Skip to content

vllm.entrypoints.openai.chat_completion.api_router

render_chat_completion async 

render_chat_completion(
    request: ChatCompletionRequest, raw_request: Request
)

Render chat completion request and return conversation and engine prompts without generating.

Source code in vllm/entrypoints/openai/chat_completion/api_router.py 
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
@router.post(
    "/v1/chat/completions/render",
    dependencies=[Depends(validate_json_request)],
    response_model=list,
    responses={
        HTTPStatus.BAD_REQUEST.value: {"model": ErrorResponse},
        HTTPStatus.NOT_FOUND.value: {"model": ErrorResponse},
        HTTPStatus.INTERNAL_SERVER_ERROR.value: {"model": ErrorResponse},
    },
)
async def render_chat_completion(request: ChatCompletionRequest, raw_request: Request):
    """Render chat completion request and return conversation and engine
    prompts without generating."""
    handler = chat(raw_request)
    if handler is None:
        base_server = raw_request.app.state.openai_serving_tokenization
        return base_server.create_error_response(
            message="The model does not support Chat Completions API"
        )

    try:
        result = await handler.render_chat_request(request)
    except Exception as e:
        return handler.create_error_response(e)

    if isinstance(result, ErrorResponse):
        return JSONResponse(content=result.model_dump(), status_code=result.error.code)

    return JSONResponse(content=result)