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

feat: add static embedding metadata to dynamic model listings for providers using OpenAIMixin

Browse source 
- 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
This commit is contained in:
Matthew Farrellee 2025-09-25 04:56:54 -04:00
parent a50b63906c
commit 466ef6f490
43 changed files with 370 additions and 1016 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -292,7 +292,7 @@ class VLLMInferenceAdapter(OpenAIMixin, LiteLLMOpenAIMixin, Inference, ModelsPro
def __init__(self, config: VLLMInferenceAdapterConfig) -> None:
LiteLLMOpenAIMixin.__init__(
self,
build_hf_repo_model_entries(),
model_entries=build_hf_repo_model_entries(),
litellm_provider_name="vllm",
api_key_from_config=config.api_token,
provider_data_api_key_field="vllm_api_token",