Discourse/discourse
Discourse/discourse
0
0
Fork 0
mirror of https://gh.wpcy.net/https://github.com/discourse/discourse.git synced 2026-05-27 17:02:55 +08:00
Code Packages Activity Actions
discourse/plugins/discourse-ai
History
Exact
David Taylor aae6385937
UX: Make AI streaming more efficient under glimmer post stream (#34068) 
In the glimmer post stream, mutating `post.cooked` will cause ember to
re-render the HTML. That conflicts with d-ai's own morphlex-based diff
streaming.

To avoid this, we can wait until all streaming has finished before
setting the cooked property of the model.

Co-authored-by: Sérgio Saquetim <saquetim@discourse.org>
2025-08-04 16:15:57 +01:00
..
admin/assets/javascripts/discourse DEV: Reapply gjs-codemod in d-ai (#33758) 2025-07-23 12:05:40 +02:00
app FEATURE: Allow re-localization twice a day if post version has changed (#34023) 2025-08-04 10:58:30 +08:00
assets UX: Make AI streaming more efficient under glimmer post stream (#34068) 2025-08-04 16:15:57 +01:00
config FEATURE: Use a persona when running the AI triage automation script (#34010) 2025-08-04 09:11:13 -03:00
db FIX: Use correct variable for triage personas migration (#34067) 2025-08-04 10:35:46 -03:00
discourse_automation FEATURE: Use a persona when running the AI triage automation script (#34010) 2025-08-04 09:11:13 -03:00
evals
lib FEATURE: Use a persona when running the AI triage automation script (#34010) 2025-08-04 09:11:13 -03:00
public/ai-share
spec FEATURE: Use a persona when running the AI triage automation script (#34010) 2025-08-04 09:11:13 -03:00
svg-icons
test/javascripts DEV: Fix various lint issues (#33811) 2025-07-24 15:27:04 +02:00
.prettierignore
about.json
plugin.rb
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