Termsslug: agentic-retrieval

Agentic Retrieval

智能体检索

Retrieval paradigm where the model orchestrates multi-step retrieval and memory injection instead of single-shot vector recall.

Curated Intelligence

6 items · Page 1/1
AWS Machine Learning BlogT1·Agents
58 pts
Amazon Bedrock Managed Knowledge Base Adds Agentic Retrieve for Memory-Aware Agents

Amazon Bedrock Managed Knowledge Base introduces Agentic Retrieve, adding user memory on top of document retrieval. The feature extracts durable facts from past conversations, selects those relevant to the current question, and injects them into the retrieval request with per-user and per-document isolation. It targets support assistants, in-product document chat, and internal policy assistants.

AWS Machine Learning BlogT1·Tools
58 pts
Amazon Bedrock Knowledge Base Adds Tabular Search for Agents

Amazon Bedrock Managed Knowledge Base now supports tabular search, letting agentic retrieval look up values and run calculations across rows in CSV, XLSX, and XLS files, then combine results with facts from related documents to answer multi-step analytical questions. The capability reuses the existing AgenticRetrieveStream request and works across mixed sources such as SharePoint and S3.

AWS Machine Learning BlogT1·Tools
48 pts
AWS Bedrock Agentic Retrieval with LangChain

Amazon Bedrock Knowledge Bases introduces 'agentic retrieval,' using a planner to decompose complex multi-dimensional questions into sub-queries to address intent loss in traditional single-vector RAG. Integrated with LangChain, this feature aims to improve coverage and accuracy for compound queries while comparing costs against standard retrieval.