skills.rest
aurainfosec
aurainfosecOFFICIAL
Explore all skills by this author →
WebsiteGitHub

bedrock

Invoke AWS Bedrock foundation models for text generation and embeddings.

Updated Feb 16, 2026
Search Tags:#embeddings#rag#streaming#aws bedrock#foundation models#iam permissions#invoke model
One-click install
npx skills add https://github.com/aurainfosec/cloud-review-automation-poc --skill bedrock-aurainfosec
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: bedrock
Source: https://github.com/aurainfosec/cloud-review-automation-poc/tree/main/skills/bedrock
Command: npx skills add https://github.com/aurainfosec/cloud-review-automation-poc --skill bedrock-aurainfosec

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Amazon Bedrock solves the problem of building generative AI capabilities by providing a unified way to access foundation models without managing model hosting yourself.

Core Features & Use Cases

  • Foundation model invocation: Generate text and perform multi-turn conversations using Bedrock runtime APIs, including streaming responses for better UX.
  • Embeddings for RAG and search: Create vector embeddings (e.g., Titan embeddings) to power semantic search, retrieval, and downstream analytics.
  • RAG and knowledge-base workflows: Use Bedrock Agent Runtime retrieval and retrieve-and-generate patterns to answer questions grounded in your knowledge bases.
  • Model access and capacity options: Discover models, check agreement/access status, and use provisioned throughput or batch inference for cost/performance tuning.

Quick Start

Invoke the Anthropic Claude model to explain AWS Lambda in 3 sentences using the bedrock-runtime invoke-model API with the model id anthropic.claude-3-sonnet-20240229-v1:0 and an input messages payload.

Frequently Asked Questions about bedrock

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

FAQPage Schema
How do I invoke AWS Bedrock foundation models for text generation?▼

To invoke AWS Bedrock foundation models for text generation, use the bedrock-runtime invoke-model API with a specific model identifier and a correctly formed input messages payload. Both synchronous and streaming inference are supported.

How do I generate vector embeddings for RAG and semantic search using AWS Bedrock?▼

You generate vector embeddings for RAG and semantic search using AWS Bedrock by invoking supported embeddings models like Titan through the runtime API. These embeddings power retrieval-augmented generation and downstream analytics.

What IAM permissions are required to use AWS Bedrock runtime APIs?▼

Using AWS Bedrock runtime APIs requires correct IAM permissions for both control-plane and runtime API access. You need authorization to discover models, check agreement status, invoke models, and access retrieval operations.

Can I use AWS Bedrock for retrieval-augmented generation grounded in my own knowledge bases?▼

Yes, you can use AWS Bedrock for retrieval-augmented generation grounded in your knowledge bases. The Bedrock Agent Runtime supports retrieve-and-generate patterns to answer questions using your specific data.

Does AWS Bedrock support streaming responses for generative AI applications?▼

AWS Bedrock supports streaming responses for generative AI applications via the invoke-model API. Streaming inference allows you to process text generation outputs progressively, improving user experience.

What is the best way to tune AWS Bedrock model access for cost and performance?▼

The best way to tune AWS Bedrock model access for cost and performance is by using provisioned throughput or batch inference options. You can discover available models and check agreement access status via control-plane APIs.

Related Skills

Explore More Software Engineering Skills→
s1366560s1366560
5

bedrock

Invoke AWS Bedrock foundation models for text, embeddings, and image generation.

Community
Intermediate
jhl-labsjhl-labs
50

RAG & Vector Search

Retrieve relevant documents and augment LLM prompts with vector search.

Official
Advanced
nesihaver-ILnesihaver-IL

aws-agentcore

Build production-grade AI agents on AWS with AgentCore components.

Community
Intermediate
oborchersoborchers
28

managed-services-over-self-hosted

Compare managed and self-hosted services using decision frameworks for small teams.

Community
Intermediate