vLLM

Extract Text (vLLM)

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

Generate Text (vLLM)

Drives a chat turn against a colocated vLLM service from a user and system String, streaming the reply as String chunks and closing with a StreamEnd; supports history and parallel stateless turns. Prefer generate_text_sglang for SGLang.

Analyze Image (vLLM VLM)

Sends one or more images plus a String prompt to a vision-language model served by a local vLLM 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.