69519393c1
EasyOCR (deep-learning OCR) replaces Tesseract as the default engine for receipt images. It handles phone photos, thermal paper, dot-matrix fonts, and rotated images significantly better than Tesseract without requiring manual preprocessing pipelines. Key design decisions: - OCR_ENGINE=easyocr (default) | tesseract — switchable via .env, no rebuild - EasyOCR Reader is a module-level singleton: model loaded once per container start, not per receipt - Falls back to Tesseract automatically if EasyOCR fails or returns < 20 chars - EXIF rotation fix still applied before EasyOCR (phone photo orientation) - Images resized to max 2000px width for speed before passing to EasyOCR - _easyocr_to_text() groups detections into visual lines (y-overlap) and sorts left-to-right within each line for clean single-string output Revert: echo "OCR_ENGINE=tesseract" >> .env && docker compose up -d agent-service Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
24 lines
630 B
Plaintext
24 lines
630 B
Plaintext
fastapi==0.115.0
|
|
uvicorn[standard]==0.30.6
|
|
pydantic==2.9.2
|
|
pydantic-settings==2.5.2
|
|
asyncpg==0.29.0
|
|
anthropic==0.34.2
|
|
httpx==0.27.2
|
|
alembic==1.13.3
|
|
sqlalchemy[asyncio]==2.0.35
|
|
json-log-formatter==0.5.2
|
|
python-dotenv==1.0.1
|
|
mcp==1.3.0
|
|
ollama==0.3.3
|
|
# Receipt parsing — also requires: apt install tesseract-ocr (for image OCR)
|
|
pdfplumber==0.11.4
|
|
Pillow==10.4.0
|
|
pytesseract==0.3.13
|
|
# EasyOCR: deep-learning OCR, better on phone photos and difficult fonts.
|
|
# Set OCR_ENGINE=tesseract in .env to use Tesseract instead.
|
|
# Note: pulls in torch (~1.5GB) — only add if disk space allows.
|
|
easyocr
|
|
python-multipart==0.0.12
|
|
docker==7.1.0
|