Mar 29 路 16 min read 路 TLDR: 馃搹 Traditional ML metrics (accuracy, F1) fail for LLMs because there's no single "correct" answer. RAGAS measures RAG pipeline quality with faithfulness, answer relevance, and context precision.
EAli commentedJul 3, 2025 路 1 min read 路 DeepEval is a framework for testing LLM results. Everything in AI architecture is overwhelming, but all they are easier to understand if we think as how to work as a team. Hasura team is awesome, reading through the new promptQL blew my mind. To...
Join discussionMay 26, 2025 路 4 min read 路 If you're looking to master prompt engineering, AI model behavior, and build testable, production-grade prompts, this is your field guide. This guide walks through everything from basic prompting anatomy to evaluations (Evals) and parameter tuning. ...
Join discussion
