Akram Ben Aissi 2b54b57145 feat: implement graceful model discovery for vLLM provider ... - Attempt model discovery first for backward compatibility - If discovery fails and refresh_models=false, continue without error - If discovery fails and refresh_models=true, fail hard with ValueError - Supports dynamic token authentication scenarios Fixes OAuth authentication issues when vLLM service requires dynamic tokens		2025-10-03 21:32:15 +02:00
..
inline	chore: remove deprecated inference.chat_completion implementations (#3654)	2025-10-03 07:55:34 -04:00
registry	feat: implement keyword and hybrid search for Weaviate provider (#3264)	2025-10-03 10:22:30 +02:00
remote	feat: implement graceful model discovery for vLLM provider	2025-10-03 21:32:15 +02:00
utils	chore: use remoteinferenceproviderconfig for remote inference providers (#3668)	2025-10-03 08:48:42 -07:00
__init__.py	API Updates (#73)	2024-09-17 19:51:35 -07:00
datatypes.py	feat: combine ProviderSpec datatypes (#3378)	2025-09-18 16:10:00 +02:00