Matthew Farrellee 60f0056cbc chore: turn OpenAIMixin into a pydantic.BaseModel ... - implement get_api_key instead of relying on LiteLLMOpenAIMixin.get_api_key - remove use of LiteLLMOpenAIMixin - add default initialize/shutdown methods to OpenAIMixin - remove __init__s to allow proper pydantic construction - remove dead code from vllm adapter and associated / duplicate unit tests - update vllm adapter to use openaimixin for model registration - remove ModelRegistryHelper from fireworks & together adapters - remove Inference from nvidia adapter - complete type hints on embedding_model_metadata - allow extra fields on OpenAIMixin, for model_store, __provider_id__, etc - new recordings for ollama		2025-10-03 14:17:43 -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: turn OpenAIMixin into a pydantic.BaseModel	2025-10-03 14:17:43 -04:00
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	chore: turn OpenAIMixin into a pydantic.BaseModel	2025-10-03 14:17:43 -04:00
test_remote_vllm.py	chore: turn OpenAIMixin into a pydantic.BaseModel	2025-10-03 14:17:43 -04:00