BEGINNER · 8 MODULES · 64 LESSONS
Embeddings Deep Dive
Turn text into vectors your team can search: compare embedding models, pick the right distance metric, chunk with care and measure retrieval quality before it reaches production.
Who it is for
- 01AI Engineers que implementan búsqueda semántica o RAG y quieren entender y medir lo que pasa adentro.
- 02Desarrolladores backend que llegan a AI y necesitan decidir con datos, no por moda.
- 03Quienes usan clases de embeddings de un framework y no saben qué revisar cuando algo falla.
- 04Equipos que tienen que elegir un modelo de embeddings y justificarlo.
Before you start
- 01Python básico (funciones, listas, diccionarios, clases) y algo de numpy.
- 02Matemática básica: suma, multiplicación, raíz cuadrada. Los conceptos de vectores y similitud se explican dentro de la guía.
- 03Opcional: una clave de la API de OpenAI para comparar con un modelo de pago.
Curriculum
01¿Qué son Embeddings?
02¿Cómo funcionan Embeddings?
- Welcome to Module 2: How Do Embeddings Work?
- Transformer Encoders: The Architecture of Modern Embeddings
- Tokenization: From Text to Tokens
- Contextualization: Embeddings That Understand Context
- Pooling Strategies: From Multiple Tokens to One Vector
- Normalization: Scaling Embeddings to Unit Magnitude
- OpenAI API Advanced: Parameters and Production Patterns
- Mini-Project: Robust API Client for Production
03Modelos de Embeddings (Comparación)
- Introduction to Module 3: Embedding Models Compared
- OpenAI Embeddings Models: Deep Dive Comparison
- Open-Source Embeddings: Self-Hosted Alternatives
- MTEB: Massive Text Embedding Benchmark
- Latency and Throughput: Real Performance
- Cost Analysis: The Economics of Embeddings
- Domain-Specific and Multilingual Embeddings
- Mini-Project: Benchmark Framework for Embedding Models
04Evaluación y Chunking Strategies
- Introduction to Module 4: Evaluation and Chunking Strategies
- Fixed-Size Chunking: Practical Implementation
- Semantic Chunking: Respecting Document Structure
- Retrieval Metrics: Measuring RAG Performance
- Creating Evaluation Datasets for RAG
- A/B Testing Chunking Strategies
- Advanced Chunking Patterns
- Mini-Project: RAG System with Intelligent Chunking
05Métricas de Distancia a Fondo
- Module 5 Introduction: Distance Metrics in Depth
- Cosine Similarity: The Standard Metric
- Euclidean Distance: When It Matches Cosine and When It Doesn't
- Dot Product and Other Metrics
- Performance Benchmarks: Where the Time Goes
- Approximate Search (ANN): Not Walking Past Every Shelf
- Introduction to FAISS: Exact, HNSW and IVF Measured
- Project: Metrics and Index Comparator
08Proyecto Integrador
- Module 8: Final Capstone Project - Complete RAG System
- Document Ingestion Pipeline
- Chunking & Embedding Pipeline Integration
- Vector Search with FAISS
- Evaluation Framework: Measuring RAG Performance
- Query Expansion & Reranking: Two-Stage Retrieval
- Production Deployment: Freezing and Protecting the Decision
- Conclusions and Next Steps
Reviews
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!