forked from phoenix-oss/llama-stack-mirror
feat: inference passthrough provider (#1166)
## 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" />
This commit is contained in:
parent
d39f8de619
commit
2b995c22eb
6 changed files with 364 additions and 0 deletions
|
@ -0,0 +1,23 @@
|
|||
# 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
|
Loading…
Add table
Add a link
Reference in a new issue