discourse/plugins/discourse-ai
2025-08-29 17:24:43 +02:00
..
admin/assets/javascripts/discourse FEATURE: Translation progress admin UI (#34239) 2025-08-15 12:19:35 -07:00
app FEATURE: add support for Groq as a pre-configured LLM (#34402) 2025-08-19 16:17:45 +10:00
assets UX: only show AI persona dropdown with multiple options (#34527) 2025-08-27 11:55:35 -04:00
config Update translations (#34633) 2025-08-29 17:24:43 +02:00
db FIX: Truncate seeded persona's names to fit name length constraint (#34393) 2025-08-18 18:08:43 -03:00
discourse_automation FIX: use an integer, not a float, in the AI tagging automation (#34622) 2025-08-28 16:39:36 -04:00
evals
lib FEATURE: add support for google image model (#34570) 2025-08-29 14:39:37 +10:00
public/ai-share
spec FEATURE: add support for google image model (#34570) 2025-08-29 14:39:37 +10:00
svg-icons
test/javascripts DEV: Fix various lint issues (#33811) 2025-07-24 15:27:04 +02:00
.prettierignore
about.json
plugin.rb FEATURE: create AI tagging automation (#34587) 2025-08-28 13:13:27 -04:00
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