discourse-ai/lib/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
personas FEATURE: PDF support for rag pipeline (#1118) 2025-02-14 12:15:07 +11:00
tools FEATURE: Tool name validation (#842) 2025-02-07 14:34:47 +11:00
bot.rb FEATURE: PDF support for rag pipeline (#1118) 2025-02-14 12:15:07 +11:00
entry_point.rb DEV: Robust check for embeddings enabled (#1116) 2025-02-06 12:18:55 -03:00
playground.rb DEV: artifact system update (#1096) 2025-02-04 16:27:27 +11:00
post_streamer.rb FIX: cancel functionality regressed (#938) 2024-11-21 17:51:45 +11:00
question_consolidator.rb FEATURE: GPT4o support and better auditing (#618) 2024-05-14 13:28:46 +10:00
response_http_streamer.rb FIX: properly spin down unused streamer threads (#1035) 2024-12-20 12:09:42 +11:00
site_settings_extension.rb DEV: Rewire AI bot internals to use LlmModel (#638) 2024-06-18 14:32:14 -03:00
tool_runner.rb REFACTOR: Separation of concerns for embedding generation. (#1027) 2024-12-16 09:55:39 -03:00