Discourse/discourse
Discourse/discourse
0
0
Fork 0
mirror of https://gh.wpcy.net/https://github.com/discourse/discourse.git synced 2026-05-07 08:54:19 +08:00
Code Packages Activity Actions
discourse/plugins/discourse-ai
History
Exact
Roman Rizzi 1d9a7222d9
FEATURE: Encourage parallel search when using tools for Discover
2025-09-29 14:59:16 -03:00
..
admin/assets/javascripts/discourse DEV: Standardize Ember route, controller and template naming (#34417) 2025-09-25 11:27:45 +01:00
app FIX: Publish the topic instead of the post to refresh topic titles (#34961) 2025-09-25 03:12:41 +08:00
assets DEV: Standardize Ember route, controller and template naming (#34417) 2025-09-25 11:27:45 +01:00
config Update translations (#34839) 2025-09-24 14:48:18 +02:00
db FEATURE: Promote Discover to a dedicated feature. (#34846) 2025-09-23 14:01:45 -03:00
discourse_automation FEATURE: Add option to flag + delete for llm triage (#34590) 2025-09-02 09:16:30 +10:00
evals
lib FEATURE: Encourage parallel search when using tools for Discover 2025-09-29 14:59:16 -03:00
public/ai-share
spec FIX: Publish the topic instead of the post to refresh topic titles (#34961) 2025-09-25 03:12:41 +08:00
svg-icons
test/javascripts DEV: Fix various lint issues (#33811) 2025-07-24 15:27:04 +02:00
.prettierignore
about.json
plugin.rb FEATURE: Promote Discover to a dedicated feature. (#34846) 2025-09-23 14:01:45 -03:00
README.md

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