Suya OCR API — vLLM-backed, OpenAI-compatible OCR service

FastAPI service wrapping the Surya-OCR-2 model (datalab-to) served through vLLM:
legacy /v1/api/ai/* endpoints, an OpenAI-compatible /v1/chat/completions endpoint,
a coalescing request batcher, a local OCR CLI, Docker packaging, multilingual
example outputs, and quantization/concurrency benchmarks.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

surya/debug/text.py

@@ -0,0 +1,8 @@
+from PIL import Image, ImageDraw
+
+
+def get_text_size(text, font):
+    im = Image.new(mode="P", size=(0, 0))
+    draw = ImageDraw.Draw(im)
+    _, _, width, height = draw.textbbox((0, 0), text=text, font=font)
+    return width, height