WOWCharlotte

1. 编写eva.py文件 ```python import json import logging import os from typing import List from kag.common.benchmarks.evaluate import Evaluate from kag.examples.utils import delay_run from kag.open_benchmark.utils.eval_qa import EvalQa, running_paras, do_main from kag.common.conf import...

### Search before asking - [x] I had searched in the [issues](https://github.com/OpenSPG/KAG/issues?q=is%3Aissue) and found no similar issues. ### Operating system information Windows ### What happened 我在使用示例文件2wiki时发生报错  具体报错信息: ``` 2025-07-01...

[Feature][Module Name] 领域知识抽取效果不佳

1

### Search before asking - [x] I had searched in the [issues](https://github.com/OpenSPG/KAG/issues?q=is%3Aissue) and found no similar feature requirement. ### Description KAG根据注入的schema抽取SPO三元组的效果不佳，运行日志查验发现，ner.py中schema变量仅提取了类的名称，未提取更多有效信息，这意味着LLM仅依靠类名称进行SPO抽取任务，导致抽取效果不佳。建议将预定义schema解析为结构统一的Python类，增加类注释和属性注释用于LLM理解。[灵感来源](https://arxiv.org/abs/2310.03668)，发表于ICLR-2024。 ```json { "instruction": "You're a very effective entity extraction...