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
|
||||
|
||||
from pydantic import BaseModel
|
||||
|
||||
from surya.common.polygon import PolygonBox
|
||||
|
||||
|
||||
class BlockOCRResult(PolygonBox):
|
||||
label: str # canonicalized layout label (Picture, Text, ...)
|
||||
raw_label: str = "" # original model label
|
||||
reading_order: int # 0-indexed position in layout output
|
||||
html: str = "" # block HTML (BLOCK_PROMPT output, "" if skipped)
|
||||
skipped: bool = False # True if label was in SKIP_OCR_LABELS
|
||||
error: bool = False
|
||||
|
||||
|
||||
class PageOCRResult(BaseModel):
|
||||
blocks: List[BlockOCRResult]
|
||||
image_bbox: List[float]
|
||||
Reference in New Issue
Block a user