forked from phoenix-oss/llama-stack-mirror
2b995c22eb
## What does this PR do? In this PR, we implement a passthrough inference provider that works for any endpoints that respect llama stack inference API definition. ## Test Plan config some endpoint that respect llama stack inference API definition and got the inference results successfully <img width="1268" alt="Screenshot 2025-02-19 at 8 52 51 PM" src="https://github.com/user-attachments/assets/447816e4-ea7a-4365-b90c-386dc7dcf4a1" />
31 lines
849 B
Python
31 lines
849 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, Dict, Optional
|
|
|
|
from pydantic import BaseModel, Field, SecretStr
|
|
|
|
from llama_stack.schema_utils import json_schema_type
|
|
|
|
|
|
@json_schema_type
|
|
class PassthroughImplConfig(BaseModel):
|
|
url: str = Field(
|
|
default=None,
|
|
description="The URL for the passthrough endpoint",
|
|
)
|
|
|
|
api_key: Optional[SecretStr] = Field(
|
|
default=None,
|
|
description="API Key for the passthrouth endpoint",
|
|
)
|
|
|
|
@classmethod
|
|
def sample_run_config(cls, **kwargs) -> Dict[str, Any]:
|
|
return {
|
|
"url": "${env.PASSTHROUGH_URL}",
|
|
"api_key": "${env.PASSTHROUGH_API_KEY}",
|
|
}
|