如何使用Neo4j社区版，进行evaluation测试

[RyuGuo]

我希望构建memos进行测试，复现论文中的数据指标。但目前我只能安装Neo4j社区版，在运行evaluation/scripts/run_locomo_eval.sh 时报错，原因是evaluation/scripts/locomo/locomo_ingestion.py 测试项中会创建10个database，导致测试失败。请问有没有修复的方式，能够将测试正常进行下去？

以下是我的配置：
mem_cube_config.json

{
  "user_id": "MEMOS_USER",
  "cube_id": "MEMOS_CUBE",
  "text_mem": {
    "backend": "tree_text",
    "config": {
      "extractor_llm": {
        "backend": "openai",
        "config": {
          "model_name_or_path": "Qwen2.5-14B-Instruct",
          "temperature": 0.8,
          "max_tokens": 1024,
          "top_p": 0.9,
          "top_k": 50,
          "api_key": "",
          "api_base": "http://0.0.0.0:3000/v1"
        }
      },
      "dispatcher_llm": {
        "backend": "openai",
        "config": {
          "model_name_or_path": "Qwen2.5-14B-Instruct",
          "temperature": 0.8,
          "max_tokens": 1024,
          "top_p": 0.9,
          "top_k": 50,
          "api_key": "",
          "api_base": "http://0.0.0.0:3000/v1"
        }
      },
      "graph_db": {
        "backend": "neo4j",
        "config": {
          "uri": "bolt://0.0.0.0:7687",
          "user": "neo4j",
          "password": "123456789",
          "db_name": "MEMOS_DB",
          "auto_create": true
        }
      },
      "embedder": {
        "backend": "universal_api",
        "config": {
          "provider": "openai",
          "model_name_or_path": "nomic-embed-text-v1.5",
          "api_key": "",
          "base_url": "http://0.0.0.0:3001/v1"
        }
      }
    }
  },
  "act_mem": {},
  "para_mem": {}
}

mos_memos_config.json

{
  "user_id": "root",
  "chat_model": {
    "backend": "openai",
    "config": {
      "model_name_or_path": "Qwen2.5-14B-Instruct",
      "api_base": "http://0.0.0.0:3000/v1",
      "api_key": "",
      "temperature": 0.1,
      "remove_think_prefix": true,
      "max_tokens": 4096
    }
  },
  "mem_reader": {
    "backend": "simple_struct",
    "config": {
      "llm": {
        "backend": "openai",
        "config": {
          "model_name_or_path": "Qwen2.5-14B-Instruct",
          "temperature": 0.8,
          "max_tokens": 1024,
          "top_p": 0.9,
          "top_k": 50,
          "api_key": "",
          "api_base": "http://0.0.0.0:3000/v1"
        }
      },
      "embedder": {
        "backend": "universal_api",
        "config": {
          "provider": "openai",
          "model_name_or_path": "nomic-embed-text-v1.5",
          "api_key": "",
          "base_url": "http://0.0.0.0:3001/v1"
        }
      },
      "chunker": {
        "backend": "sentence",
        "config": {
          "tokenizer_or_token_counter": "gpt2",
          "chunk_size": 512,
          "chunk_overlap": 128,
          "min_sentences_per_chunk": 1
        }
      }
    }
  },
  "max_turns_window": 30,
  "top_k": "__TOP_K__",
  "enable_textual_memory": true,
  "enable_activation_memory": false,
  "enable_parametric_memory": false
}