phoenix-harbor
Installation
SKILL.md
Phoenix for Harbor
Use the Phoenix Harbor plugin to record Harbor agent evaluations as versioned Phoenix datasets, experiments, runs, scores, and ATIF traces.
Harbor runs agents and verifiers. Phoenix records and compares their results.
For a new evaluation, start with Build and run Harbor tasks to create and validate a task. Then follow this file to record runs and compare results in Phoenix. For a worked verifier built with Phoenix Evals, see Use Phoenix Evals in a verifier.
Requirements
- Python 3.12 or newer
- Harbor 0.21.0 or newer
arize-phoenix-clientinstalled with theharborextra- Phoenix server 15.0 or newer
Install the client and Harbor in the same Python environment: