Matthew Farrellee b67aef2fc4 feat: add static embedding metadata to dynamic model listings for providers using OpenAIMixin (#3547) ... # What does this PR do? - remove auto-download of ollama embedding models - add embedding model metadata to dynamic listing w/ unit test - add support and tests for allowed_models - removed inference provider models.py files where dynamic listing is enabled - store embedding metadata in embedding_model_metadata field on inference providers - make model_entries optional on ModelRegistryHelper and LiteLLMOpenAIMixin - make OpenAIMixin a ModelRegistryHelper - skip base64 embedding test for remote::ollama, always returns floats - only use OpenAI client for ollama model listing - remove unused build_model_entry function - remove unused get_huggingface_repo function ## Test Plan ci w/ new tests		2025-09-25 17:17:00 -04:00
..
dell-tgi.md	docs: concepts and building_applications migration (#3534)	2025-09-24 14:05:30 -07:00
dell.md	docs: concepts and building_applications migration (#3534)	2025-09-24 14:05:30 -07:00
meta-reference-gpu.md	docs: provider and distro codegen migration (#3531)	2025-09-24 14:01:29 -07:00
nvidia.md	feat: add static embedding metadata to dynamic model listings for providers using OpenAIMixin (#3547)	2025-09-25 17:17:00 -04:00
passthrough.md	docs: concepts and building_applications migration (#3534)	2025-09-24 14:05:30 -07:00
starter.md	docs: fix broken links (#3540)	2025-09-24 14:16:31 -07:00