Skip to main content

​
More Cookbooks

evals-cookbook

Evaluations Quickstart

online-evals

Run Online Evals in the Arize UI

offline-evals

Run Offline Evals in Code

session-level-evals

Session-Level Evaluations

cookbooks-frameworks

Agent Trajectory Evaluations

rag-cookbook

Evaluating RAG

​
Span-Level Evaluation

Evaluate code functionality

Evaluate hallucination

Evaluate human ground truth vs. AI

Evaluate Q&A correctness

Evaluate RAG

Evaluate reference links

Evaluate relevance

Evaluate SQL correctness

Evaluate tool calling

Evaluate toxicity

Evaluate user frustration