phoenix — GitHub Copilot plugin: what it does, how to install
Add AI observability, evaluation, and OpenInference tracing tools to GitHub Copilot. It helps when you need to inspect traces or debug LLM apps.
copilot plugin install phoenix@awesome-copilotWhat phoenix does
The plugin bundles three skills: phoenix-cli, phoenix-evals, and phoenix-tracing. The phoenix-cli skill lets your assistant fetch traces, inspect datasets, and query the Phoenix GraphQL API.
With phoenix-evals, you can build and run evaluations directly on your LLM workflows. The phoenix-tracing skill brings OpenInference semantic conventions and instrumentation into the editor.
Install it if your stack already runs on Phoenix from Arize AI. Without Phoenix, these skills have nothing to query.
What it helps with
- fetch LLM execution traces with Phoenix CLI
- build and run evaluators for AI applications
- instrument code with OpenInference semantic conventions
- query datasets and experiments via Phoenix GraphQL API
Example prompts for the agent
- Instrument our LLM calls with OpenInference conventions using phoenix-tracing
- Fetch the latest failed traces using phoenix-cli
- Run evaluators on our test dataset with phoenix-evals
How to install phoenix
Command from the source
copilot plugin install phoenix@awesome-copilotFrom the same set554
The whole set →Similar
Questions about phoenix
How to install phoenix in GitHub Copilot?
Run copilot plugin install phoenix@awesome-copilot in your terminal.
What does the phoenix plugin do?
It adds Arize AI Phoenix observability skills to your agent. This includes CLI trace debugging, OpenInference instrumentation, and evaluation workflows for LLM apps.
What skills are included in the phoenix plugin?
The plugin provides phoenix-cli for trace and dataset queries, phoenix-evals for model evaluations, and phoenix-tracing for OpenInference semantic conventions.
Source text
phoenix · MIT
# Phoenix Plugin Phoenix AI observability skills for LLM application debugging, evaluation, and tracing. Includes CLI debugging tools, LLM evaluation workflows, and OpenInference tracing instrumentation. ## Installation ```bash # Using Copilot CLI copilot plugin install phoenix@awesome-copilot ``` ## What's Included ### Skills | Skill | Description | |-------|-------------| | `phoenix-cli` | Debug LLM applications using the Phoenix CLI. Fetch traces, analyze errors, review experiments, inspect datasets, and query the GraphQL API. | | `phoenix-evals` | Build and run evaluators for AI/LLM applications using Phoenix. | | `phoenix-tracing` | OpenInference semantic conventions and instrumentation for Phoenix AI observability. |
© Arize AI · MIT · github/awesome-copilot