app/core/qdrant_points.py aktualisiert

app/core/qdrant_points.py

@@ -9,10 +9,7 @@ def _names(prefix: str) -> Tuple[str, str, str]:
 
 
 def _to_uuid(stable_key: str) -> str:
-    """
-    Erzeuge eine stabile UUIDv5 aus einem stabilen String-Key (z. B. note_id, chunk_id, edge_id).
-    Wir verwenden NAMESPACE_URL, damit die UUIDs deterministisch sind.
-    """
+    """Stabile UUIDv5 aus einem String-Key (deterministisch)."""
     return str(uuid.uuid5(uuid.NAMESPACE_URL, stable_key))
 
 
@@ -22,14 +19,12 @@ def points_for_note(
     note_vec: List[float] | None,
     dim: int,
 ) -> Tuple[str, List[rest.PointStruct]]:
-    """
-    (collection_name, [PointStruct]) für die Notes-Collection.
-    Falls kein Note-Embedding vorhanden -> Nullvektor der Länge `dim`.
-    """
+    """Notes-Collection: falls kein Note-Embedding -> Nullvektor der Länge dim."""
     notes_col, _, _ = _names(prefix)
     vector = note_vec if note_vec is not None else [0.0] * int(dim)
-    # Qdrant-Point-ID MUSS int oder UUID sein -> aus note_id eine UUIDv5 machen
-    point_id = _to_uuid(note_payload["note_id"])
+    # Qdrant-Point-ID MUSS int/UUID sein
+    raw_note_id = note_payload.get("note_id") or note_payload.get("id") or "missing-note-id"
+    point_id = _to_uuid(raw_note_id)
     pt = rest.PointStruct(id=point_id, vector=vector, payload=note_payload)
     return notes_col, [pt]
 
@@ -40,26 +35,42 @@ def points_for_chunks(
     vectors: List[List[float]],
 ) -> Tuple[str, List[rest.PointStruct]]:
     """
-    (collection_name, [PointStruct]) für die Chunks-Collection.
-    Erwartet pro Chunk einen Vektor (oder Nullvektor, wenn --skip-embed).
+    Chunks-Collection: erwartet pro Chunk einen Vektor.
+    Robustheit:
+      - Fehlt 'chunk_id', nutze 'id', sonst baue '${note_id}#${i}' (1-basiert).
+      - Schreibe die abgeleitete ID zurück in die Payload (pl['chunk_id']).
     """
     _, chunks_col, _ = _names(prefix)
     points: List[rest.PointStruct] = []
-    for pl, vec in zip(chunk_payloads, vectors):
-        point_id = _to_uuid(pl["chunk_id"])
+    for i, (pl, vec) in enumerate(zip(chunk_payloads, vectors), start=1):
+        chunk_id = pl.get("chunk_id") or pl.get("id")
+        if not chunk_id:
+            note_id = pl.get("note_id") or pl.get("parent_note_id") or "missing-note"
+            chunk_id = f"{note_id}#{i}"
+            pl["chunk_id"] = chunk_id  # persistenter Fallback in Payload
+        point_id = _to_uuid(chunk_id)
         points.append(rest.PointStruct(id=point_id, vector=vec, payload=pl))
     return chunks_col, points
 
 
 def points_for_edges(prefix: str, edge_payloads: List[dict]) -> Tuple[str, List[rest.PointStruct]]:
     """
-    (collection_name, [PointStruct]) für die Edges-Collection.
-    Edges-Collection ist ohne Vektor angelegt -> nur Payload + UUID-IDs.
+    Edges-Collection ohne Vektor.
+    Robustheit:
+      - Fehlt 'edge_id', dann konstruiere aus (kind, source_id, target_id, seq) eine stabile ID.
     """
     _, _, edges_col = _names(prefix)
     points: List[rest.PointStruct] = []
     for pl in edge_payloads:
-        point_id = _to_uuid(pl["edge_id"])
+        edge_id = pl.get("edge_id")
+        if not edge_id:
+            kind = pl.get("kind", "edge")
+            s = pl.get("source_id", "unknown-src")
+            t = pl.get("target_id", "unknown-tgt")
+            seq = pl.get("seq") or pl.get("order") or ""
+            edge_id = f"{kind}:{s}->{t}#{seq}"
+            pl["edge_id"] = edge_id
+        point_id = _to_uuid(edge_id)
         points.append(rest.PointStruct(id=point_id, payload=pl))
     return edges_col, points