{"version":1,"type":"story","url":"https://digestai.news/story/amazon-bedrock-adds-agentic-retrieval-to-managed-knowledge-bases","json":"https://digestai.news/story/amazon-bedrock-adds-agentic-retrieval-to-managed-knowledge-bases.json","markdown":"https://digestai.news/story/amazon-bedrock-adds-agentic-retrieval-to-managed-knowledge-bases.md","slug":"amazon-bedrock-adds-agentic-retrieval-to-managed-knowledge-bases","headline":"Amazon Bedrock adds agentic retrieval to managed knowledge bases","summary":"Amazon Bedrock now offers agentic retrieval for its managed knowledge bases, letting developers break complex queries into sub‑queries, evaluate evidence, and re‑search if needed. The AWS Machine Learning Blog walks through using LangChain and the langchain‑aws package to call either the standard Retrieve API or the AgenticRetrieveStream API.\n\nThe tutorial covers prerequisites such as an AWS account with Bedrock access, IAM roles for the knowledge‑base service and API caller, and an S3 bucket for documents. It explains how to create a knowledge base, ingest data, and query it with both retrieval paths, including cost considerations. Agentic retrieval improves recall on the MuSiQue multi‑hop benchmark, especially for hard questions, and supports guardrails in BLOCK mode.\n\nPractical guidance is provided: use standard retrieval for single‑intent questions to keep latency low and costs down; use agentic retrieval for multi‑part queries to get more accurate answers. The post also shows how to read trace events, handle scoring differences, and tune the maxAgentIteration parameter. The feature is available in us‑east‑1 and other Bedrock‑managed‑knowledge‑base regions.","keyPoints":["Amazon Bedrock Managed Knowledge Base now supports agentic retrieval via AgenticRetrieveStream API","LangChain’s langchain‑aws package exposes both standard and agentic retrieval functions","Agentic retrieval improves recall on MuSiQue, especially for hardest multi‑hop questions"],"whyItMatters":"The new agentic retrieval lets developers build RAG systems that decompose complex queries, reducing manual prompt engineering and improving answer quality for enterprise applications.","category":{"slug":"agents","name":"Agents & Tools","url":"https://digestai.news/category/agents"},"entities":{"companies":["Amazon","LangChain"],"models":[],"people":[]},"firstPublishedAt":"2026-10-05T15:53:56Z","updatedAt":"2026-10-05T15:53:56Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"AWS Machine Learning Blog","title":"Agentic retrieval with LangChain and Amazon Bedrock Knowledge Bases","url":"https://aws.amazon.com/blogs/machine-learning/agentic-retrieval-with-langchain-and-amazon-bedrock-knowledge-bases","publishedAt":"2026-10-05T15:53:56Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":{"title":"Amazon Builds Comprehensive AI Agent Infrastructure","url":"https://digestai.news/thread/amazon-expands-seller-assistant-from-chatbot-to-operating-system-for-merchants","storyCount":4},"cite":{"text":"Digest AI, \"Amazon Bedrock adds agentic retrieval to managed knowledge bases\", 5 October 2026, https://digestai.news/story/amazon-bedrock-adds-agentic-retrieval-to-managed-knowledge-bases","publisher":"Digest AI","title":"Amazon Bedrock adds agentic retrieval to managed knowledge bases","datePublished":"2026-10-05T15:53:56Z","url":"https://digestai.news/story/amazon-bedrock-adds-agentic-retrieval-to-managed-knowledge-bases"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}