[Docs]: PaddleNLP/applications/neural_search/recall/in_batch_negative/

[kg-nlp]

软件环境

- paddlepaddle:
- paddlepaddle-gpu: 
- paddlenlp:

详细描述

代码与readme内容不一致

[w5688414]

请问是哪个地方不一致呢？有详细信息吗？

[kg-nlp]

命令行参数similar_text_pair 重复，实际源码中train_batch_neg是similar_text_pair_file

[kg-nlp]

neural_serch/ranking/cross_encoder/deploy/python/web_service.py 第69行

str(sim_score) 应该为 str(sim_score.tolist())

[w5688414]

similar_text_pair_file

请问您用的是什么环境？为什么需要转list？

[kg-nlp]

下载的最新版的代码，cross_encoder 模型服务返回的分数类型为numpy,不转成 list,在客户端请求
result = np.array(eval(ret.value[0])) ，ret.value[0] 会报错

[w5688414]

我在0.9的环境测试没问题，请问您的是什么serving环境：

paddle-serving-app             0.9.0
paddle-serving-client          0.9.0
paddle-serving-server          0.9.0

下载的最新版的代码，cross_encoder 模型服务返回的分数类型为numpy,不转成 list,在客户端请求 result = np.array(eval(ret.value[0])) ，ret.value[0] 会报错

[github-actions]

This issue is stale because it has been open for 60 days with no activity. 当前issue 60天内无活动，被标记为stale。

[github-actions]

This issue was closed because it has been inactive for 14 days since being marked as stale. 当前issue 被标记为stale已有14天，即将关闭。