mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
a483a58c6e
# What does this PR do? with the new /v1/providers API, /v1/inspect/providers is duplicative, deprecate it by removing the route, and add a test for the full /v1/providers API resolves #1623 ## Test Plan `uv run pytest -v tests/integration/providers --stack-config=ollama --text-model="meta-llama/Llama-3.2-3B-Instruct" --embedding-model=all-MiniLM-L6-v2` <img width="1512" alt="Screenshot 2025-03-18 at 9 18 38 AM" src="https://github.com/user-attachments/assets/2db30f25-3ff6-4374-b39d-0047f093fe36" /> Signed-off-by: Charlie Doern <cdoern@redhat.com>
45 lines
1 KiB
Python
45 lines
1 KiB
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 List, Protocol, runtime_checkable
|
|
|
|
from pydantic import BaseModel
|
|
|
|
from llama_stack.schema_utils import json_schema_type, webmethod
|
|
|
|
|
|
@json_schema_type
|
|
class RouteInfo(BaseModel):
|
|
route: str
|
|
method: str
|
|
provider_types: List[str]
|
|
|
|
|
|
@json_schema_type
|
|
class HealthInfo(BaseModel):
|
|
status: str
|
|
# TODO: add a provider level status
|
|
|
|
|
|
@json_schema_type
|
|
class VersionInfo(BaseModel):
|
|
version: str
|
|
|
|
|
|
class ListRoutesResponse(BaseModel):
|
|
data: List[RouteInfo]
|
|
|
|
|
|
@runtime_checkable
|
|
class Inspect(Protocol):
|
|
@webmethod(route="/inspect/routes", method="GET")
|
|
async def list_routes(self) -> ListRoutesResponse: ...
|
|
|
|
@webmethod(route="/health", method="GET")
|
|
async def health(self) -> HealthInfo: ...
|
|
|
|
@webmethod(route="/version", method="GET")
|
|
async def version(self) -> VersionInfo: ...
|