Files
vLLM/vllm/entrypoints/generate/structured_decisions/api_router.py
T
d33872dfeb [Feat] Structured decisions endpoint (/v1/systemone) (#59299)
Signed-off-by: Matt Mastracci <matthew@mastracci.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Francisco Javier Arceo <4163062+franciscojavierarceo@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Francisco Javier Arceo <4163062+franciscojavierarceo@users.noreply.github.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
2026-10-08 14:48:12 +00:00

54 lines
1.8 KiB
Python

# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
from http import HTTPStatus
from fastapi import APIRouter, Depends, FastAPI, Request
from fastapi.responses import JSONResponse
from vllm.entrypoints.serve.engine.protocol import ErrorResponse
from vllm.entrypoints.serve.utils.api_utils import (
load_aware_call,
validate_json_request,
with_cancellation,
)
from .protocol import StructuredDecisionRequest
from .serving import ServingStructuredDecisions
router = APIRouter()
def structured_decisions(request: Request) -> ServingStructuredDecisions | None:
return getattr(request.app.state, "serving_structured_decisions", None)
@router.post(
"/v1/systemone",
dependencies=[Depends(validate_json_request)],
responses={
HTTPStatus.BAD_REQUEST.value: {"model": ErrorResponse},
HTTPStatus.NOT_FOUND.value: {"model": ErrorResponse},
HTTPStatus.INTERNAL_SERVER_ERROR.value: {"model": ErrorResponse},
HTTPStatus.NOT_IMPLEMENTED.value: {"model": ErrorResponse},
},
)
@with_cancellation
@load_aware_call
async def create_structured_decision(
request: StructuredDecisionRequest, raw_request: Request
):
handler = structured_decisions(raw_request)
if handler is None:
raise NotImplementedError(
"The model does not support the structured decision API"
)
result = await handler.create_decision(request, raw_request)
if isinstance(result, ErrorResponse):
return JSONResponse(content=result.model_dump(), status_code=result.error.code)
return JSONResponse(content=result.model_dump())
def register_structured_decisions_api_router(app: FastAPI):
if getattr(app.state.args, "enable_structured_decisions", False):
app.include_router(router)