Fundamentals of GenAI — AWS Certified AI Practitioner

Official references for this objective

• Amazon Web Services — What are Generative AI Models? - Generative AI Models Explained - AWS

  A model with a larger context window retains more of the previous conversation and provides more relevant responses.

• Amazon Web Services — What is Generative AI? - Gen AI Explained - AWS

  GANs work by training two neural networks in a competitive manner. The first network, known as the generator, generates fake data samples

• Amazon Web Services — The role of vector databases in generative AI applications | AWS Database Blog

  Used in this way, such vectors are referred to as embeddings

• Amazon Web Services — Prompt engineering concepts - Amazon Bedrock

  also known as few-shot prompting or in-context learning , where a shot corresponds to a paired example input and the desired output.

• Amazon Web Services — What are Foundation Models? - Foundation Models in Generative AI Explained - AWS

  the computational power required for foundation modeling has doubled every 3.4 months since 2012

• Amazon Web Services — What is Embedding? - Embeddings in Machine Learning Explained - AWS

  Embeddings reduce the number of dimensions by identifying commonalities and patterns between various features. This consequently reduces the computing resources and time required to process

• Amazon Web Services — Comparing Retrieval Augmented Generation and fine-tuning - AWS Prescriptive Guidance

  RAG allows you to build a question-answering system for your custom documents without fine-tuning. RAG can incorporate the latest documents in a few

• Amazon Web Services — Prompt engineering for foundation models - Amazon SageMaker AI

  If temperature=0 , the response is made up of only the highest probability words (greedy decoding)

• Amazon Web Services — Tailoring foundation models for your business needs: A comprehensive guide to RAG, fine-tuning, and hybrid approaches | Artificial Intelligence

  They can fine-tune the model every couple of months to keep it aligned with the company’s overall tone. Meanwhile, RAG can retrieve the latest product