Designs

Company tags are community-reported. Counts on cards show how many people reported that design.

• 

  125. Design a Prompt and Semantic Cache for LLMs

  Exact, semantic and prefix caching in front of LLMs: scoped keys, distances with an error budget, tenant isolation, invalidation and measured savings.

  ClassicMedium

  CachingGenerative AIAI infrastructure

  +4

  AWSEmbeddingsLLMsRetrieval

  Worked design

  Practice
• 

  131. Design Retrieval-Augmented Generation

  Answers from private documents with citations: chunking, BM25 + vector retrieval, reranking, permission filters, grounding checks and evaluation.

  ClassicMedium

  Generative AIAWSLLMs

  +2

  RAGRetrieval

  Worked design

  Practice

Each design brings together the brief, practice, examples and discussion.