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
..
bedrock	fix: use lambda pattern for bedrock config env vars (#3307)	2025-09-05 10:45:11 +02:00
test_inference_client_caching.py	chore: update the groq inference impl to use openai-python for openai-compat functions (#3348)	2025-09-06 15:36:27 -07:00
test_litellm_openai_mixin.py	feat: add static embedding metadata to dynamic model listings for providers using OpenAIMixin (#3547)	2025-09-25 17:17:00 -04:00
test_openai_base_url_config.py	feat: include all models from provider's /v1/models (#3471)	2025-09-18 05:17:11 -04:00
test_remote_vllm.py	fix(dev): fix vllm inference recording (await models.list) (#3524)	2025-09-23 12:56:33 -04:00