pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 20:42:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: Resolve KnowledgeGraph entity resolution errors (#6653) (#6691)

Browse Source 
### Related Issue: #6653
### Environment:

Using nightly version

Elasticsearch database

### Bug Description:
When clicking the "Entity Resolution" button in KnowledgeGraph,
encountered the following errors:

graphrag/entity_resolution.py

```
list(sub_connect_graph.nodes) AttributeError
```

graphrag/general/extractor.py
```
node0_attrs[attr] = sorted(set(node0_attrs[attr].extend(node1_attrs[attr])))
TypeError: 'NoneType' object is not iterable
```
```
for attr in ["keywords", "source_id"]:  
 KeyError I think attribute "keywords" is in edges not nodes
```
graphrag/utils.py
```
settings.docStoreConn.delete()  # Sync function called as async
```
### Changes Made:

Fixed AttributeError in entity_resolution.py by properly handling graph
nodes

Fixed TypeError and KeyError in extractor.py by separate operations

Corrected async/sync mismatch in document deletion call
This commit is contained in:
Yue-Lyu123
2025-03-31 22:31:35 +08:00
committed by GitHub
parent 0a42e5777e
commit ece59034f7
3 changed files with 5 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
graphrag/general/extractor.py
View File

@ -201,8 +201,7 @@ class Extractor:
# Merge two nodes, keep "entity_name", "entity_type", "page_rank" unchanged.
node1_attrs = graph.nodes[node1]
node0_attrs["description"] += f"{GRAPH_FIELD_SEP}{node1_attrs['description']}"
for attr in ["keywords", "source_id"]:
node0_attrs[attr] = sorted(set(node0_attrs[attr].extend(node1_attrs[attr])))
node0_attrs["source_id"] = sorted(set(node0_attrs["source_id"].extend(node1_attrs.get("source_id", []))))
for neighbor in graph.neighbors(node1):
change.removed_edges.add(get_from_to(node1, neighbor))
if neighbor not in nodes_set:
@ -213,8 +212,8 @@ class Extractor:
edge0_attrs = graph.get_edge_data(nodes[0], neighbor)
edge0_attrs["weight"] += edge1_attrs["weight"]
edge0_attrs["description"] += f"{GRAPH_FIELD_SEP}{edge1_attrs['description']}"
edge0_attrs["keywords"] = list(set(edge0_attrs["keywords"].extend(edge1_attrs["keywords"])))
edge0_attrs["source_id"] = list(set(edge0_attrs["source_id"].extend(edge1_attrs["source_id"])))
for attr in ["keywords", "source_id"]:
edge0_attrs[attr] = sorted(set(edge0_attrs[attr].extend(edge1_attrs.get(attr, []))))
edge0_attrs["description"] = await self._handle_entity_relation_summary(f"({nodes[0]}, {neighbor})", edge0_attrs["description"])
graph.add_edge(nodes[0], neighbor, **edge0_attrs)
else: