Fu DaiandClaude Opus 4.8
1a585693be
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>
20 lines
568 B
Python
20 lines
568 B
Python
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]
|