Embeddings and Vector Databases: concepts and vocabulary | Complete Generative AI: From Foundations to Production
A self-paced 26-week learning path with 15 modules: AI foundations, Python, machine learning, transformers, LLMs, prompts, APIs, embeddings, RAG, frameworks, agents, customization, multimodal AI, Spring Boot with React, and production LLMOps. Includes 15 practical assignments and three portfolio projects.
Prerequisites: Begin with basic computer skills. Programming is introduced in Weeks 2–3. Use a local Python environment for coding labs; Java and React experience helps in Weeks 21–22. Model downloads, provider accounts and deployment resources are optional learner-managed dependencies. The 26-week schedule is suggested; reading estimates exclude independent project work.
Learning goals
Embeddings and semantic search
Cosine similarity
Chunking strategies
Vector indexes
FAISS, Chroma, Pinecone and pgvector concepts
Hybrid search and metadata filtering
Understand the foundations
An embedding model maps an input into a fixed-dimensional vector useful for comparing certain relationships. Cosine similarity measures vector direction; it is not a calibrated probability of relevance. Store the embedding model identifier and version with each index. Vectors from incompatible embedding spaces cannot be meaningfully mixed just because their dimensions match. Re-embedding requires a deliberate migration and evaluation because rankings may change when the representation changes.
Connect the ideas
Chunk documents along meaningful boundaries and retain source IDs, offsets, versions and permissions. Small chunks may lose context; large chunks may dilute a match and exceed a later prompt budget. Exact nearest-neighbor search compares every candidate; approximate indexes trade retrieval recall for speed and memory. FAISS is a similarity-search library, Chroma is a vector-oriented store, Pinecone is a managed vector service and pgvector adds vector capabilities to PostgreSQL. Select by operational needs and measured workload rather than assuming identical features.
Checkpoint: explain these concepts in your own words, then describe one failure that the design must detect. Use synthetic or permissioned data throughout the course.
01. Introduction to Artificial Intelligence · Week 1
02. Python Programming for Gen AI · Weeks 2–3
03. Mathematics and Machine Learning Foundations · Week 4
04. Deep Learning and Transformers · Weeks 5–6
05. Large Language Models (LLMs) · Weeks 7–8
06. Prompt Engineering · Weeks 9–10
07. Generative AI APIs and Application Development · Week 11
08. Embeddings and Vector Databases · Weeks 12–13
09. Retrieval-Augmented Generation (RAG) · Weeks 14–15
10. LangChain, LlamaIndex and AI Frameworks · Week 16
11. AI Agents and Agentic AI · Weeks 17–18
12. Fine-Tuning and Model Customization · Week 19
13. Multimodal Generative AI · Week 20
14. Gen AI with Java Spring Boot and React · Weeks 21–22
15. Production Gen AI, LLMOps and Capstone · Weeks 23–26