discourse-ai/spec
Sam cabecb801e
FEATURE: disable rate limiting when skipping hyde (#793)
Embedding search is rate limited due to potentially expensive
hyde operation (which require LLM access).

Embedding generally is very cheap compared to it. (usually 100x cheaper)

This raises the limit to 100 per minute for embedding searches,
while keeping the old 4 per minute for HyDE powered search.
2024-09-04 15:51:01 +10:00
..
configuration FIX: Correctly display errors when parent module needs to be disabled first (#788) 2024-08-30 17:16:11 -03:00
fabricators FIX: LlmModel validations. (#742) 2024-08-06 14:35:35 -03:00
fixtures FIX: Load categories from search response (#612) 2024-05-14 17:13:25 +03:00
jobs FIX: we were never reindexing old content (#786) 2024-08-30 14:37:55 +10:00
lib FEATURE: more accurate and faster titles (#791) 2024-09-03 15:52:20 +10:00
models DEV: Clearly separate post/composer helper settings (#747) 2024-08-12 15:40:23 -07:00
requests FEATURE: disable rate limiting when skipping hyde (#793) 2024-09-04 15:51:01 +10:00
serializers DEV: Fix new Rubocop offenses 2024-03-06 15:23:29 +01:00
services/discourse_ai FIX: more robust summary implementation (#750) 2024-08-13 08:47:47 -03:00
shared FEATURE: GPT4o Tokenizer (#721) 2024-07-22 15:26:14 -03:00
support FIX: typo causing text_embedding_3_large to fail (#460) 2024-02-05 11:16:36 +11:00
system FIX: Display cached summaries with our new streamer. (#792) 2024-09-03 18:45:28 -03:00
tasks FIX: Filter soft-deleted topics when backfilling sentiment (#527) 2024-03-12 21:01:24 -03:00
plugin_helper.rb DEV: Remove old code now that features rely on LlmModels. (#729) 2024-07-30 13:44:57 -03:00
plugin_spec.rb DEV: Clearly separate post/composer helper settings (#747) 2024-08-12 15:40:23 -07:00