mirror of
https://github.com/discourse/discourse-ai.git
synced 2025-06-24 00:22:14 +00:00
49fe986974
## 🔍 Overview As reported on [Meta](https://meta.discourse.org/t/when-selecting-text-and-giving-ai-a-custom-prompt-based-on-the-text-the-popup-cannot-be-scrolled/368687?u=keegan), you are currently unable to scroll on long AI post helper results when on mobile. This update fixes that by allowing scroll back. No test as it's tricky to test scroll behavior. ## 🔗 Relevant Links https://meta.discourse.org/t/when-selecting-text-and-giving-ai-a-custom-prompt-based-on-the-text-the-popup-cannot-be-scrolled/368687 ## 📹 Screen Recording ### ← Before https://github.com/user-attachments/assets/9dc6f6a2-b9d4-46a8-91ee-ad1ed6f47de0 ### → After https://github.com/user-attachments/assets/ca93dba1-eefb-4d03-9b47-c4a8ba291117
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