Add multimodal module: receipt images to Java records on the real OpenAI, Anthropic and Ollama models against an OCR-backed local server, validation, repair retry, accuracy by photo condition

Co-Authored-By: Claude Sonnet 5.5 <[email protected]> Claude-Session: https://claude.ai/code/session_01JXVi2GMQ7bR5EmbUFdDj7N
2026-10-09 07:07:57 +00:00
parent b0bba995e6
commit d67ac0630b
31 changed files with 1339 additions and 0 deletions
@@ -0,0 +1,9 @@
+#!/usr/bin/env bash
+# Regenerates every file under output/ from the test suite. Needs the tesseract OCR program on the PATH
+# (apt install tesseract-ocr). No Docker, no API key, no network.
+set -euo pipefail
+cd "$(dirname "$0")/.."
+command -v tesseract >/dev/null || { echo "tesseract not found"; exit 1; }
+rm -rf target
+mvn -q -B test 2>&1 | grep -E "Tests run:|BUILD|FAIL" || true
+ls output