[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"cheat-sheet---en":3,"domain-info---en":3,"topic-info----en":3,"prev-aws-certified-ai-practitioner-foundation-model-applications-fm-application-design-retrieval-augmented-generation-en":4,"lesson-aws-certified-ai-practitioner-foundation-model-applications-fm-application-design-retrieval-augmented-generation-en":19,"next-aws-certified-ai-practitioner-foundation-model-applications-fm-application-design-retrieval-augmented-generation-en":30},null,{"locked":5,"reason":6,"meta":7,"item":3},true,"paywall",{"title":8,"description":9,"isFree":10,"estimatedMinutes":11,"difficulty":12,"learningObjectives":13},"Inference Parameters","Same prompt, same model, different answers: the inference parameters that control how a model chooses each token, when to reach for each one, and the settings that quietly break a feature.",false,18,"intermediate",[14,15,16,17,18],"Explain how a model chooses each token from a probability distribution","Describe what temperature, top-k, and top-p each do to that distribution","Distinguish reshaping the distribution from truncating it","Choose settings for a factual task versus a creative task","Identify what response length, penalties, and stop sequences control",{"locked":5,"reason":6,"meta":20,"item":3},{"title":21,"description":22,"isFree":10,"estimatedMinutes":23,"difficulty":12,"learningObjectives":24},"Retrieval Augmented Generation (RAG)","Give a model access to your private, current data without retraining it: how RAG retrieves relevant passages at query time, how Amazon Bedrock Knowledge Bases automates it, and where the boundary with fine-tuning sits.",20,[25,26,27,28,29],"Explain the problem RAG solves that a base model cannot","Describe the two phases of RAG: ingestion and retrieval at query time","Explain what Amazon Bedrock Knowledge Bases automates","Distinguish RAG from fine-tuning and from pasting everything into a long context window","Identify business applications where RAG is the right fit",{"locked":5,"reason":6,"meta":31,"item":3},{"title":32,"description":33,"isFree":10,"estimatedMinutes":34,"difficulty":12,"learningObjectives":35},"Vector Databases on AWS","The store that makes retrieval possible: what a vector database does, why RAG needs one, and the AWS services the exam expects you to name for holding embeddings.",16,[36,37,38,39],"Explain what a vector database stores and the search it performs","Explain why similarity search needs a purpose-built index at scale","Name the AWS services the exam lists for storing embeddings and match each to a fit","Choose a vector store based on an existing data stack"]