feat: allow user-defined node- and relationship- properties in MultiHopSpecificQuerySynthesizer

- Users should be able to set the relationship type to use for identifying clusters and the relationship property used for identifying overlapping concepts within the triple.
- This will not change default behavior, but allows users to override.

Author: alex-graber-pmi

ragas/src/ragas/testset/synthesizers/multi_hop/specific.py

@@ -27,28 +27,19 @@
 
 @dataclass
 class MultiHopSpecificQuerySynthesizer(MultiHopQuerySynthesizer):
-    """
-    Synthesizes overlap based queries by choosing specific chunks and generating a
-    keyphrase from them and then generating queries based on that.
-
-    Attributes
-    ----------
-    generate_query_prompt : PydanticPrompt
-        The prompt used for generating the query.
-    """
+    """Synthesize multi-hop queries based on a chunk cluster defined by entity overlap."""
 
     name: str = "multi_hop_specific_query_synthesizer"
-    relation_type: str = "entities_overlap"
     property_name: str = "entities"
+    relation_type: str = "entities_overlap"
+    relation_overlap_property: str = "overlapped_items"
     theme_persona_matching_prompt: PydanticPrompt = ThemesPersonasMatchingPrompt()
     generate_query_reference_prompt: PydanticPrompt = QueryAnswerGenerationPrompt()
 
     def get_node_clusters(self, knowledge_graph: KnowledgeGraph) -> t.List[t.Tuple]:
-
+        """Identify clusters of nodes based on the specified relationship condition."""
         node_clusters = knowledge_graph.find_two_nodes_single_rel(
-            relationship_condition=lambda rel: (
-                True if rel.type == self.relation_type else False
-            )
+            relationship_condition=lambda rel: rel.type == self.relation_type
         )
         logger.info("found %d clusters", len(node_clusters))
         return node_clusters
@@ -61,7 +52,8 @@ async def _generate_scenarios(
         callbacks: Callbacks,
     ) -> t.List[MultiHopScenario]:
         """
-        Generates a list of scenarios on type MultiHopSpecificQuerySynthesizer
+        Generate a list of scenarios of type MultiHopScenario.
+
         Steps to generate scenarios:
         1. Filter the knowledge graph to find cluster of nodes or defined relation type. Here entities_overlap
         2. Calculate the number of samples that should be created per cluster to get n samples in total
@@ -87,7 +79,7 @@ async def _generate_scenarios(
             if len(scenarios) < n:
                 node_a, node_b = triplet[0], triplet[-1]
                 overlapped_items = []
-                overlapped_items = triplet[1].properties["overlapped_items"]
+                overlapped_items = triplet[1].properties[self.relation_overlap_property]
                 if overlapped_items:
                     themes = list(dict(overlapped_items).keys())
                     prompt_input = ThemesPersonasInput(