Catch quality regressions in your AI application.
What it does
Builds evaluation frameworks that measure LLM application quality using automated scores, human feedback, and benchmarks.
When to use it
Use when measuring LLM performance, comparing models or prompts, or detecting regressions before deployment.
How to use it
Give it an LLM application to evaluate; it implements evaluation code for measuring application quality.
What you provide
- An existing project
Latest review
What you need · 2
The quick-start evaluation implementation runs in Python; no runtime version is specified.
The quick-start evaluation implementation imports numpy and uses it to aggregate metric scores.
Access · 0
No additional actions listed.