Matthew Farrellee a3e249807b chore: remove vision model URL workarounds and simplify client creation (#2775) ... The vision models are now available at the standard URL, so the workaround code has been removed. This also simplifies the codebase by eliminating the need for per-model client caching. - Remove special URL handling for meta/llama-3.2-11b/90b-vision-instruct models - Convert _get_client method to _client property for cleaner API - Remove unnecessary lru_cache decorator and functools import - Simplify client creation logic to use single base URL for all models		2025-07-16 07:10:04 -07:00
..
agent	chore: default to pytest asyncio-mode=auto (#2730)	2025-07-11 13:00:24 -07:00
agents	chore: default to pytest asyncio-mode=auto (#2730)	2025-07-11 13:00:24 -07:00
inference	chore: block network access from unit tests (#2732)	2025-07-12 16:53:54 -07:00
nvidia	chore: remove vision model URL workarounds and simplify client creation (#2775)	2025-07-16 07:10:04 -07:00
utils	feat: add infrastructure to allow inference model discovery (#2710)	2025-07-14 11:38:53 -07:00
vector_io	feat: Implement keyword search in milvus (#2231)	2025-07-14 19:39:55 -04:00
test_configs.py	feat(api): don't return a payload on file delete (#1640)	2025-03-25 17:12:36 -07:00