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" />
23 lines
671 B
Python
23 lines
671 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 pydantic import BaseModel
|
|
|
|
from .config import PassthroughImplConfig
|
|
|
|
|
|
class PassthroughProviderDataValidator(BaseModel):
|
|
url: str
|
|
api_key: str
|
|
|
|
|
|
async def get_adapter_impl(config: PassthroughImplConfig, _deps):
|
|
from .passthrough import PassthroughInferenceAdapter
|
|
|
|
assert isinstance(config, PassthroughImplConfig), f"Unexpected config type: {type(config)}"
|
|
impl = PassthroughInferenceAdapter(config)
|
|
await impl.initialize()
|
|
return impl
|