mirror of
https://gh.wpcy.net/https://github.com/discourse/discourse.git
synced 2026-05-12 01:20:18 +08:00
7641075c99
This commit reverts af2f94cca9bd76fde14055d3087103f90a7c5c1b since it is hiding the root cause of the problem by manually cleaning up database records in a system test. This should not be required as the database transaction should be rolled back at the end of every test. |
||
|---|---|---|
| .. | ||
| admin/assets/javascripts/discourse | ||
| app | ||
| assets | ||
| config | ||
| db | ||
| discourse_automation | ||
| evals | ||
| lib | ||
| public/ai-share | ||
| spec | ||
| svg-icons | ||
| test/javascripts | ||
| .prettierignore | ||
| about.json | ||
| plugin.rb | ||
| README.md | ||
Discourse AI Plugin
Plugin Summary
For more information, please see: https://meta.discourse.org/t/discourse-ai/259214?u=falco
Evals
The directory evals contains AI evals for the Discourse AI plugin.
You may create a local config by copying config/eval-llms.yml to config/eval-llms.local.yml and modifying the values.
To run them use:
cd evals ./run --help
Usage: evals/run [options]
-e, --eval NAME Name of the evaluation to run
--list-models List models
-m, --model NAME Model to evaluate (will eval all models if not specified)
-l, --list List evals
To run evals you will need to configure API keys in your environment:
OPENAI_API_KEY=your_openai_api_key ANTHROPIC_API_KEY=your_anthropic_api_key GEMINI_API_KEY=your_gemini_api_key
