fix - in run_local_search(), avoid re-reading create_final_nodes.parquet file (#592)

ksachdeva · web-flow · commit e8df283b2472 · 2024-07-24T15:26:37.000-04:00
diff --git a/.semversioner/next-release/patch-20240724150548966311.json b/.semversioner/next-release/patch-20240724150548966311.json
@@ -0,0 +1,4 @@
+{
+  "type": "patch",
+  "description": "remove duplicate file read"
+}
diff --git a/graphrag/query/cli.py b/graphrag/query/cli.py
@@ -110,7 +110,6 @@ def run_local_search(
     final_relationships = pd.read_parquet(
         data_path / "create_final_relationships.parquet"
     )
-    final_nodes = pd.read_parquet(data_path / "create_final_nodes.parquet")
     final_entities = pd.read_parquet(data_path / "create_final_entities.parquet")
     final_covariates_path = data_path / "create_final_covariates.parquet"
     final_covariates = (

-Original file line number
+Diff line change
@@ @@ -0,0 +1,4 @@ @@
 +{
 +  "type": "patch",
 +  "description": "remove duplicate file read"
 +}
Original file line number	Diff line number	Diff line change
`@@ -110,7 +110,6 @@ def run_local_search(`
`110`	`110`	`final_relationships = pd.read_parquet(`
`111`	`111`	`data_path / "create_final_relationships.parquet"`
`112`	`112`	`)`
`113`		`- final_nodes = pd.read_parquet(data_path / "create_final_nodes.parquet")`
`114`	`113`	`final_entities = pd.read_parquet(data_path / "create_final_entities.parquet")`
`115`	`114`	`final_covariates_path = data_path / "create_final_covariates.parquet"`
`116`	`115`	`final_covariates = (`