phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-08 19:10:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Introduce model_store, shield_store, memory_bank_store

Browse source
This commit is contained in:
Ashwin Bharambe 2024-10-06 16:29:33 -07:00 • committed by Ashwin Bharambe
parent e45a417543
commit 91e0063593
19 changed files with 172 additions and 297 deletions
Download patch file Download diff file Expand all files Collapse all files

12
llama_stack/apis/inference/inference.py
View file

@ -173,7 +173,13 @@ class EmbeddingsResponse(BaseModel):
embeddings: List[List[float]]
class ModelStore(Protocol):
def get_model(self, identifier: str) -> ModelDef: ...
class Inference(Protocol):
model_store: ModelStore
@webmethod(route="/inference/completion")
async def completion(
self,
@ -207,9 +213,3 @@ class Inference(Protocol):
@webmethod(route="/inference/register_model")
async def register_model(self, model: ModelDef) -> None: ...
@webmethod(route="/inference/list_models")
async def list_models(self) -> List[ModelDef]: ...
@webmethod(route="/inference/get_model")
async def get_model(self, identifier: str) -> Optional[ModelDef]: ...