Adds ensure_blla_model.py which loads the blla segmentation model with
ketos on every container start. If the model is missing or in the legacy
PyTorch ZIP format (incompatible with ketos 7), it re-downloads the
correct CoreML protobuf model from Zenodo (DOI 10.5281/zenodo.14602569).
The Dockerfile now uses entrypoint.sh which runs this check before
starting uvicorn.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Two workers × ~5 GB Surya model load = ~10 GB required, exceeding the
8 GB memory cap and causing OOM on the first /train call. Two OS
processes also cause model-state divergence after training, contradicting
the single-node constraint documented in ADR-001.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- POST /train in ocr-service with ZIP Slip validation, TemporaryDirectory,
ketos transfer learning, timestamped backups (keep last 3), in-process reload
- X-Training-Token auth (no-op in dev when TRAINING_TOKEN env is empty)
- trainModel() in OcrClient interface + RestClientOcrClient (10-min timeout,
multipart upload, forwards X-Training-Token when configured)
- TRAINING_TOKEN env var wired in docker-compose; --workers 2 in Dockerfile
so /health stays responsive during synchronous training
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Kraken 7 requires pyvips (optional dep) for -f pdf mode.
Added libvips42 system package and pyvips Python package.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
torchvision installed from PyPI expects CUDA torch operator
registrations. Installing from the CPU whl index ensures torchvision
matches the CPU-only torch build. Fixes 'torchvision::nms does not
exist' RuntimeError on startup.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Python microservice (ocr-service/):
- FastAPI app with /ocr and /health endpoints
- Surya engine: transformer-based OCR for typewritten/modern handwriting
- Kraken engine: historical HTR for Kurrent/Suetterlin with
pure-Python polygon-to-quad approximation (gift wrapping + rotating calipers)
- Eager model loading at startup via lifespan context manager
- PDF download via httpx, page rendering via pypdfium2 at 300 DPI
Java RestClientOcrClient:
- Implements OcrClient + OcrHealthClient interfaces
- Calls Python service via Spring RestClient
- Health check with graceful fallback
Docker Compose:
- New ocr-service container (mem_limit 6g, no host ports)
- Health check with start_period 60s for model loading
- ocr_models volume for Kraken model files
- Backend depends on ocr-service health
Refs #226, #227
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
