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

add configuration to control which models are exposed

Browse source
This commit is contained in:
Ashwin Bharambe 2025-07-22 16:16:08 -07:00
parent 2e5ffab4e3
commit e3396513e9
7 changed files with 21 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

5
llama_stack/providers/remote/inference/fireworks/config.py
View file

@ -6,13 +6,14 @@
from typing import Any
from pydantic import BaseModel, Field, SecretStr
from pydantic import Field, SecretStr
from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
from llama_stack.schema_utils import json_schema_type
@json_schema_type
class FireworksImplConfig(BaseModel):
class FireworksImplConfig(RemoteInferenceProviderConfig):
url: str = Field(
default="https://api.fireworks.ai/inference/v1",
description="The URL for the Fireworks server",

2
llama_stack/providers/remote/inference/fireworks/fireworks.py
View file

@ -70,7 +70,7 @@ logger = get_logger(name=__name__, category="inference")
class FireworksInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProviderData):
def __init__(self, config: FireworksImplConfig) -> None:
ModelRegistryHelper.__init__(self, MODEL_ENTRIES)
ModelRegistryHelper.__init__(self, MODEL_ENTRIES, config.allowed_models)
self.config = config
async def initialize(self) -> None:

5
llama_stack/providers/remote/inference/together/config.py
View file

@ -6,13 +6,14 @@
from typing import Any
from pydantic import BaseModel, Field, SecretStr
from pydantic import Field, SecretStr
from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
from llama_stack.schema_utils import json_schema_type
@json_schema_type
class TogetherImplConfig(BaseModel):
class TogetherImplConfig(RemoteInferenceProviderConfig):
url: str = Field(
default="https://api.together.xyz/v1",
description="The URL for the Together AI server",

2
llama_stack/providers/remote/inference/together/together.py
View file

@ -66,7 +66,7 @@ logger = get_logger(name=__name__, category="inference")
class TogetherInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProviderData):
def __init__(self, config: TogetherImplConfig) -> None:
ModelRegistryHelper.__init__(self, MODEL_ENTRIES)
ModelRegistryHelper.__init__(self, MODEL_ENTRIES, config.allowed_models)
self.config = config
async def initialize(self) -> None: