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>

.gitignore

@@ -0,0 +1,27 @@
+# Python bytecode
+__pycache__/
+*.py[cod]
+
+# Logs
+logs/
+*.log
+
+# Virtualenvs, caches, agent tooling
+.venv*/
+.pytest_cache/
+.agents/
+.codex/
+
+# Benchmark / eval / quantization artifacts (kept on disk, never in git)
+results/
+baseline_outputs/
+eval_set/
+
+# Local docs / working notes
+docs/
+
+# Scratch OCR inputs/outputs
+temp_image_*
+output.json
+compare_out/
+*.pdf