54cbd49171
All checks were successful
Deploy to Staging / Build Images (pull_request) Successful in 31s
Deploy to Staging / Deploy to Staging (pull_request) Successful in 31s
Deploy to Staging / Verify Staging (pull_request) Successful in 2m19s
Deploy to Staging / Notify Staging Ready (pull_request) Successful in 8s
Deploy to Staging / Notify Staging Failure (pull_request) Has been skipped
Implement VIN-specific OCR extraction with optimized preprocessing: - Add POST /extract/vin endpoint for VIN extraction - VIN preprocessor: CLAHE, deskew, denoise, adaptive threshold - VIN validator: check digit validation, OCR error correction (I->1, O->0) - VIN extractor: PSM modes 6/7/8, character whitelist, alternatives - Response includes confidence, bounding box, and alternatives - Unit tests for validator and preprocessor - Integration tests for VIN extraction endpoint Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
96 lines
2.3 KiB
Python
96 lines
2.3 KiB
Python
"""Pydantic models for OCR API request/response validation."""
|
|
from enum import Enum
|
|
from typing import Optional
|
|
|
|
from pydantic import BaseModel, Field
|
|
|
|
|
|
class DocumentType(str, Enum):
|
|
"""Types of documents that can be processed."""
|
|
|
|
VIN = "vin"
|
|
RECEIPT = "receipt"
|
|
MANUAL = "manual"
|
|
UNKNOWN = "unknown"
|
|
|
|
|
|
class ExtractedField(BaseModel):
|
|
"""A single extracted field with confidence score."""
|
|
|
|
value: str
|
|
confidence: float = Field(ge=0.0, le=1.0)
|
|
|
|
|
|
class BoundingBox(BaseModel):
|
|
"""Bounding box for detected region."""
|
|
|
|
x: int
|
|
y: int
|
|
width: int
|
|
height: int
|
|
|
|
|
|
class VinAlternative(BaseModel):
|
|
"""Alternative VIN candidate."""
|
|
|
|
vin: str
|
|
confidence: float = Field(ge=0.0, le=1.0)
|
|
|
|
|
|
class VinExtractionResponse(BaseModel):
|
|
"""Response from VIN extraction endpoint."""
|
|
|
|
success: bool
|
|
vin: Optional[str] = None
|
|
confidence: float = Field(ge=0.0, le=1.0)
|
|
bounding_box: Optional[BoundingBox] = Field(default=None, alias="boundingBox")
|
|
alternatives: list[VinAlternative] = Field(default_factory=list)
|
|
processing_time_ms: int = Field(alias="processingTimeMs")
|
|
error: Optional[str] = None
|
|
|
|
model_config = {"populate_by_name": True}
|
|
|
|
|
|
class OcrResponse(BaseModel):
|
|
"""Response from OCR extraction."""
|
|
|
|
success: bool
|
|
document_type: DocumentType = Field(alias="documentType")
|
|
raw_text: str = Field(alias="rawText")
|
|
confidence: float = Field(ge=0.0, le=1.0)
|
|
extracted_fields: dict[str, ExtractedField] = Field(
|
|
default_factory=dict, alias="extractedFields"
|
|
)
|
|
processing_time_ms: int = Field(alias="processingTimeMs")
|
|
|
|
model_config = {"populate_by_name": True}
|
|
|
|
|
|
class JobStatus(str, Enum):
|
|
"""Status of an async OCR job."""
|
|
|
|
PENDING = "pending"
|
|
PROCESSING = "processing"
|
|
COMPLETED = "completed"
|
|
FAILED = "failed"
|
|
|
|
|
|
class JobResponse(BaseModel):
|
|
"""Response for async job status."""
|
|
|
|
job_id: str = Field(alias="jobId")
|
|
status: JobStatus
|
|
progress: Optional[int] = Field(default=None, ge=0, le=100)
|
|
result: Optional[OcrResponse] = None
|
|
error: Optional[str] = None
|
|
|
|
model_config = {"populate_by_name": True}
|
|
|
|
|
|
class JobSubmitRequest(BaseModel):
|
|
"""Request to submit an async OCR job."""
|
|
|
|
callback_url: Optional[str] = Field(default=None, alias="callbackUrl")
|
|
|
|
model_config = {"populate_by_name": True}
|