LMSYS

Extract Text (SGLang)

Sends each Image to an OCR vision-language model served by a local SGLang sidecar over the OpenAI-compatible chat endpoint, then emits a joined String transcript or per-block regions with Polygon/Rectangle bounds and confidence.

Analyze Image (SGLang VLM)

Sends one or more images plus a String prompt to a vision-language model served by a local SGLang sidecar and returns the model's reply as a String. The image input is a oneof spanning a single image, an image-with-label, a batch, or labeled batch.

Generate Text (SGLang)

Drives a chat turn against a colocated SGLang service from a user and system String, streaming the reply as String chunks and closing with a StreamEnd; supports JSON-object output and rolling conversation history.