feat: persist ocr_quality_score and use it for numeric filtering

Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>
2026-03-01 13:46:43 +00:00
parent 705b970522
commit 83c3405c98
8 changed files with 120 additions and 42 deletions
@@ -122,6 +122,12 @@ def _run_schema_migrations(engine: Any) -> None:
                conn.execute(text("ALTER TABLE files ADD COLUMN document_title VARCHAR"))
            logger.info("Migration complete: 'document_title' column added to files")

+        if "ocr_quality_score" not in columns:
+            logger.info("Migrating files: adding 'ocr_quality_score' column")
+            with engine.begin() as conn:
+                conn.execute(text("ALTER TABLE files ADD COLUMN ocr_quality_score INTEGER"))
+            logger.info("Migration complete: 'ocr_quality_score' column added to files")
+
        # Migration: Drop unique index on filehash to allow duplicate records
        try:
            indexes = inspector.get_indexes("files")