Signed-off-by: zjy0516 <riverclouds.zhu@qq.com> Signed-off-by: Isotr0py <Isotr0py@outlook.com> Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com> Co-authored-by: Isotr0py <Isotr0py@outlook.com>
92 lines
3.2 KiB
Python
92 lines
3.2 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
from argparse import Namespace
|
|
from http import HTTPStatus
|
|
from typing import Any
|
|
|
|
from fastapi import APIRouter, Depends, FastAPI, Request
|
|
from fastapi.responses import JSONResponse
|
|
from starlette.datastructures import State
|
|
|
|
from vllm.engine.protocol import EngineClient
|
|
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 vllm.entrypoints.serve.utils.request_logger import RequestLogger
|
|
from vllm.logger import init_logger
|
|
from vllm.renderers.chat_utils import load_chat_template
|
|
from vllm.tasks import SupportedTask
|
|
|
|
from .protocol import StructuredDecisionRequest
|
|
from .serving import ServingStructuredDecisions
|
|
from .strategies import ReadContext, select_read_strategy
|
|
|
|
logger = init_logger(__name__)
|
|
|
|
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):
|
|
app.include_router(router)
|
|
|
|
|
|
def init_structured_decisions_state(
|
|
engine_client: EngineClient,
|
|
state: State,
|
|
args: Namespace,
|
|
request_logger: RequestLogger | None,
|
|
supported_tasks: tuple[SupportedTask, ...],
|
|
default_chat_template_kwargs: dict[str, Any],
|
|
):
|
|
state.serving_structured_decisions = None
|
|
try:
|
|
strategy_cls = select_read_strategy(engine_client.model_config, supported_tasks)
|
|
strategy = strategy_cls(
|
|
ReadContext(
|
|
engine_client=engine_client,
|
|
online_renderer=state.online_renderer,
|
|
chat_template=load_chat_template(args.chat_template),
|
|
chat_template_content_format=args.chat_template_content_format,
|
|
default_chat_template_kwargs=default_chat_template_kwargs,
|
|
)
|
|
)
|
|
except ValueError as e:
|
|
logger.debug("/v1/systemone is disabled: %s", e)
|
|
return
|
|
state.serving_structured_decisions = ServingStructuredDecisions(
|
|
state.openai_serving_models, strategy, request_logger=request_logger
|
|
)
|