genai-bedrock

Question 1

Foundation Models

Answer 1

Large-scale pre-trained AI models that can be adapted for various tasks. They form the basis of many generative AI applications.

Question 2

Amazon Bedrock

Answer 2

A fully managed service that provides API access to foundation models from AWS and third-party providers for building generative AI applications.

Question 3

Retrieval Augmented Generation (RAG)

Answer 3

A technique that enhances AI model responses by incorporating external knowledge sources improving accuracy and relevance of generated content.

Question 4

Prompt Engineering

Answer 4

The practice of crafting effective inputs for AI models to generate desired outputs including techniques like zero-shot few-shot and chain-of-thought prompting.

Question 5

Vector Databases

Answer 5

Specialized databases designed to efficiently store and retrieve high-dimensional vectors or embeddings crucial for semantic search and similarity comparisons in AI applications.

Question 6

Responsible AI

Answer 6

Practices and principles ensuring AI systems are ethical fair transparent and accountable addressing bias privacy and safety concerns.

Question 7

Amazon SageMaker

Answer 7

A fully managed machine learning platform for building training and deploying ML models at scale.

Question 8

AWS Shared Responsibility Model

Answer 8

A security model that defines the distribution of responsibilities for security and compliance between AWS and the customer in cloud environments.

Question 9

Generative AI

Answer 9

AI systems capable of creating new content such as text images audio and video based on training data and prompts.

Question 10

Fine-tuning

Answer 10

The process of adapting a pre-trained model to a specific task or domain by further training on a smaller specialized dataset.