first commit

Co-authored-by: Cursor <cursoragent@cursor.com>

scripts/run_all_samples.py

@@ -0,0 +1,42 @@
+"""Run chunking on all sample files in data/."""
+
+from __future__ import annotations
+
+import sys
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).resolve().parent.parent / "backend"))
+
+from rag_cut.models import SplitConfig, SplitMode
+from rag_cut.pipeline import chunk_document
+
+DATA = Path(__file__).resolve().parent.parent / "data"
+OUT = Path(__file__).resolve().parent.parent / "storage"
+
+
+def main() -> None:
+    for path in sorted(DATA.iterdir()):
+        if not path.is_file():
+            continue
+        ext = path.suffix.lower()
+        if ext == ".xlsx":
+            config = SplitConfig(mode=SplitMode.BY_ROW, rows_per_chunk=5)
+        else:
+            config = SplitConfig(mode=SplitMode.DEFAULT)
+
+        print(f"\n{'=' * 60}\n{path.name} ({ext})")
+        result = chunk_document(path, config=config)
+        print(f"blocks={result.block_count} chunks={result.chunk_count} mode={result.split_mode.value}")
+
+        out_file = OUT / f"{path.stem}_chunks.json"
+        out_file.write_text(result.model_dump_json(indent=2), encoding="utf-8")
+        print(f"saved -> {out_file.name}")
+
+        if result.chunks:
+            c0 = result.chunks[0]
+            print(f"chunk[0] types={c0.block_types} chars={c0.char_count}")
+            print(c0.content[:300].replace("\n", " ") + "...")
+
+
+if __name__ == "__main__":
+    main()