Add standalone GeminiEngine class for maintenance schedule extraction
from PDF owners manuals using Vertex AI Gemini 2.5 Flash with structured
JSON output enforcement, 20MB size limit, and lazy initialization.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add VISION_MONTHLY_LIMIT config setting (default 1000)
- Update CloudEngine to use WIF credential config via ADC
- Rewrite HybridEngine to support cloud-primary with Redis counter
- Pass monthly_limit through engine factory
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add engine abstraction tests and update docs to reflect PaddleOCR primary
architecture with optional Google Vision cloud fallback.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
CloudEngine wraps Google Vision TEXT_DETECTION with lazy init.
HybridEngine runs primary engine, falls back to cloud when confidence
is below threshold. Disabled by default (OCR_FALLBACK_ENGINE=none).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace direct pytesseract calls with OcrEngine interface in vin_extractor.py,
receipt_extractor.py, and ocr_service.py. PSM mode fallbacks replaced with
engine-agnostic single-line/single-word configs. Dead _process_ocr_data removed.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Introduce pluggable OcrEngine ABC with PaddleOCR PP-OCRv4 as primary
engine and Tesseract wrapper for backward compatibility. Engine factory
reads OCR_PRIMARY_ENGINE config to instantiate the correct engine.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When OCR reads extra characters (e.g. sticker border as 'C', spurious
'Z' insertion), the raw text exceeds 17 chars and the old first-17
trim produced wrong VINs. New strategy tries all 17-char sliding
windows and single/double character deletions, validating each via
check digit. For 'CWVGGNPE2Z4NP069500', this finds the correct VIN
'WVGGNPE24NP069500' (valid check digit) instead of 'CWVGGNPE2Z4NP0695'
(invalid).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
tessedit_char_whitelist does not work with OEM 1 (LSTM engine) and
causes empty/erratic output. This was the root cause of Tesseract
returning empty text despite clear, well-preprocessed images.
Character filtering is already handled post-OCR by the VIN validator's
correct_ocr_errors() method (I->1, O->0, Q->0, etc).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The min-channel correctly extracts contrast (white text=255 vs green
sticker bg=130), but Tesseract expects dark text on light background.
Without inversion, the grayscale-only path returned empty text for
every PSM mode because Tesseract couldn't see bright-on-dark text.
Invert via bitwise_not: text becomes 0 (black), sticker bg becomes
125 (gray). Fixes all three OCR paths (adaptive, grayscale, Otsu).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Two fixes:
1. Always use min-channel for color images instead of gated comparison
that was falling back to standard grayscale (which has only 23%
contrast for white-on-green VIN stickers).
2. Add grayscale-only OCR path (CLAHE + denoise, no thresholding)
between adaptive and Otsu attempts. Tesseract's LSTM engine is
designed to handle grayscale input directly and often outperforms
binarized input where thresholding creates artifacts.
Pipeline order: adaptive threshold → grayscale-only → Otsu threshold
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace std-based channel selection (which incorrectly picked green for
green-tinted VIN stickers) with per-pixel min(B,G,R). White text stays
255 in all channels while colored backgrounds drop to their weakest
channel value, giving 2x contrast improvement. Add morphological
opening after thresholding to remove noise speckles from car body
surface that were confusing Tesseract's page segmentation.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
White text on green VIN stickers has only ~12% contrast in standard
grayscale conversion because the green channel dominates luminance.
The new _best_contrast_channel method evaluates each RGB channel's
standard deviation and selects the one with highest contrast, giving
~2x improvement for green-tinted VIN stickers. Falls back to standard
grayscale for neutral-colored images.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Save original, adaptive, and Otsu preprocessed images to
/tmp/vin-debug/{timestamp}/ when LOG_LEVEL is set to debug.
No images saved at info level. Volume mount added for access.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace filesystem-based debug system (VIN_DEBUG_DIR) with standard
logger.debug() calls that flow through Loki when LOG_LEVEL=DEBUG.
Use .env.logging variable for OCR LOG_LEVEL. Increase image capture
quality to 0.95 for better OCR accuracy.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Implement async PDF processing for owner's manuals with maintenance
schedule extraction:
- Add PDF preprocessor with PyMuPDF for text/scanned PDF handling
- Add maintenance pattern matching (mileage, time, fluid specs)
- Add service name mapping to maintenance subtypes
- Add table detection and parsing for schedule tables
- Add manual extractor orchestrating the complete pipeline
- Add POST /extract/manual endpoint for async job submission
- Add Redis job queue support for manual extraction jobs
- Add progress tracking during processing
Processing pipeline:
1. Analyze PDF structure (text layer vs scanned)
2. Find maintenance schedule sections
3. Extract text or OCR scanned pages at 300 DPI
4. Detect and parse maintenance tables
5. Normalize service names and extract intervals
6. Return structured maintenance schedules with confidence scores
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implement receipt-specific OCR extraction for fuel receipts:
- Pattern matching modules for date, currency, and fuel data extraction
- Receipt-optimized image preprocessing for thermal receipts
- POST /extract/receipt endpoint with field extraction
- Confidence scoring per extracted field
- Cross-validation of fuel receipt data
- Unit tests for all pattern matchers
Extracted fields: merchantName, transactionDate, totalAmount,
fuelQuantity, pricePerUnit, fuelGrade
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
OCR Service (Python/FastAPI):
- POST /extract for synchronous OCR extraction
- POST /jobs and GET /jobs/{job_id} for async processing
- Image preprocessing (deskew, denoise) for accuracy
- HEIC conversion via pillow-heif
- Redis job queue for async processing
Backend (Fastify):
- POST /api/ocr/extract - authenticated proxy to OCR
- POST /api/ocr/jobs - async job submission
- GET /api/ocr/jobs/:jobId - job polling
- Multipart file upload handling
- JWT authentication required
File size limits: 10MB sync, 200MB async
Processing time target: <3 seconds for typical photos
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add Python-based OCR service container (mvp-ocr) as the 6th service:
- Python 3.11-slim with FastAPI/uvicorn
- Tesseract OCR with English language pack
- pillow-heif for HEIC image support
- opencv-python-headless for image preprocessing
- Health endpoint at /health
- Unit tests for health, HEIC support, and Tesseract availability
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
