Merge branch 'feature/vqa-pipeline' of https://github.com/open-sciencelab/GraphGen into feature/vqa-pipeline

Author: ChenZiHong-Gavin

graphgen/models/partitioner/anchor_bfs_partitioner.py

@@ -101,7 +101,7 @@ async def _pick_anchor_ids(
 
         anchor_ids: Set[str] = set()
         for node_id, meta in nodes:
-            node_type = str(meta.get("entity_type") or "").lower()
+            node_type = str(meta.get("entity_type", "")).lower()
             if self.anchor_type.lower() in node_type:
                 anchor_ids.add(node_id)
         return anchor_ids

graphgen/models/reader/csv_reader.py

@@ -10,7 +10,7 @@ def read(self, file_path: str) -> List[Dict[str, Any]]:
 
         df = pd.read_csv(file_path)
         for _, row in df.iterrows():
-            if row.get("type") == "text" and self.text_column not in row:
+            if "type" in row and row["type"] == "text" and self.text_column not in row:
                 raise ValueError(
                     f"Missing '{self.text_column}' in document: {row.to_dict()}"
                 )