Learn how to build evals for LLM applications: datasets from real traffic, deterministic checks, LLM-as-judge with binary rubrics, CI integration, and the biases and common mistakes that silently invalidate your metrics. Includes a complete pytest harness ready to use.
Verificando acceso...
Learn the basics of LangChain to build AI applications. From installation to your first functional pattern.
Battle-tested patterns for building production-ready RAG (Retrieval-Augmented Generation) systems in 2026: semantic chunking, embedding selection, hybrid search, and cross-encoder reranking.
Learn to stream a language model's response token by token using Server-Sent Events (SSE). Covers the FastAPI backend, consuming the stream in the browser with EventSource and fetch, error handling and cancellation, and the common mistakes that break streaming in production.