marcel/familienarchiv
1
0
Fork 0
Code Issues 115 Pull Requests Actions Packages Projects Releases Wiki Activity

feat(ocr): add /train endpoint to OCR service and OcrClient.trainModel()

Browse Source 
- 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>
This commit is contained in:
Marcel
2026-04-13 14:40:53 +02:00
parent cfa3c4df67
commit bc97a2dade
6 changed files with 188 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
backend/src/test/java/org/raddatz/familienarchiv/service/OcrClientDefaultStreamTest.java
View File

@@ -12,10 +12,15 @@ class OcrClientDefaultStreamTest {
@Test
void defaultStreamBlocksSynthesizesEventsFromExtractBlocks() {
OcrClient client = (pdfUrl, scriptType) -> List.of(
new OcrBlockResult(0, 0.1, 0.1, 0.8, 0.04, null, "Line 1"),
new OcrBlockResult(0, 0.1, 0.2, 0.8, 0.04, null, "Line 2"),
new OcrBlockResult(1, 0.1, 0.1, 0.8, 0.04, null, "Line 3"));
OcrClient client = new OcrClient() {
@Override public List<OcrBlockResult> extractBlocks(String pdfUrl, ScriptType scriptType) {
return List.of(
new OcrBlockResult(0, 0.1, 0.1, 0.8, 0.04, null, "Line 1"),
new OcrBlockResult(0, 0.1, 0.2, 0.8, 0.04, null, "Line 2"),
new OcrBlockResult(1, 0.1, 0.1, 0.8, 0.04, null, "Line 3"));
}
@Override public TrainingResult trainModel(byte[] zip) { return null; }
};
List<OcrStreamEvent> events = new ArrayList<>();
client.streamBlocks("http://test", ScriptType.TYPEWRITER, events::add);
@@ -42,7 +47,10 @@ class OcrClientDefaultStreamTest {
@Test
void defaultStreamBlocksHandlesEmptyResults() {
OcrClient client = (pdfUrl, scriptType) -> List.of();
OcrClient client = new OcrClient() {
@Override public List<OcrBlockResult> extractBlocks(String pdfUrl, ScriptType scriptType) { return List.of(); }
@Override public TrainingResult trainModel(byte[] zip) { return null; }
};
List<OcrStreamEvent> events = new ArrayList<>();
client.streamBlocks("http://test", ScriptType.TYPEWRITER, events::add);