light_ollama_demo 中 global 模式引用 'll_entities_context' 错误

[MengLLS]

INFO:lightrag:Logger initialized for working directory: ./dickens
INFO:lightrag:Load KV llm_response_cache with 0 data
INFO:lightrag:Load KV full_docs with 0 data
INFO:lightrag:Load KV text_chunks with 0 data
INFO:nano-vectordb:Init {'embedding_dim': 768, 'metric': 'cosine', 'storage_file': './dickens/vdb_entities.json'} 0 data
INFO:nano-vectordb:Init {'embedding_dim': 768, 'metric': 'cosine', 'storage_file': './dickens/vdb_relationships.json'} 0 data
INFO:nano-vectordb:Init {'embedding_dim': 768, 'metric': 'cosine', 'storage_file': './dickens/vdb_chunks.json'} 0 data
global
INFO:httpx:HTTP Request: POST http://localhost:11434/api/chat "HTTP/1.1 200 OK"
INFO:lightrag:kw_prompt result:

{
  "high_level_keywords": "故事的主角",
  "low_level_keywords": "主要角色"
}

INFO:httpx:HTTP Request: POST http://localhost:11434/api/embeddings "HTTP/1.1 200 OK"
WARNING:lightrag:No high level context found. Switching to local mode.
Traceback (most recent call last):
File "/gemini/code/LightRAG/examples/lightrag_ollama_demo.py", line 54, in
rag.query("这个故事的主要人物有哪些?", param=QueryParam(mode="global"))
File "/gemini/code/LightRAG/lightrag/lightrag.py", line 517, in query
return loop.run_until_complete(self.aquery(query, param))
File "/root/miniconda3/lib/python3.10/asyncio/base_events.py", line 649, in run_until_complete
return future.result()
File "/gemini/code/LightRAG/lightrag/lightrag.py", line 521, in aquery
response = await kg_query(
File "/gemini/code/LightRAG/lightrag/operate.py", line 532, in kg_query
context = await _build_query_context(
File "/gemini/code/LightRAG/lightrag/operate.py", line 656, in _build_query_context
ll_entities_context,
UnboundLocalError: local variable 'll_entities_context' referenced before assignment

其他模式都没问题,就global会报错