discourse-ai/lib
Rafael dos Santos Silva 3b8f900486
FIX: Handle unicode on tokenizer (#515)
* FIX: Handle unicode on tokenizer

Our fast track code broke when strings had characters who are longer in tokens than
in UTF-8.

Admins can set `DISCOURSE_AI_STRICT_TOKEN_COUNTING: true` in app.yml to ensure token counting is strict, even if slower.


Co-authored-by: wozulong <sidle.pax_0e@icloud.com>
2024-03-14 17:33:30 -03:00
..
ai_bot FIX: don't show share conversation incorrectly (#526) 2024-03-13 11:24:22 +11:00
ai_helper FIX: Prevent AI chat thread titles from being created before replies are posted (#517) 2024-03-07 16:14:17 -03:00
automation FEATURE: support for claude opus and sonnet (#508) 2024-03-06 06:04:37 +11:00
completions FIX: Tune function calling (#519) 2024-03-09 08:46:40 +11:00
configuration UX: Re-introduce embedding settings validations (#457) 2024-02-01 16:54:09 -03:00
database DEV: port directory structure to Zeitwerk (#319) 2023-11-29 15:17:46 +11:00
embeddings DEV: Fix module namespace breaking reloads (#530) 2024-03-14 15:19:28 -03:00
inference FEATURE: AI Quick Semantic Search (#501) 2024-03-08 13:02:50 -03:00
nsfw DEV: Fix various typos (#434) 2024-01-19 12:51:26 +01:00
sentiment FIX: Truncate content for sentiment/toxicity classification (#431) 2024-01-17 15:17:58 -03:00
summarization UX: Validations to LLM-backed features (except AI Bot) (#436) 2024-01-29 16:04:25 -03:00
tasks/modules FIX: Filter soft-deleted topics when backfilling sentiment (#527) 2024-03-12 21:01:24 -03:00
tokenizer FIX: Handle unicode on tokenizer (#515) 2024-03-14 17:33:30 -03:00
toxicity FIX: Truncate content for sentiment/toxicity classification (#431) 2024-01-17 15:17:58 -03:00
utils FEATURE: DNS SRV support for TEI (#363) 2023-12-18 13:21:21 -03:00
automation.rb FEATURE: support for claude opus and sonnet (#508) 2024-03-06 06:04:37 +11:00
chat_message_classificator.rb DEV: port directory structure to Zeitwerk (#319) 2023-11-29 15:17:46 +11:00
classificator.rb DEV: port directory structure to Zeitwerk (#319) 2023-11-29 15:17:46 +11:00
engine.rb DEV: port directory structure to Zeitwerk (#319) 2023-11-29 15:17:46 +11:00
guardian_extensions.rb FIX: don't show share conversation incorrectly (#526) 2024-03-13 11:24:22 +11:00
post_classificator.rb DEV: port directory structure to Zeitwerk (#319) 2023-11-29 15:17:46 +11:00