GuideBeginner
AI Semantics Guide
Understand how vectors, vector spaces, similarity metrics and semantic search work conceptually — the foundational knowledge that makes embeddings, vector databases and RAG possible. A rigorous yet accessible guide with zero math prerequisites and zero code.
- 56
- lessons
- 8
- modules
- English · Spanish
- available in
- Yes
- certificate
- Free
- access
Outcomes
What you'll be able to do
- Explain what vectors are geometrically (direction, magnitude, high dimensions) without formal math
- Understand vector spaces as "universes of meaning" where proximity equals similarity
- Calculate cosine similarity conceptually and know when to use each distance metric
- Design k-Nearest Neighbors search on paper and understand index trade-offs (HNSW, IVF)
- Compare keyword search vs semantic search with a practical decision matrix
- Diagram semantic search architectures (indexing pipeline, query pipeline, hybrid search)
- Explain why RAG works and why retrieval quality determines RAG quality
- Evaluate real-world use cases: Q&A systems, document search, code search, recommendations
Before you start
What you need to bring
It's for you if...
- AI Engineers who want deep conceptual understanding before implementing embeddings and RAG
- Developers who use vector databases and embeddings but don't fully understand the theory behind them
- Technical professionals transitioning into AI who need the mathematical intuition without the PhD
- Students in the AI Engineering Path between fundamentals and hands-on embedding implementation
- Anyone who wants to explain "how semantic search works" to their team with confidence
Requirements and materials
- AI Fundamentals Guide completed (what is an LLM, what is a transformer)
- Basic math: addition, subtraction, multiplication, square roots
- Basic geometry: Cartesian coordinates (x, y), 2D plane
- No linear algebra, no code, no ML experience required
Content
The syllabus, module by module
Open any of them to see its lessons.
- 1. Module Introduction: Vectors - The Foundation of Everything
- 2. What Is a Vector?
- 3. Vectors in 2D and 3D: Visualization and Coordinates
- 4. Vectors in High Dimensions: From 3D to 1536D
- 5. Basic Vector Operations
- 6. Why Vectors in AI: From Words to Geometry
- 7. Capstone Exercise: Mapping Concepts to Vectors
- 1. Module Introduction: Vector Spaces - The Universe of Meaning
- 2. What Is a Vector Space?
- 3. Bases and Dimensions: The Axes of the Universe
- 4. Subspaces and Projections: Regions and Visualization
- 5. Normalization and Transformations
- 6. Semantic Spaces in AI: How LLMs Organize Meaning
- 7. Capstone Exercise: Designing a Semantic Vector Space
- 1. Module Introduction: Similarity and Distance - Measuring Closeness in the Space
- 2. Euclidean Distance: The Straight Line
- 3. Manhattan Distance and Other Metrics
- 4. Cosine Similarity: The Key Metric for AI
- 5. Comparing the Metrics
- 6. Metrics in Semantic Search
- 7. Capstone Exercise: Computing and Comparing Metrics
- 1. Module Introduction: Proximity Search - Finding Nearest Neighbors
- 2. kNN Conceptually: The K Nearest Neighbors
- 3. Search Indexes: Exact vs Approximate
- 4. HNSW: Hierarchical Navigable Graphs
- 5. IVF: Inverted File Index and Clustering
- 6. Trade-offs and Decisions: Choosing the Right Index
- 7. Capstone Exercise: Designing a Search Strategy
- 1. Module Introduction: Keyword vs Semantic Search
- 2. Keyword Search: Traditional Search by Keywords
- 3. Semantic Search: Vector Search by Meaning
- 4. Comparison: Keyword vs Semantic Search
- 5. Hybrid Search: The Best of Both Worlds
- 6. When to Use Each Search Method
- 7. Capstone Exercise: Classifying 10 Queries
- 1. Module Introduction: Designing Search Systems
- 2. The Overall Architecture of a Search System
- 3. The Indexing Pipeline: Chunking and Embeddings
- 4. Query Processing: From Query to Results
- 5. Advanced Ranking Strategies
- 6. Evaluating Search Quality
- 7. Search System Case Studies
- 8. Capstone Exercise: Designing a Search System
Where it fits
This guide is part of something bigger
It's studied inside these programs, with support and dates.
Common questions
What people usually ask
No limit. It's a free guide: come in whenever you like, as often as you like.
No. Modules run from easier to harder, but you can jump to the one you need. Progress is saved per lesson.
Whatever is needed is listed under “What you need to bring”, above. If nothing is listed there, you can start from zero.
In the Club's WhatsApp group, and every two weeks there's a live with an instructor where questions get worked through.
Yes. It's issued automatically once you finish every lesson, with a verifiable code you can share on LinkedIn.
No. This guide is self-paced with no dates. The bootcamp is live, by cohort, with work someone reviews.
Start whenever you like
What students say
These reviews are from enrolled students who completed at least 50% of the course. We moderate reviews only on content grounds (spam, offensive language, personal data), never for being critical or negative.
No approved reviews yet.
Be the first to share your experience!