phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-27 06:28:50 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(registry): make the Stack query providers for model listing

Browse source
This commit is contained in:
Ashwin Bharambe 2025-07-22 14:13:21 -07:00
parent cd8715d327
commit 2e5ffab4e3
12 changed files with 127 additions and 124 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama_stack/apis/inference/inference.py
View file

@ -819,12 +819,6 @@ class OpenAIEmbeddingsResponse(BaseModel):
class ModelStore(Protocol):
async def get_model(self, identifier: str) -> Model: ...
async def update_registered_llm_models(
self,
provider_id: str,
models: list[Model],
) -> None: ...
class TextTruncation(Enum):
"""Config for how to truncate text for embedding when text is longer than the model's max sequence length. Start and End semantics depend on whether the language is left-to-right or right-to-left.