phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

migrate model to Resource and new registration signature (#410)

Browse source 
* resource oriented object design for models

* add back llama_model field

* working tests

* register singature fix

* address feedback

---------

Co-authored-by: Dinesh Yeduguru <dineshyv@fb.com>
This commit is contained in:
Dinesh Yeduguru 2024-11-08 16:12:57 -08:00 • committed by GitHub
parent bd0622ef10
commit ec644d3418
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
17 changed files with 99 additions and 90 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):

34
llama_stack/apis/models/models.py
View file

@ -7,37 +7,33 @@
from typing import Any, Dict, List, Literal, Optional, Protocol, runtime_checkable
from llama_models.schema_utils import json_schema_type, webmethod
from pydantic import BaseModel, Field
from pydantic import Field
from llama_stack.apis.resource import Resource, ResourceType
class ModelDef(BaseModel):
identifier: str = Field(
description="A unique name for the model type",
)
llama_model: str = Field(
description="Pointer to the underlying core Llama family model. Each model served by Llama Stack must have a core Llama model.",
)
@json_schema_type
class Model(Resource):
type: Literal[ResourceType.model.value] = ResourceType.model.value
metadata: Dict[str, Any] = Field(
default_factory=dict,
description="Any additional metadata for this model",
)
@json_schema_type
class ModelDefWithProvider(ModelDef):
type: Literal["model"] = "model"
provider_id: str = Field(
description="The provider ID for this model",
)
@runtime_checkable
class Models(Protocol):
@webmethod(route="/models/list", method="GET")
async def list_models(self) -> List[ModelDefWithProvider]: ...
async def list_models(self) -> List[Model]: ...
@webmethod(route="/models/get", method="GET")
async def get_model(self, identifier: str) -> Optional[ModelDefWithProvider]: ...
async def get_model(self, identifier: str) -> Optional[Model]: ...
@webmethod(route="/models/register", method="POST")
async def register_model(self, model: ModelDefWithProvider) -> None: ...
async def register_model(
self,
model_id: str,
provider_model_id: Optional[str] = None,
provider_id: Optional[str] = None,
metadata: Optional[Dict[str, Any]] = None,
) -> Model: ...