[Frontend][2/n] Improve pooling entrypoints | embed. (#36110)

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
This commit is contained in:
wang.yuqi
2026-03-09 11:42:19 +08:00
committed by GitHub
parent c4d859c274
commit fff3711a24
20 changed files with 508 additions and 755 deletions
@@ -2,12 +2,10 @@
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
from fastapi import APIRouter, Depends, Request
from starlette.responses import JSONResponse
from fastapi.responses import JSONResponse, Response
from vllm.entrypoints.openai.utils import validate_json_request
from vllm.entrypoints.pooling.classify.protocol import (
ClassificationRequest,
)
from vllm.entrypoints.pooling.classify.protocol import ClassificationRequest
from vllm.entrypoints.pooling.classify.serving import ServingClassification
from vllm.entrypoints.utils import (
create_error_response,
@@ -19,7 +17,7 @@ router = APIRouter()
def classify(request: Request) -> ServingClassification | None:
return request.app.state.openai_serving_classification
return request.app.state.serving_classification
@router.post("/classify", dependencies=[Depends(validate_json_request)])
@@ -27,7 +25,7 @@ def classify(request: Request) -> ServingClassification | None:
@load_aware_call
async def create_classify(
request: ClassificationRequest, raw_request: Request
) -> JSONResponse:
) -> Response:
handler = classify(raw_request)
if handler is None:
error_response = create_error_response(