Tech Meridian ← ENTITY INDEX
PROMY MERIDIAN RU

COMPANY · ENTITY #13724

Amazon Bedrock Managed Knowledge Base

Related event timeline, sources and context from the news index.

EVENT TIMELINE

5

COMPANIES · 1 SOURCE · AWS Machine Learning

Amazon Bedrock Managed Knowledge Base gains AgentCore memory integration via AgenticRetrieveStream

Amazon describes an opt-in integration that lets Bedrock Managed Knowledge Base use AgentCore memory as a retrieval source by adding a memoryConfiguration to AgenticRetrieveStream. The feature stores conversations, extracts durable facts, retrieves relevant per-user memory alongside document search (respecting ACLs), and saves turns back to memory; the post includes a multi-tenant sample using Cognito, S3 ACLs, and IAM controls.

6.0

COMPANIES · 1 SOURCE · AWS Machine Learning

Amazon Bedrock adds versioned retrieval instructions to customize tenant answers

Amazon Bedrock Managed Knowledge Base now supports managed, versioned retrieval instructions that let you define persona, answerFormat, retrievalGuidance, and answerPolicy so a single shared knowledge base can return tenant-specific answers. Instructions are created and reviewed (CreateRetrievalInstruction returns HTTP 202), can be versioned with CreateRetrievalInstructionVersion, activated to ACTIVE with a DRAFT pointer, and applied per request (requests default to DRAFT unless a version is named).

6.0

CODING · 1 SOURCE · AWS Machine Learning

Amazon Bedrock adds Managed Knowledge Base migration guide to Agent Toolkit

AWS added a knowledge base migration guide to the amazon-bedrock skill in the Agent Toolkit for AWS to help teams move from customer-managed vector stores to Amazon Bedrock Managed Knowledge Base. The guide lets a coding agent perform read-only discovery, produce a migration plan or IaC for a replacement knowledge base, and assist with creation and validation, while Managed Knowledge Base provides managed embeddings, a reranker, native connectors, ACL-aware ingestion, agentic retrieval, and AgentCore Gateway integration.

6.0

CODING · 1 SOURCE · AWS Machine Learning

Amazon outlines Crawl4AI workflow to prepare web content for Bedrock Knowledge Bases

AWS published a how‑to showing a sample workflow that uses the open‑source Crawl4AI crawler to generate Markdown plus metadata sidecars uploaded to Amazon S3 for ingestion by Amazon Bedrock Knowledge Bases. The post explains when to use the built‑in Bedrock Web Crawler versus Crawl4AI for targeted extraction, custom metadata, and boilerplate pruning, and links an aws‑samples repo with the implementation using EventBridge, ECS/Fargate, and S3.

6.0

CODING · 1 SOURCE · AWS Machine Learning

Amazon Bedrock Managed Knowledge Bases supports agentic retrieval; LangChain walkthrough

A technical walkthrough demonstrates using LangChain with Amazon Bedrock Managed Knowledge Bases to compare standard single-shot retrieval (Retrieve API) and multi-step agentic retrieval (AgenticRetrieveStream API). The post explains architecture, IAM permissions, boto3 version requirements (agentic_retrieve_stream requires boto3 >= 1.43.32), and trade-offs including cost and trace event inspection.

6.0