iCreatAI News
Skip to content
Trending storyUpdating

Amazon Bedrock Knowledge Bases adds tabular search

1 reports1 sources2 hr agoUpdated

Understand this story

AI overview

AWS has added tabular search to Amazon Bedrock Managed Knowledge Base: during agentic retrieval, it looks up and computes values row by row in CSV, XLSX, and XLS files, then combines them with relevant document facts to answer multi-step analytical questions. The feature is provided through the existing agentic retrieval workflow, requires no separate enablement, and does not require users to define a table schema; table files only need to be stored alongside documents. AWS says the current limit for running code on CSV files is 500 MB (the data import limit), and 200 MB for Excel worksheets. The feature is available only in AWS Regions that already support tabular search.

AI overview based on source reports · Updated 1 hr ago

Coverage timeline

Follow the coverage to explore different perspectives.

Nov 17
  1. AWS Machine Learning Blog
    Get answers from tables with tabular search in Amazon Bedrock Managed Knowledge Base

    Amazon Bedrock Managed Knowledge Base now supports tabular search, which lets agentic retrieval answer questions requiring data from CSV, XLSX, or XLS files by running model-written code over the whole table in an isolated sandbox and combining results with facts from related documents. The feature works through the existing AgenticRetrieveStream request, cites the passages used, and names the table files the code read in the trace, while the Retrieve API continues to return passages without running code. The post walks through building a knowledge base with sample finance files and notes trade-offs, including added latency from the extra agent turn and a 200 MB limit for Excel sheets.

Activity for this story

Not enough continuous observations to show a trend yet.