From 7184c7b3abdb69c952310d446e32094ba169dfc5 Mon Sep 17 00:00:00 2001
From: yangdx <gzdaniel@me.com>
Date: Thu, 17 Jul 2025 11:30:49 +0800
Subject: [PATCH] fix: change default edge weight from 0.0 to 1.0 in entity
 extraction and graph storage

- Update extract_entities function in operate.py to use 1.0 as default weight
- Fix Neo4j implementation to use 1.0 instead of 0.0 for missing edge weights
- Fix Memgraph implementation to use 1.0 instead of 0.0 for missing edge weights
- Ensures consistent non-zero default weights across all graph storage backends
---
 lightrag/kg/memgraph_impl.py |  2 +-
 lightrag/kg/neo4j_impl.py    |  8 ++++----
 lightrag/operate.py          | 13 +++++++------
 3 files changed, 12 insertions(+), 11 deletions(-)

diff --git a/lightrag/kg/memgraph_impl.py b/lightrag/kg/memgraph_impl.py
index 3d2c131e..16185775 100644
--- a/lightrag/kg/memgraph_impl.py
+++ b/lightrag/kg/memgraph_impl.py
@@ -414,7 +414,7 @@ class MemgraphStorage(BaseGraphStorage):
                 if records:
                     edge_result = dict(records[0]["edge_properties"])
                     for key, default_value in {
-                        "weight": 0.0,
+                        "weight": 1.0,
                         "source_id": None,
                         "description": None,
                         "keywords": None,
diff --git a/lightrag/kg/neo4j_impl.py b/lightrag/kg/neo4j_impl.py
index b0efc4b5..847b73b0 100644
--- a/lightrag/kg/neo4j_impl.py
+++ b/lightrag/kg/neo4j_impl.py
@@ -535,7 +535,7 @@ class Neo4JStorage(BaseGraphStorage):
                             # logger.debug(f"Result: {edge_result}")
                             # Ensure required keys exist with defaults
                             required_keys = {
-                                "weight": 0.0,
+                                "weight": 1.0,
                                 "source_id": None,
                                 "description": None,
                                 "keywords": None,
@@ -559,7 +559,7 @@ class Neo4JStorage(BaseGraphStorage):
                             )
                             # Return default edge properties on error
                             return {
-                                "weight": 0.0,
+                                "weight": 1.0,
                                 "source_id": None,
                                 "description": None,
                                 "keywords": None,
@@ -610,7 +610,7 @@ class Neo4JStorage(BaseGraphStorage):
                     edge_props = edges[0]  # choose the first if multiple exist
                     # Ensure required keys exist with defaults
                     for key, default in {
-                        "weight": 0.0,
+                        "weight": 1.0,
                         "source_id": None,
                         "description": None,
                         "keywords": None,
@@ -621,7 +621,7 @@ class Neo4JStorage(BaseGraphStorage):
                 else:
                     # No edge found – set default edge properties
                     edges_dict[(src, tgt)] = {
-                        "weight": 0.0,
+                        "weight": 1.0,
                         "source_id": None,
                         "description": None,
                         "keywords": None,
diff --git a/lightrag/operate.py b/lightrag/operate.py
index e3456d92..77eaa70c 100644
--- a/lightrag/operate.py
+++ b/lightrag/operate.py
@@ -1016,8 +1016,8 @@ async def _merge_edges_then_upsert(
         already_edge = await knowledge_graph_inst.get_edge(src_id, tgt_id)
         # Handle the case where get_edge returns None or missing fields
         if already_edge:
-            # Get weight with default 0.0 if missing
-            already_weights.append(already_edge.get("weight", 0.0))
+            # Get weight with default 1.0 if missing
+            already_weights.append(already_edge.get("weight", 1.0))
 
             # Get source_id with empty string default if missing or None
             if already_edge.get("source_id") is not None:
@@ -1284,6 +1284,7 @@ async def merge_nodes_and_edges(
                             "content": f"{edge_data['src_id']}\t{edge_data['tgt_id']}\n{edge_data['keywords']}\n{edge_data['description']}",
                             "source_id": edge_data["source_id"],
                             "file_path": edge_data.get("file_path", "unknown_source"),
+                            "weight": edge_data.get("weight", 1.0),
                         }
                     }
                     await relationships_vdb.upsert(data_for_vdb)
@@ -2493,9 +2494,9 @@ async def _find_most_related_edges_from_entities(
         if edge_props is not None:
             if "weight" not in edge_props:
                 logger.warning(
-                    f"Edge {pair} missing 'weight' attribute, using default value 0.0"
+                    f"Edge {pair} missing 'weight' attribute, using default value 1.0"
                 )
-                edge_props["weight"] = 0.0
+                edge_props["weight"] = 1.0
 
             combined = {
                 "src_tgt": pair,
@@ -2548,9 +2549,9 @@ async def _get_edge_data(
         if edge_props is not None:
             if "weight" not in edge_props:
                 logger.warning(
-                    f"Edge {pair} missing 'weight' attribute, using default value 0.0"
+                    f"Edge {pair} missing 'weight' attribute, using default value 1.0"
                 )
-                edge_props["weight"] = 0.0
+                edge_props["weight"] = 1.0
 
             # Use edge degree from the batch as rank.
             combined = {