phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-15 22:47:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

resource oriented object design for models

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-11-07 16:43:55 -08:00
parent 5625aef48a
commit ca88f3f182
17 changed files with 63 additions and 82 deletions
Download patch file Download diff file Expand all files Collapse all files

10
llama_stack/apis/models/client.py
View file

@ -26,16 +26,16 @@ class ModelsClient(Models):
async def shutdown(self) -> None:
pass
async def list_models(self) -> List[ModelDefWithProvider]:
async def list_models(self) -> List[Model]:
async with httpx.AsyncClient() as client:
response = await client.get(
f"{self.base_url}/models/list",
headers={"Content-Type": "application/json"},
)
response.raise_for_status()
return [ModelDefWithProvider(**x) for x in response.json()]
return [Model(**x) for x in response.json()]
async def register_model(self, model: ModelDefWithProvider) -> None:
async def register_model(self, model: Model) -> None:
async with httpx.AsyncClient() as client:
response = await client.post(
f"{self.base_url}/models/register",
@ -46,7 +46,7 @@ class ModelsClient(Models):
)
response.raise_for_status()
async def get_model(self, identifier: str) -> Optional[ModelDefWithProvider]:
async def get_model(self, identifier: str) -> Optional[Model]:
async with httpx.AsyncClient() as client:
response = await client.get(
f"{self.base_url}/models/get",
@ -59,7 +59,7 @@ class ModelsClient(Models):
j = response.json()
if j is None:
return None
return ModelDefWithProvider(**j)
return Model(**j)
async def run_main(host: str, port: int, stream: bool):