7-module course covering RAG, vector search, orchestration, evaluation, monitoring, and best practices. Code for all modules lives in the GitHub repo.
Modules
3 of 7 modules completed
Agentic RAG
Built a RAG system from scratch — search, prompt engineering, chunking — then made it agentic with function calling and an LLM-driven loop.
Vector Search
Semantic search with embeddings — moving beyond keyword matching to meaning-based retrieval. Built vector search by hand with numpy, then with minsearch, sqlitesearch, and PGVector; combined keyword and vector search with hybrid RRF fusion.
Orchestration
AI orchestration with Kestra — context engineering, AI Copilot, RAG (static + web search), autonomous agents, and multi-agent delegation, all wrapped in versioned, observable workflows.
Evaluation
Measuring RAG quality — LLM-as-judge, retrieval metrics, and systematic evaluation.
Monitoring
Observability for LLM applications in production.
Best Practices
Hybrid search, guardrails, and production patterns for reliable LLM systems.
Project
End-to-end LLM application — putting everything together.