phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-09 11:20:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Another round of simplification and clarity for models/shields/memory_banks stuff

Browse source
This commit is contained in:
Ashwin Bharambe 2024-10-09 19:19:26 -07:00
parent 73a0a34e39
commit b55034c0de
27 changed files with 454 additions and 444 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -6,7 +6,7 @@
from enum import Enum
from typing import List, Literal, Optional, Protocol, Union
from typing import List, Literal, Optional, Protocol, runtime_checkable, Union
from llama_models.schema_utils import json_schema_type, webmethod
@ -177,6 +177,7 @@ class ModelStore(Protocol):
def get_model(self, identifier: str) -> ModelDef: ...
@runtime_checkable
class Inference(Protocol):
model_store: ModelStore
@ -214,6 +215,3 @@ class Inference(Protocol):
model: str,
contents: List[InterleavedTextMedia],
) -> EmbeddingsResponse: ...
@webmethod(route="/inference/register_model")
async def register_model(self, model: ModelDef) -> None: ...