discourse-ai/spec/lib/modules/ai_bot
Sam 0c9466059c
DEV: improve artifact editing and eval system (#1130)
- Add non-contiguous search/replace support using ... syntax
- Add judge support for evaluating LLM outputs with ratings
- Improve error handling and reporting in eval runner
- Add full section replacement support without search blocks
- Add fabricators and specs for artifact diffing
- Track failed searches to improve debugging
- Add JS syntax validation for artifact versions in eval system
- Update prompt documentation with clear guidelines

* improve eval output

* move error handling

* llm as a judge

* fix spec

* small note on evals
2025-02-19 15:44:33 +11:00
..
artifact_update_strategies DEV: improve artifact editing and eval system (#1130) 2025-02-19 15:44:33 +11:00
jobs/regular FEATURE: more accurate and faster titles (#791) 2024-09-03 15:52:20 +10:00
personas FEATURE: PDF support for rag pipeline (#1118) 2025-02-14 12:15:07 +11:00
tools DEV: improve artifact editing and eval system (#1130) 2025-02-19 15:44:33 +11:00
bot_spec.rb DEV: Remove old code now that features rely on LlmModels. (#729) 2024-07-30 13:44:57 -03:00
entry_point_spec.rb FEATURE: PDF support for rag pipeline (#1118) 2025-02-14 12:15:07 +11:00
playground_spec.rb FEATURE: PDF support for rag pipeline (#1118) 2025-02-14 12:15:07 +11:00
question_consolidator_spec.rb DEV: Remove old code now that features rely on LlmModels. (#729) 2024-07-30 13:44:57 -03:00
site_setting_extension_spec.rb DEV: Rewire AI bot internals to use LlmModel (#638) 2024-06-18 14:32:14 -03:00