BriefsToolAvailable now1 min read

Amazon Bedrock adds single-shot and retrieval-only modes to knowledge bases

Amazon Bedrock Managed Knowledge Base adds single-shot RAG and retrieval-only options via the AgenticRetrieveStream API with new iteration settings.

Amazon Bedrock adds single-shot and retrieval-only modes to knowledge bases — image from AWS
Image: AWS

Summary

Amazon Bedrock Managed Knowledge Base now supports single-shot retrieval-augmented generation and retrieval-only requests through the AgenticRetrieveStream API. By adjusting the maxAgentIteration parameter from 0 to 5, applications can choose between retrieval-only passages, single-shot RAG, or multi-step agentic retrieval. This lets developers balance speed, cost, and answer quality without maintaining separate code paths for simple and complex queries.

What changed

  • Amazon Bedrock Managed Knowledge Base now supports single-shot retrieval-augmented generation and retrieval-only requests through AgenticRetrieveStream .
  • The maxAgentIteration range is now 0-5.
  • Setting maxAgentIteration to 1 enables single-shot RAG with one retrieval and one answer.
  • Setting maxAgentIteration to 0 returns passages only with zero large language model calls.

Availability

Available now

“Amazon Bedrock Managed Knowledge Base now supports single-shot Retrieval Augmented Generation (RAG) and retrieval-only requests through AgenticRetrieveStream .”

Founder takeaway

Test your queries against the new 0 and 1 iteration settings in AgenticRetrieveStream to reduce latency and model usage on direct lookups while reserving agentic mode for complex multi-part questions.

Source

Researched and drafted with AI from the official sources above, then checked automatically before publishing. Spotted a mistake? Tell us.

SharePost on XLinkedIn

Related

More briefs

All briefs
  1. LangSmith adds coding agent reporting and outcome tracking — image from LangChain

    ToolBeta

    LangSmith adds coding agent reporting and outcome tracking

    LangChain updates LangSmith with new reporting features that link AI coding agent spend to GitHub pull requests and GitLab merge requests.

    LangChain1 min read

  2. Reson8 releases Rumble-2-Flash as an open 0.5B speech AI model — image from Hugging Face

    ToolAvailable now

    Reson8 releases Rumble-2-Flash as an open 0.5B speech AI model

    Reson8 released Rumble-2-Flash, an open 0.5B-parameter speech recognition AI model supporting over forty languages.

    Hugging Face1 min read

  3. NVIDIA releases RTX Spark compact desktops for local AI — image from NVIDIA

    ToolAvailable now

    NVIDIA releases RTX Spark compact desktops for local AI

    ASUS, Dell, and MSI launched new RTX Spark desktops to run local AI agents, generation, and model fine-tuning on Windows.

    NVIDIA1 min read

One email, every Monday

Briefs are published here through the day. Monday Heist is the email: one useful AI workflow, the files to use it, and the catch. The first issue is being prepared; subscribers get it first. Free, and you can leave in one click.

One email. Every Monday.