Deep copy txt units on local search to avoid race conditions (#1118)

* Deep copy txt units on local search to avoid race conditions * Format
microsoft · Sep 11, 2024 · cdf5fc4 · cdf5fc4
1 parent e7ee8cb
commit cdf5fc4
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 1 deletion.
diff --git a/.semversioner/next-release/patch-20240910212339849025.json b/.semversioner/next-release/patch-20240910212339849025.json
@@ -0,0 +1,4 @@
+{
+  "type": "patch",
+  "description": "Deep copy txt units on local search to avoid race conditions"
+}
diff --git a/graphrag/query/structured_search/local_search/mixed_context.py b/graphrag/query/structured_search/local_search/mixed_context.py
@@ -3,6 +3,7 @@
 """Algorithms to build context data for local search prompt."""
 
 import logging
+from copy import deepcopy
 from typing import Any
 
 import pandas as pd
@@ -319,7 +320,7 @@ def _build_text_unit_context(
             for text_id in entity.text_unit_ids or []:
                 if text_id not in text_unit_ids_set and text_id in self.text_units:
                     text_unit_ids_set.add(text_id)
-                    selected_unit = self.text_units[text_id]
+                    selected_unit = deepcopy(self.text_units[text_id])
                     num_relationships = count_relationships(
                         selected_unit, entity, self.relationships
                     )