Sihyeon Jang 3ccbb46938 perf: fix cache key generation for model list caching ... - Replace Request object with user.id in cache key for get_all_models - Request objects are new instances per HTTP request, preventing cache hits - Cache keys now use user.id ensuring proper cache functionality - Affects both Ollama and OpenAI model list endpoints Signed-off-by: Sihyeon Jang <sihyeon.jang@navercorp.com>		2025-09-03 05:17:41 +09:00
..
data	refac: mv backend files to /open_webui dir	2024-09-04 16:54:48 +02:00
internal	refactor: format	2025-08-10 22:28:31 +08:00
migrations	refac: account details	2025-08-21 02:39:25 +04:00
models	refac	2025-08-26 22:05:27 +04:00
retrieval	refac	2025-09-01 14:27:20 +04:00
routers	perf: fix cache key generation for model list caching	2025-09-03 05:17:41 +09:00
socket	refac	2025-08-28 13:25:48 +04:00
static	refac	2025-08-10 00:02:58 +04:00
storage	refac/fix: s3 checksum validation	2025-08-21 12:44:16 +04:00
test	chore: format, lint	2025-07-16 15:23:18 +09:00
utils	enh: llama cpp timing stats	2025-09-01 22:49:49 +04:00
__init__.py	Update __init__.py	2025-04-15 09:55:35 +02:00
alembic.ini	fix: Alembic CLI commands from failing	2025-08-15 04:17:47 -04:00
config.py	refac	2025-09-01 02:41:29 +04:00
constants.py	feat: follow ups	2025-06-03 18:07:29 +04:00
env.py	refac/enh	2025-08-28 03:24:26 +04:00
functions.py	fix: __tools__ param issue	2025-08-25 14:29:05 +04:00
main.py	fix: fillter exception handling	2025-09-01 14:14:20 +04:00
tasks.py	implement redis_key_prefix env support in all areas invoking redis to allow for clustermode compatibility with new docs function	2025-07-22 13:40:29 -04:00