refactor: rename mathod_params

Author: ChenZiHong-Gavin

graphgen/configs/aggregated_config.yaml

@@ -12,7 +12,7 @@ quiz_and_judge: # quiz and test whether the LLM masters the knowledge points
   re_judge: false # whether to re-judge the existing quiz samples
 partition: # graph partition configuration
   method: ece # ece is a custom partition method based on comprehension loss
-  ece_params:
+  method_params:
     bidirectional: true # whether to traverse the graph in both directions
     edge_sampling: max_loss # edge sampling strategy, support: random, max_loss, min_loss
     expand_method: max_width # expand method, support: max_width, max_depth

graphgen/configs/atomic_config.yaml

@@ -12,7 +12,7 @@ quiz_and_judge: # quiz and test whether the LLM masters the knowledge points
   re_judge: false # whether to re-judge the existing quiz samples
 partition: # graph partition configuration
   method: ece # ece is a custom partition method based on comprehension loss
-  ece_params:
+  method_params:
     bidirectional: true # whether to traverse the graph in both directions
     edge_sampling: max_loss # edge sampling strategy, support: random, max_loss, min_loss
     expand_method: max_width # expand method, support: max_width, max_depth

graphgen/configs/cot_config.yaml

@@ -10,7 +10,7 @@ quiz_and_judge: # quiz and test whether the LLM masters the knowledge points
   enabled: false
 partition: # graph partition configuration
   method: leiden # leiden is a community detection algorithm
-  leiden_params:
+  method_params:
     max_size: 20 # Maximum size of communities
     use_lcc: false
     random_seed: 42

graphgen/configs/multi_hop_config.yaml

@@ -12,7 +12,7 @@ quiz_and_judge: # quiz and test whether the LLM masters the knowledge points
   re_judge: false # whether to re-judge the existing quiz samples
 partition: # graph partition configuration
   method: ece # ece is a custom partition method based on comprehension loss
-  ece_params:
+  method_params:
     bidirectional: true # whether to traverse the graph in both directions
     edge_sampling: max_loss # edge sampling strategy, support: random, max_loss, min_loss
     expand_method: max_width # expand method, support: max_width, max_depth

graphgen/graphgen.py

@@ -242,7 +242,7 @@ async def generate(self, partition_config: Dict, generate_config: Dict):
                 self.synthesizer_llm_client,
                 self.tokenizer_instance,
                 self.graph_storage,
-                partition_config["ece_params"],
+                partition_config["method_params"],
                 self.text_chunks_storage,
                 self.progress_bar,
             )
@@ -251,7 +251,7 @@ async def generate(self, partition_config: Dict, generate_config: Dict):
                 self.synthesizer_llm_client,
                 self.tokenizer_instance,
                 self.graph_storage,
-                partition_config["ece_params"],
+                partition_config["method_params"],
                 self.text_chunks_storage,
                 self.progress_bar,
             )
@@ -260,15 +260,15 @@ async def generate(self, partition_config: Dict, generate_config: Dict):
                 self.synthesizer_llm_client,
                 self.tokenizer_instance,
                 self.graph_storage,
-                partition_config["ece_params"],
+                partition_config["method_params"],
                 self.text_chunks_storage,
                 self.progress_bar,
             )
         elif mode == "cot":
             results = await generate_cot(
                 self.graph_storage,
                 self.synthesizer_llm_client,
-                method_params=partition_config["leiden_params"],
+                method_params=partition_config["method_params"],
             )
         else:
             raise ValueError(f"Unknown generation mode: {mode}")