phase a audit

python/vector/vector_ingest.py

@@ -11,7 +11,8 @@ from pathlib import Path
 parser = argparse.ArgumentParser(description="Build FAISS index from NDJSON")
 
 parser.add_argument("--index", required=True, help="Path to index.ndjson")
-parser.add_argument("--out", required=True, help="Path to output vector.index")
+parser.add_argument("--out", required=True, help="Path to output vector.index (tmp)")
+
 parser.add_argument("--model", default="all-MiniLM-L6-v2", help="SentenceTransformer model")
 
 args = parser.parse_args()
@@ -82,13 +83,7 @@ with open(index_path, "r", encoding="utf-8") as f:
 if not texts:
     print("No chunks found. Removing vector index.")
 
-    if out_path.exists():
-        out_path.unlink()
-
-    meta_path = out_path.with_suffix(".meta.json")
-    if meta_path.exists():
-        meta_path.unlink()
-
+    # Entferne final erst später in PHP atomar
     sys.exit(0)
 
 print(f"Loaded {len(texts)} chunks.")
@@ -119,16 +114,19 @@ index.add(embeddings)
 # Ensure output directory exists
 out_path.parent.mkdir(parents=True, exist_ok=True)
 
+# ---------------------------------------------------------
+# Write FAISS index (tmp)
+# ---------------------------------------------------------
 print(f"Writing FAISS index to {out_path}")
 faiss.write_index(index, str(out_path))
 
 # ---------------------------------------------------------
-# Write ID mapping meta
+# Write ID mapping meta (tmp)
 # ---------------------------------------------------------
-meta_path = out_path.with_suffix(".meta.json")
+meta_tmp_path = Path(str(out_path) + ".meta.json")
 
-with open(meta_path, "w", encoding="utf-8") as f:
+with open(meta_tmp_path, "w", encoding="utf-8") as f:
     json.dump(ids, f)
 
 print(f"Indexed {len(ids)} chunks successfully.")
-sys.exit(0)
+sys.exit(0)