Module 3 of 6Lesson 2 of 2~16 min
Understand embeddings and semantic search
Understanding semantic search helps a PM predict which questions the assistant will handle well and which it will miss. With no math, the lesson explains how embeddings match texts by meaning, which settings are product decisions, and which weaknesses to anticipate in the specs.
Lesson objective
By the end of this lesson, you will be able to explain how semantic search retrieves passages, list the product decisions it involves (model, number of passages, relevance threshold) and anticipate its weak spots.
Topics covered
- embeddings
- semantic search
- vector database
- relevance threshold
Where it fits
Chunk and index
How do documents become passages that retrieval can find?
Lessons in this module
- Choose a chunking strategy
- Understand embeddings and semantic search (this lesson)
What you will learn in the course
This lesson is part of the course Design a RAG architecture that fits your product
- Choose, for an information need, between long context, data injected by the application, RAG and fine-tuning, and justify the choice by volume, update frequency, access rights and cost.
- Specify the source inventory, exclusions, the metadata to capture and the document chunking strategy.
- Design retrieval: semantic, keyword or hybrid search, reranking, contextual retrieval, number of passages and relevance threshold.
- Specify the answer grounded in sources, how citations are displayed, how conflicting sources are handled and what happens when nothing is found.
- Specify access filtering before the model reads any passage, and index freshness (resync, deletions, versions).
- Build a set of 30 test questions that covers RAG failure modes and diagnose which stage caused a wrong answer.
- Estimate the cost items of a RAG system and choose between a hosted tool, a managed knowledge base, a vector database and a custom build.
Related courses
- Build an AI assistant for your productAdvanced · ~3 hr
- Evaluate an AI feature: test sets, metrics and LLM judgesAdvanced · ~3 hr
- Ship and monitor an AI feature in productionExpert · ~3 hr