Cianplan

Level 5: AI / LLM systems · L5.8 Generative AI on AWS: Bedrock in practice (AIP-C01)

RAG on AWS: Knowledge Bases and vector stores

Design a Bedrock knowledge base: data sources, chunking, embeddings, vector store, metadata filters, reranking and keeping the index current.

13 min · Pro

What you take away

  • Amazon Bedrock Knowledge Bases runs the L5.2 pipeline for you: parse, chunk, embed, store, retrieve, with sync jobs that re-ingest only what changed.

And 3 more inside the class, in Pro.

How the class is laid out

  1. The problem
  2. The simple version
  3. The L5.2 pipeline, managed
  4. Permissions are yours to carry
  5. Check your understanding