AI Engineer: Introduction to RAG & Search

AI Engineer: Introduction to RAG & Search is a self-paced, intermediate course that teaches developers how to build production-ready Retrieval-Augmented Generation (RAG) systems that extend an LLM's context and improve its answers. Learners study information retrieval and search, including TF-IDF, BM25, semantic and hybrid search, and ANN algorithms, and work with vector databases such as Weaviate and PgVector, embeddings, chunking, reranking, and prompt engineering. Each module pairs theory with hands-on work, including building a RAG system on a vector database and a RAG-based document summarizer, using Langfuse for observability and evaluation.

• Who This Course is For
  • Developers and aspiring AI engineers who want to build RAG and search systems
  • Intermediate learners with some Python experience and basic understanding of LLMs
  • Learners who want theory explained before applying it hands-on
• What to Expect
  • Self-paced modules that start with theory, then move to hands-on work
  • Search techniques including TF-IDF, BM25, semantic, hybrid search, and ANN algorithms
  • Tools including Weaviate, PgVector, embeddings, and Langfuse for observability and prompt management
• What You'll Achieve
  • Design and deploy end-to-end RAG systems with semantic and hybrid retrieval
  • Build a vector database RAG system and a RAG-based document summarizer
  • Make LLM applications production-ready with observability, evaluation, and prompt versioning