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>
This commit is contained in:
@@ -0,0 +1,19 @@
|
||||
from typing import List, Optional
|
||||
|
||||
from pydantic import BaseModel
|
||||
|
||||
from surya.common.polygon import PolygonBox
|
||||
|
||||
|
||||
class LayoutBox(PolygonBox):
|
||||
label: str # canonicalized via LAYOUT_PRED_RELABEL
|
||||
raw_label: str # original model label, before canonicalization
|
||||
position: int # reading order index
|
||||
count: int = 0 # model's token estimate for OCR output (multiple of 50)
|
||||
|
||||
|
||||
class LayoutResult(BaseModel):
|
||||
bboxes: List[LayoutBox]
|
||||
image_bbox: List[float]
|
||||
raw: Optional[str] = None # raw model output, useful for debugging
|
||||
error: bool = False
|
||||
Reference in New Issue
Block a user