Google Cloud · Agentic Architect
RAG pipelines and vector retrieval
Agentic Architect · Lesson 8 of 16 · 1:05:43
YouTube loads only after you press play. This chapter opens at its timestamp in the full course. Watch on YouTube ↗
In this lesson
Prepare for the Google Cloud Professional Agentic Architect exam, on the official exam guide. In this lesson: the RAG pipeline (chunking, embeddings, retrieval), vector databases, hybrid search and reranking, and Agent Retrieval. Includes three original practice questions.
Preview the topics
- Cymbal Air’s corpus has grown to tens of millions of chunks in RagManagedDb, and retrieval latency keeps rising with every import. What should the team change?
- Mechanics search for exact part numbers, like A320-27, and the dense vector search keeps returning passages about similar parts instead. What should the team add?
- Cymbal Air wants a search engine for its agents where embeddings are generated automatically for each new record, with hybrid search and reranking, and no pipeline to maintain. What fits best?