[Bugfix][Frontend] Expose completion response schemas in OpenAPI (#60926)

Signed-off-by: Guan Luo <gluo@nvidia.com>
Signed-off-by: sfeng33 <4florafeng@gmail.com>
Co-authored-by: sfeng33 <4florafeng@gmail.com>
This commit is contained in:
GuanLuo
2026-10-13 18:54:06 +00:00
committed by GitHub
co-authored by sfeng33
parent c5bda658d2
commit 6d1daa9fe5
5 changed files with 220 additions and 15 deletions
@@ -10,10 +10,12 @@ from fastapi.responses import JSONResponse, StreamingResponse
from vllm.entrypoints.openai.completion.protocol import (
CompletionRequest,
CompletionResponse,
CompletionStreamResponse,
)
from vllm.entrypoints.openai.completion.serving import OpenAIServingCompletion
from vllm.entrypoints.serve.engine.protocol import ErrorResponse
from vllm.entrypoints.serve.utils.api_utils import (
json_or_sse_responses,
load_aware_call,
validate_json_request,
with_cancellation,
@@ -35,12 +37,15 @@ def completion(request: Request) -> OpenAIServingCompletion | None:
@router.post(
"/v1/completions",
dependencies=[Depends(validate_json_request)],
responses={
HTTPStatus.OK.value: {"content": {"text/event-stream": {}}},
HTTPStatus.BAD_REQUEST.value: {"model": ErrorResponse},
HTTPStatus.NOT_FOUND.value: {"model": ErrorResponse},
HTTPStatus.INTERNAL_SERVER_ERROR.value: {"model": ErrorResponse},
},
**json_or_sse_responses(
CompletionResponse,
CompletionStreamResponse,
{
HTTPStatus.BAD_REQUEST.value: {"model": ErrorResponse},
HTTPStatus.NOT_FOUND.value: {"model": ErrorResponse},
HTTPStatus.INTERNAL_SERVER_ERROR.value: {"model": ErrorResponse},
},
),
)
@with_cancellation
@load_aware_call