[Feature]: Add as an online service endpoint for the OCR model like "/ocr"

[zhcn000000]

🚀 The feature, motivation and pitch

Add an online service endpoint for the OCR model to provide simple online services with dedicated OCR interfaces for LLM based ocr models, such as DeepSeek-OCR, PaddleOCR-VL, LightOnOCR, and GOTOCR, just like the speech-to-text endpoint, rather than only providing offline OCR interfaces

Alternatives

Request just like

class OCRRequest(OpenAIBaseModel):
    model: str
    image: str
    prompt: str

Response just like

class OCRResponse(OpenAIBaseModel):
    text: str
    model: str
    usage: dict 

Additional context

No response

Before submitting a new issue...

• Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

[heheda12345]

For online serving of OCR models, please refer to https://docs.vllm.ai/projects/recipes/en/latest/DeepSeek/DeepSeek-OCR.html#online-ocr-serving