feat: Add OCR integration for automatic receipt data extraction

Implement Tesseract-based OCR to automatically extract vendor name,
date, total amount, and VAT from uploaded receipt images/PDFs,
reducing manual data entry and improving accuracy.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

data-entry-app/backend/app/schemas/ocr.py

@@ -0,0 +1,84 @@
+"""Pydantic schemas for OCR API."""
+
+from datetime import date
+from decimal import Decimal
+from typing import Optional
+
+from pydantic import BaseModel, Field
+
+
+class ExtractionData(BaseModel):
+    """Extracted receipt data from OCR."""
+
+    receipt_type: str = Field(default='bon_fiscal', description="Receipt type: bon_fiscal or chitanta")
+    receipt_number: Optional[str] = Field(default=None, description="Receipt number")
+    receipt_series: Optional[str] = Field(default=None, description="Receipt series")
+    receipt_date: Optional[date] = Field(default=None, description="Receipt date")
+    amount: Optional[Decimal] = Field(default=None, description="Total amount")
+    partner_name: Optional[str] = Field(default=None, description="Vendor/partner name")
+    cui: Optional[str] = Field(default=None, description="CUI (fiscal identification code)")
+    description: Optional[str] = Field(default=None, description="Optional description")
+
+    confidence_amount: float = Field(default=0.0, ge=0, le=1, description="Amount extraction confidence")
+    confidence_date: float = Field(default=0.0, ge=0, le=1, description="Date extraction confidence")
+    confidence_vendor: float = Field(default=0.0, ge=0, le=1, description="Vendor extraction confidence")
+    overall_confidence: float = Field(default=0.0, ge=0, le=1, description="Overall confidence score")
+    raw_text: str = Field(default="", description="Raw OCR text")
+
+    class Config:
+        """Pydantic config."""
+        json_schema_extra = {
+            "example": {
+                "receipt_type": "bon_fiscal",
+                "receipt_number": "12345",
+                "receipt_series": None,
+                "receipt_date": "2024-01-15",
+                "amount": 125.50,
+                "partner_name": "MEGA IMAGE SRL",
+                "cui": "12345678",
+                "description": None,
+                "confidence_amount": 0.95,
+                "confidence_date": 0.90,
+                "confidence_vendor": 0.75,
+                "overall_confidence": 0.87,
+                "raw_text": "BON FISCAL\nMEGA IMAGE SRL\n..."
+            }
+        }
+
+
+class OCRResponse(BaseModel):
+    """OCR API response."""
+
+    success: bool = Field(description="Whether OCR processing was successful")
+    message: str = Field(description="Status message")
+    data: Optional[ExtractionData] = Field(default=None, description="Extracted data")
+
+    class Config:
+        """Pydantic config."""
+        json_schema_extra = {
+            "example": {
+                "success": True,
+                "message": "OCR processing successful. Found: amount, date, vendor",
+                "data": {
+                    "receipt_type": "bon_fiscal",
+                    "receipt_number": "12345",
+                    "receipt_date": "2024-01-15",
+                    "amount": 125.50,
+                    "partner_name": "MEGA IMAGE SRL",
+                    "cui": "12345678",
+                    "confidence_amount": 0.95,
+                    "confidence_date": 0.90,
+                    "confidence_vendor": 0.75,
+                    "overall_confidence": 0.87,
+                    "raw_text": "BON FISCAL\nMEGA IMAGE SRL\n..."
+                }
+            }
+        }
+
+
+class OCRStatusResponse(BaseModel):
+    """OCR service status response."""
+
+    available: bool = Field(description="Whether OCR service is available")
+    engines: list[str] = Field(description="Available OCR engines")
+    message: str = Field(description="Status message")