fix: UnicodeEncode error when save/load knowledge graph (#1900)

Author: jjmachan

src/ragas/testset/graph.py

@@ -173,24 +173,51 @@ def _add_relationship(self, relationship: Relationship):
         self.relationships.append(relationship)
 
     def save(self, path: t.Union[str, Path]):
-        """Saves the knowledge graph to a JSON file."""
+        """Saves the knowledge graph to a JSON file.
+
+        Parameters
+        ----------
+        path : Union[str, Path]
+            Path where the JSON file should be saved.
+
+        Notes
+        -----
+        The file is saved using UTF-8 encoding to ensure proper handling of Unicode characters
+        across different platforms.
+        """
         if isinstance(path, str):
             path = Path(path)
 
         data = {
             "nodes": [node.model_dump() for node in self.nodes],
             "relationships": [rel.model_dump() for rel in self.relationships],
         }
-        with open(path, "w") as f:
+        with open(path, "w", encoding="utf-8") as f:
             json.dump(data, f, cls=UUIDEncoder, indent=2, ensure_ascii=False)
 
     @classmethod
     def load(cls, path: t.Union[str, Path]) -> "KnowledgeGraph":
-        """Loads a knowledge graph from a path."""
+        """Loads a knowledge graph from a path.
+
+        Parameters
+        ----------
+        path : Union[str, Path]
+            Path to the JSON file containing the knowledge graph.
+
+        Returns
+        -------
+        KnowledgeGraph
+            The loaded knowledge graph.
+
+        Notes
+        -----
+        The file is read using UTF-8 encoding to ensure proper handling of Unicode characters
+        across different platforms.
+        """
         if isinstance(path, str):
             path = Path(path)
 
-        with open(path, "r") as f:
+        with open(path, "r", encoding="utf-8") as f:
             data = json.load(f)
 
         nodes = [Node(**node_data) for node_data in data["nodes"]]

tests/unit/test_knowledge_graph_save.py

@@ -0,0 +1,62 @@
+from ragas.testset.graph import KnowledgeGraph, Node, NodeType, Relationship
+
+
+def test_knowledge_graph_save_with_problematic_chars(tmp_path):
+    # Create a knowledge graph with special characters
+    kg = KnowledgeGraph()
+
+    # Create nodes with various Unicode characters including ones that might cause charmap codec issues
+    problematic_chars = [
+        chr(i) for i in range(0x0080, 0x00FF)  # Extended ASCII/Latin-1 characters
+    ] + [
+        "\u2022",  # bullet
+        "\u2192",  # arrow
+        "\u2665",  # heart
+        "\u2605",  # star
+        "\u221E",  # infinity
+        "\u00B5",  # micro
+        "\u2264",  # less than or equal
+        "\u2265",  # greater than or equal
+        "\u0391",  # Greek letters
+        "\u0392",
+        "\u0393",
+        "\uFFFF",  # Special Unicode characters
+    ]
+
+    # Create multiple nodes with combinations of problematic characters
+    for i, char in enumerate(problematic_chars):
+        text = f"Test{char}Text with special char at position {i}"
+        node = Node(
+            properties={
+                "text": text,
+                "description": f"Node {i} with {char}",
+                "metadata": f"Extra {char} info",
+            },
+            type=NodeType.CHUNK,
+        )
+        kg.add(node)
+
+    # Add some relationships to make it more realistic
+    nodes = kg.nodes
+    for i in range(len(nodes) - 1):
+        rel = Relationship(
+            source=nodes[i],
+            target=nodes[i + 1],
+            type="next",
+            properties={"info": f"Link {i} with special char {problematic_chars[i]}"},
+        )
+        kg.add(rel)
+
+    # Try to save to a temporary file
+    save_path = tmp_path / "test_knowledge_graph.json"
+    kg.save(str(save_path))
+
+    # Try to load it back to verify
+    loaded_kg = KnowledgeGraph.load(str(save_path))
+
+    # Verify the content was preserved
+    assert len(loaded_kg.nodes) == len(kg.nodes)
+    assert len(loaded_kg.relationships) == len(kg.relationships)
+
+    # Verify the special characters were preserved in the first node
+    assert loaded_kg.nodes[0].properties["text"] == nodes[0].properties["text"]