phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 20:14:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: turn OpenAIMixin into a pydantic.BaseModel

Browse source 
- 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
This commit is contained in:
Matthew Farrellee 2025-10-02 20:47:54 -04:00
parent ce77c27ff8
commit 60f0056cbc
57 changed files with 12520 additions and 1254 deletions
Download patch file Download diff file Expand all files Collapse all files

8
tests/unit/providers/inference/test_inference_client_caching.py
View file

@ -22,7 +22,7 @@ def test_groq_provider_openai_client_caching():
"""Ensure the Groq provider does not cache api keys across client requests"""
config = GroqConfig()
inference_adapter = GroqInferenceAdapter(config)
inference_adapter = GroqInferenceAdapter(config=config)
inference_adapter.__provider_spec__ = MagicMock()
inference_adapter.__provider_spec__.provider_data_validator = (
@ -40,7 +40,7 @@ def test_openai_provider_openai_client_caching():
"""Ensure the OpenAI provider does not cache api keys across client requests"""
config = OpenAIConfig()
inference_adapter = OpenAIInferenceAdapter(config)
inference_adapter = OpenAIInferenceAdapter(config=config)
inference_adapter.__provider_spec__ = MagicMock()
inference_adapter.__provider_spec__.provider_data_validator = (
@ -59,7 +59,7 @@ def test_together_provider_openai_client_caching():
"""Ensure the Together provider does not cache api keys across client requests"""
config = TogetherImplConfig()
inference_adapter = TogetherInferenceAdapter(config)
inference_adapter = TogetherInferenceAdapter(config=config)
inference_adapter.__provider_spec__ = MagicMock()
inference_adapter.__provider_spec__.provider_data_validator = (
@ -77,7 +77,7 @@ def test_together_provider_openai_client_caching():
def test_llama_compat_provider_openai_client_caching():
"""Ensure the LlamaCompat provider does not cache api keys across client requests"""
config = LlamaCompatConfig()
inference_adapter = LlamaCompatInferenceAdapter(config)
inference_adapter = LlamaCompatInferenceAdapter(config=config)
inference_adapter.__provider_spec__ = MagicMock()
inference_adapter.__provider_spec__.provider_data_validator = (