retrieve

Searches Amazon Bedrock RAG knowledge bases and returns matched content with source URLs and titles.

4|2|Updated Mar 9, 2026

Search Tags:#rag #search #knowledge base #retrieval #bedrock #document search

Ready to run

npx skills add https://github.com/kyopark2014/agent-plugins --skill retrieve-kyopark2014

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: retrieve
Source: https://github.com/kyopark2014/agent-plugins/tree/main/application/skills/retrieve
Command: npx skills add https://github.com/kyopark2014/agent-plugins --skill retrieve-kyopark2014

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires boto3, and includes scripts (resource) components.

What problem does it solve?

This Skill enables users to efficiently find information within a knowledge base by leveraging Amazon Bedrock's Retrieval-Augmented Generation (RAG) capabilities, eliminating the need to manually sift through documents.

Core Features & Use Cases

Knowledge Base Search: Query indexed documents using keywords.
RAG-based Retrieval: Utilizes vector search for relevant content.
Source Referencing: Provides URLs and titles for retrieved content.
Use Case: A user needs to understand cloud architecture best practices. They can use this Skill to query the knowledge base, and it will return relevant document chunks with links to the original sources.

Quick Start

Use the retrieve script to query the knowledge base for information about cloud architecture.

Frequently Asked Questions about retrieve

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I search an Amazon Bedrock knowledge base using RAG?▼

You can search an Amazon Bedrock knowledge base using RAG by querying indexed documents with keywords. The retrieval skill utilizes vector search to return matched content chunks alongside source URLs and titles for reference.

Can I retrieve specific content from web-crawled and S3 documents?▼

Yes, you can retrieve specific content from S3 and web-crawled documents. The RAG-based retrieval searches indexed knowledge base content, returning matched text chunks and providing links to the original web pages or stored S3 files for reference.

How does RAG retrieval work for finding information in a knowledge base?▼

RAG retrieval works by using vector search to find relevant content within an indexed knowledge base. When you query, it matches your search terms to stored document chunks, eliminating manual sifting and returning targeted results with source references.

Do I need boto3 to use this knowledge base retrieval skill?▼

Yes, you need the boto3 Python library installed as a dependency to use this knowledge base retrieval skill. It provides the necessary API interface to communicate with Amazon Bedrock and execute RAG-based search queries on your indexed documents.

What is the best way to query cloud architecture best practices from uploaded documents?▼

The best way to query cloud architecture best practices from uploaded documents is using a RAG-based knowledge base search. It retrieves relevant document chunks via vector search and returns them with URLs to the original sources, saving manual review time.