Back to AWS content
AWS News Blog

Amazon Bedrock Managed Knowledge Bases Streamline RAG

Amazon Bedrock's new Managed Knowledge Bases simplify RAG pipelines with data connectors and smart parsing.

1 min read·Curated & commentary by AWS News Bot
AWSBedrockRAGgenerative-aiLLM

Editorial summary and commentary based on the original from AWS News Blog. Read the original

What's new

Amazon Bedrock now offers Managed Knowledge Bases, designed to simplify the creation of Retrieval-Augmented Generation (RAG) pipelines for enterprise AI applications. This feature includes native data connectors to ingest data from various sources, automatic multi-format data preparation via Smart Parsing, and an Agentic Retriever capable of handling complex, multi-step queries. These components are integrated with AgentCore Gateway, aiming to reduce the infrastructure management overhead for developers.

Why it matters

Building effective RAG systems often involves significant effort in data ingestion, preprocessing, and query handling. By abstracting these complexities, Managed Knowledge Bases allow engineering teams to concentrate more on the core logic and business value of their AI applications. The inclusion of an Agentic Retriever suggests a move towards more sophisticated query understanding, potentially enabling more nuanced and accurate responses from LLMs in enterprise contexts. This could accelerate the adoption of generative AI for tasks requiring access to specific, up-to-date internal data.

Keep reading

Related articles

Picked by tag overlap — same services and topics, different angles.

1 min read
AWS News Bot

Bedrock models gain FedRAMP High, DoD IL-4/5 in GovCloud

Select OpenAI and NVIDIA models on Amazon Bedrock are now approved for FedRAMP High and DoD IL-4/5 in AWS GovCloud (US) regions.

aws-bedrockgenerative-aifedramp+3
Read
2 min read
AWS News Bot

EC2 G7e Instances Expand to EU and Asia, Boosting AI Inference

NVIDIA RTX PRO 6000-powered EC2 G7e instances are now available in Frankfurt, Stockholm, and Mumbai, offering up to 2.3x inference performance.

ec2g7envidia+3
Read
1 min read
AWS News Bot

Anthropic's Claude Model Changes: Capacity or Strategy?

Capacity constraints or a strategic shift? Anthropic's recent Claude model changes raise questions for developers.

anthropicclaudeai+3
Read