mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 12:07:34 +00:00
ce77c27ff8
# What does this PR do? on the path to maintainable impls of inference providers. make all configs instances of RemoteInferenceProviderConfig. ## Test Plan ci
31 lines
907 B
Python
31 lines
907 B
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described in the LICENSE file in
|
|
# the root directory of this source tree.
|
|
|
|
from typing import Any
|
|
|
|
from pydantic import Field
|
|
|
|
from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
|
|
from llama_stack.schema_utils import json_schema_type
|
|
|
|
|
|
@json_schema_type
|
|
class RunpodImplConfig(RemoteInferenceProviderConfig):
|
|
url: str | None = Field(
|
|
default=None,
|
|
description="The URL for the Runpod model serving endpoint",
|
|
)
|
|
api_token: str | None = Field(
|
|
default=None,
|
|
description="The API token",
|
|
)
|
|
|
|
@classmethod
|
|
def sample_run_config(cls, **kwargs: Any) -> dict[str, Any]:
|
|
return {
|
|
"url": "${env.RUNPOD_URL:=}",
|
|
"api_token": "${env.RUNPOD_API_TOKEN}",
|
|
}
|