[BUG]新增应用时调试报错

[beijingtl]

联系方式

517699029@qq.com

MaxKB 版本

版本号：v0.9.0 (build at 2024-03-21T18:39, commit: 96a0e4b)

问题描述

在新增应用时，配置好应用内的细节后，在右侧的测试窗口对话时提示报错。

重现步骤

1. 设置应用。在新建应用后，设置好名称、大模型，以及选择知识库后。
2. 在右侧调试输入“hi”，同时也尝试过其他输入文本，都提示相同错误。

期待的正确结果

不报错，返回信息。

相关日志输出

waiting for postgres
2024-03-24 19:04:56.830 CST [141] FATAL:  the database system is starting up
127.0.0.1:5432 - rejecting connections
waiting for postgres
2024-03-24 19:04:57.845 CST [144] FATAL:  the database system is starting up
127.0.0.1:5432 - rejecting connections
waiting for postgres
2024-03-24 19:04:58.860 CST [147] FATAL:  the database system is starting up
127.0.0.1:5432 - rejecting connections
2024-03-24 19:04:59.005 CST [31] LOG:  database system was not properly shut down; automatic recovery in progress
2024-03-24 19:04:59.051 CST [31] LOG:  redo starts at 0/1E75BC0
2024-03-24 19:04:59.051 CST [31] LOG:  invalid record length at 0/1E75CA8: wanted 24, got 0
2024-03-24 19:04:59.051 CST [31] LOG:  redo done at 0/1E75C70 system usage: CPU: user: 0.00 s, system: 0.00 s, elapsed: 0.00 s
2024-03-24 19:04:59.247 CST [29] LOG:  checkpoint starting: end-of-recovery immediate wait
2024-03-24 19:04:59.566 CST [29] LOG:  checkpoint complete: wrote 3 buffers (0.0%); 0 WAL file(s) added, 0 removed, 0 recycled; write=0.120 s, sync=0.031 s, total=0.366 s; sync files=2, longest=0.016 s, average=0.016 s; distance=0 kB, estimate=0 kB
2024-03-24 19:04:59.624 CST [7] LOG:  database system is ready to accept connections
waiting for postgres
127.0.0.1:5432 - accepting connections
Operations to perform:
  Apply all migrations: application, contenttypes, dataset, django_apscheduler, embedding, setting, users
Running migrations:
  No migrations to apply.
  Your models in app(s): 'application' have changes that are not yet reflected in a migration, and so won't be applied.
  Run 'manage.py makemigrations' to make new migrations, and then re-run 'manage.py migrate' to apply them.
Operations to perform:
  Apply all migrations: application, contenttypes, dataset, django_apscheduler, embedding, setting, users
Running migrations:
  No migrations to apply.
  Your models in app(s): 'application' have changes that are not yet reflected in a migration, and so won't be applied.
  Run 'manage.py makemigrations' to make new migrations, and then re-run 'manage.py migrate' to apply them.
2024-03-24 19:09:59.593 CST [29] LOG:  checkpoint starting: time
2024-03-24 19:10:00.273 CST [29] LOG:  checkpoint complete: wrote 4 buffers (0.0%); 0 WAL file(s) added, 0 removed, 0 recycled; write=0.333 s, sync=0.044 s, total=0.681 s; sync files=4, longest=0.029 s, average=0.011 s; distance=3 kB, estimate=3 kB
2024-03-24 19:40:08 [basehttp INFO] "GET /api/provider/model_type_list?provider=model_ollama_provider HTTP/1.1" 200 109
2024-03-24 19:40:08 [basehttp INFO] "GET /api/provider/model_form?provider=model_ollama_provider&model_type=LLM&model_name=qwen:1.8b HTTP/1.1" 200 542
2024-03-24 19:40:08 [basehttp INFO] "GET /api/provider/model_list?provider=model_ollama_provider&model_type=LLM HTTP/1.1" 200 2538
2024-03-24 19:40:33 [basehttp INFO] "PUT /api/model/579cf4de-e995-11ee-a74e-0242ac100a08 HTTP/1.1" 200 303
2024-03-24 19:40:33 [basehttp INFO] "GET /api/model?name= HTTP/1.1" 200 305
2024-03-24 19:44:59.716 CST [29] LOG:  checkpoint starting: time
2024-03-24 19:44:59.997 CST [29] LOG:  checkpoint complete: wrote 2 buffers (0.0%); 0 WAL file(s) added, 0 removed, 0 recycled; write=0.132 s, sync=0.046 s, total=0.281 s; sync files=2, longest=0.031 s, average=0.023 s; distance=1 kB, estimate=3 kB
2024-03-24 20:36:51 [basehttp INFO] "GET /ui/assets/SyncWebDialog-5c10ee06.css HTTP/1.1" 200 280
2024-03-24 20:36:51 [basehttp INFO] "GET /ui/assets/index-bcb9597e.js HTTP/1.1" 200 4351
2024-03-24 20:36:51 [basehttp INFO] "GET /ui/assets/index-3090d140.css HTTP/1.1" 200 295
2024-03-24 20:36:51 [basehttp INFO] "GET /ui/assets/SyncWebDialog-1c3d5bfd.js HTTP/1.1" 200 2158
/usr/local/lib/python3.11/site-packages/django/db/models/base.py:364: RuntimeWarning: Model 'dataset.dynamics' was already registered. Reloading models is not advised as it can lead to inconsistencies, most notably with related models.
  new_class._meta.apps.register_model(new_class._meta.app_label, new_class)
2024-03-24 20:36:51 [basehttp INFO] "GET /api/dataset/1/20 HTTP/1.1" 200 414
2024-03-24 20:36:51 [basehttp INFO] "GET /ui/assets/icon_document-2fa30876.svg HTTP/1.1" 200 1376
2024-03-24 20:36:53 [basehttp INFO] "GET /api/application/1/20 HTTP/1.1" 200 1988
2024-03-24 20:36:54 [basehttp INFO] "GET /ui/assets/index-b44a8f06.js HTTP/1.1" 200 10328
2024-03-24 20:36:54 [basehttp INFO] "GET /ui/assets/index-49976e2c.css HTTP/1.1" 200 405
2024-03-24 20:36:54 [basehttp INFO] "GET /api/application HTTP/1.1" 200 1937
2024-03-24 20:36:54 [basehttp INFO] "GET /api/application/fcbfad3a-e995-11ee-a74e-0242ac100a08/access_token HTTP/1.1" 200 223
2024-03-24 20:36:54 [basehttp INFO] "GET /api/application/fcbfad3a-e995-11ee-a74e-0242ac100a08 HTTP/1.1" 200 1996
2024-03-24 20:36:55 [basehttp INFO] "GET /ui/chat/34b6f605902a90af HTTP/1.1" 200 460
2024-03-24 20:36:55 [basehttp INFO] "GET /ui/assets/index-1b0dc722.js HTTP/1.1" 200 3259345
2024-03-24 20:36:55 [basehttp INFO] "GET /ui/assets/index-b342bee3.css HTTP/1.1" 200 433601
2024-03-24 20:37:02 [basehttp INFO] "GET /api/user_manage/1/20 HTTP/1.1" 200 369
2024-03-24 20:37:04 [basehttp INFO] "GET /api/provider HTTP/1.1" 200 17325
2024-03-24 20:37:04 [basehttp INFO] "GET /api/model?name= HTTP/1.1" 200 305
2024-03-24 20:37:06 [basehttp INFO] "GET /api/provider/model_type_list?provider=model_ollama_provider HTTP/1.1" 200 109
2024-03-24 20:37:06 [basehttp INFO] "GET /api/provider/model_form?provider=model_ollama_provider&model_type=LLM&model_name=qwen:1.8b HTTP/1.1" 200 542
2024-03-24 20:37:06 [basehttp INFO] "GET /api/provider/model_list?provider=model_ollama_provider&model_type=LLM HTTP/1.1" 200 2538
2024-03-24 20:37:21 [basehttp INFO] "GET /ui/assets/index-0531091d.js HTTP/1.1" 200 968
2024-03-24 20:37:21 [basehttp INFO] "GET /ui/assets/index-9da5a7b8.css HTTP/1.1" 200 805
2024-03-24 20:37:21 [basehttp INFO] "GET /ui/assets/icon_send-280a4ce1.svg HTTP/1.1" 200 945
2024-03-24 20:37:21 [basehttp INFO] "GET /ui/assets/icon_send_colorful-1f161525.svg HTTP/1.1" 200 1415
2024-03-24 20:37:21 [basehttp INFO] "POST /api/application/authentication HTTP/1.1" 200 403
2024-03-24 20:37:21 [basehttp INFO] "GET /api/application/profile HTTP/1.1" 200 508
2024-03-24 20:37:22 [basehttp INFO] "GET /ui/assets/icon_robot-c95ad06b.svg HTTP/1.1" 200 1337
2024-03-24 20:37:40 [basehttp INFO] "PUT /api/model/579cf4de-e995-11ee-a74e-0242ac100a08 HTTP/1.1" 200 303
2024-03-24 20:37:40 [basehttp INFO] "GET /api/model?name= HTTP/1.1" 200 305
2024-03-24 20:37:43 [basehttp INFO] "GET /ui/assets/user-icon-c413d294.svg HTTP/1.1" 200 1033
2024-03-24 20:37:43 [basehttp INFO] "GET /api/application/fcbfad3a-e995-11ee-a74e-0242ac100a08/chat/open HTTP/1.1" 200 88
/usr/local/lib/python3.11/site-packages/langchain_core/_api/deprecation.py:117: LangChainDeprecationWarning: The function `__call__` was deprecated in LangChain 0.1.7 and will be removed in 0.2.0. Use invoke instead.
  warn_deprecated(
2024-03-24 20:37:44 [handle_exception ERROR] substring not found:Traceback (most recent call last):
  File "/usr/local/lib/python3.11/site-packages/rest_framework/views.py", line 506, in dispatch
    response = handler(request, *args, **kwargs)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/maxkb/app/apps/common/auth/authentication.py", line 94, in run
    return func(view, request, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/maxkb/app/apps/application/views/chat_views.py", line 83, in post
    'client_type': request.auth.client_type}).chat()
                                              ^^^^^^
  File "/opt/maxkb/app/apps/application/serializers/chat_message_serializers.py", line 191, in chat
    pipline_message.run(params)
  File "/opt/maxkb/app/apps/application/chat_pipeline/pipeline_manage.py", line 29, in run
    step.run(self)
  File "/opt/maxkb/app/apps/application/chat_pipeline/I_base_chat_pipeline.py", line 122, in run
    self._run(manage)
  File "/opt/maxkb/app/apps/application/chat_pipeline/step/reset_problem_step/i_reset_problem_step.py", line 37, in _run
    padding_problem = self.execute(**self.context.get('step_args'))
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/maxkb/app/apps/application/chat_pipeline/step/reset_problem_step/impl/base_reset_problem_step.py", line 32, in execute
    padding_problem = response.content[response.content.index('<data>') + 6:response.content.index('</data>')]
                                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: substring not found

2024-03-24 20:37:44 [basehttp INFO] "POST /api/application/chat_message/4f4b48ee-e9db-11ee-a973-0242ac100a06 HTTP/1.1" 200 61

附加信息

1. 已经测试了ollma服务正常。
   

(base) admin@ai-server:~$ curl http://172.16.10.2:11434/v1/chat/completions -d '{
  "model": "qwen:1.8b",
  "stream": false,
  "messages": [
    { "role": "user", "content": "1+1=?" }
  ]
}'
{"id":"chatcmpl-401","object":"chat.completion","created":1711283990,"model":"qwen:1.8b","system_fingerprint":"fp_ollama","choices":[{"index":0,"message":{"role":"assistant","content":"1 + 1 = 2\n"},"finish_reason":"stop"}],"usage":{"prompt_tokens":9,"completion_tokens":10,"total_tokens":19}}

2. 已经确认 test知识库里面，有文档，且里面有内容。
   
   

[baixin513]

感谢反馈，我们排查一下。

[baixin513]

您好，确认一下是否开启了【问题优化】？ 您可以关闭后在提问测试一下看看。
可能是开启了问题优化，但大模型未能返回优化后的问题导致。这里我们再优化一下处理逻辑。

[beijingtl]

您好，确认一下是否开启了【问题优化】？ 您可以关闭后在提问测试一下看看。 可能是开启了问题优化，但大模型未能返回优化后的问题导致。这里我们再优化一下处理逻辑。

你好。确实开启了“问题优化”导致的，关闭后就可以了。

[wanghe-fit2cloud]

v0.9.1 版本已发布。