn, Head of Data and AI Technology MRH Trowe is using Bedrock Managed Knowledge Bases to power an internal AI Copilot that gives employees instant, grounded answers from across their corporate knowledge base — spanning thousands of documents in Confluence and SharePoint, in both English and German. With native connectors and built-in access controls, their teams can search across policies, client documentation, and operational content without building custom retrieval pipelines — accelerating how their employees access the knowledge they need to serve clients. – Dr. Malte Polley, Teamleader Data Analytics & AI
Source: awsml
