QAnything icon indicating copy to clipboard operation
QAnything copied to clipboard

[BUG] 本地部署后点击知识库新建,显示“请求失败”

Open fire717 opened this issue 1 year ago • 1 comments

是否已有关于该错误的issue或讨论? | Is there an existing issue / discussion for this?

  • [X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions

该问题是否在FAQ中有解答? | Is there an existing answer for this in FAQ?

  • [X] 我已经搜索过FAQ | I have searched FAQ

当前行为 | Current Behavior

docker-compose -f docker-compose-linux.yaml up qanything_local 正常启动,进入前端页面,左侧输入任意知识库名称,点击新建按钮,转圈几秒后显示请求失败。

期望行为 | Expected Behavior

新建知识库成功。

运行环境 | Environment

- OS:Ubuntu 18.04
- NVIDIA Driver: 535.154.05
- CUDA: 12.2
- Docker Compose: 2.24.0
- NVIDIA GPU Memory: 24G

QAnything日志 | QAnything logs

UPLOAD_ROOT_PATH: /workspace/qanything_local/QANY_DB/content None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used. [2024-01-18 17:50:20 +0800] [91] [INFO] Sanic v23.6.0 [2024-01-18 17:50:20 +0800] [91] [INFO] Goin' Fast @ http://0.0.0.0:8777 [2024-01-18 17:50:20 +0800] [91] [INFO] mode: production, w/ 4 workers [2024-01-18 17:50:20 +0800] [91] [INFO] server: sanic, HTTP/1.1 [2024-01-18 17:50:20 +0800] [91] [INFO] python: 3.10.12 [2024-01-18 17:50:20 +0800] [91] [INFO] platform: Linux-5.4.0-144-generic-x86_64-with-glibc2.35 [2024-01-18 17:50:20 +0800] [91] [INFO] packages: sanic-routing==23.12.0, sanic-ext==23.6.0 None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used. None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used. None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used. None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used. None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used. UPLOAD_ROOT_PATH: /workspace/qanything_local/QANY_DB/content [2024-01-18 17:50:23 +0800] [635] [INFO] Sanic Extensions: [2024-01-18 17:50:23 +0800] [635] [INFO] > injection [0 dependencies; 0 constants] [2024-01-18 17:50:23 +0800] [635] [INFO] > openapi [http://0.0.0.0:8777/docs] [2024-01-18 17:50:23 +0800] [635] [INFO] > http [2024-01-18 17:50:23 +0800] [635] [INFO] > templating [jinja2==3.1.3] UPLOAD_ROOT_PATH: /workspace/qanything_local/QANY_DB/content [2024-01-18 17:50:23 +0800] [636] [INFO] Sanic Extensions: [2024-01-18 17:50:23 +0800] [636] [INFO] > injection [0 dependencies; 0 constants] [2024-01-18 17:50:23 +0800] [636] [INFO] > openapi [http://0.0.0.0:8777/docs] [2024-01-18 17:50:23 +0800] [636] [INFO] > http [2024-01-18 17:50:23 +0800] [636] [INFO] > templating [jinja2==3.1.3] UPLOAD_ROOT_PATH: /workspace/qanything_local/QANY_DB/content [2024-01-18 17:50:23 +0800] [638] [INFO] Sanic Extensions: [2024-01-18 17:50:23 +0800] [638] [INFO] > injection [0 dependencies; 0 constants] [2024-01-18 17:50:23 +0800] [638] [INFO] > openapi [http://0.0.0.0:8777/docs] [2024-01-18 17:50:23 +0800] [638] [INFO] > http [2024-01-18 17:50:23 +0800] [638] [INFO] > templating [jinja2==3.1.3] UPLOAD_ROOT_PATH: /workspace/qanything_local/QANY_DB/content [2024-01-18 17:50:23 +0800] [637] [INFO] Sanic Extensions: [2024-01-18 17:50:23 +0800] [637] [INFO] > injection [0 dependencies; 0 constants] [2024-01-18 17:50:23 +0800] [637] [INFO] > openapi [http://0.0.0.0:8777/docs] [2024-01-18 17:50:23 +0800] [637] [INFO] > http [2024-01-18 17:50:23 +0800] [637] [INFO] > templating [jinja2==3.1.3] init local_doc_qa in local init local_doc_qa in local init local_doc_qa in local init local_doc_qa in local [2024-01-18 17:50:23 +0800] [635] [INFO] Starting worker [635] [2024-01-18 17:50:23 +0800] [636] [INFO] Starting worker [636] [2024-01-18 17:50:23 +0800] [638] [INFO] Starting worker [638] [2024-01-18 17:50:23 +0800] [637] [INFO] Starting worker [637]

复现方法 | Steps To Reproduce

就在本地按官方说明操作

备注 | Anything else?

No response

fire717 avatar Jan 18 '24 09:01 fire717

我也有这样的问题,F12发现前端访问的url是“localhost”,那么原因就找到了:qanything是部署在公司机房的服务器,并不是浏览器所在的“本地电脑”。 故解决办法:启动时选择cloud,输入服务器的IP地址。

now-101 avatar Jan 19 '24 00:01 now-101

我也有这样的问题,F12发现前端访问的url是“localhost”,那么原因就找到了:qanything是部署在公司机房的服务器,并不是浏览器所在的“本地电脑”。 故解决办法:启动时选择cloud,输入服务器的IP地址。

感谢,请问启动时具体如何操作呢?我是按照README执行docker-compose -f docker-compose-linux.yaml up qanything_local就直接启动了,没有选择的步骤,尝试在.env.production修改localhost为ip也没效果

fire717 avatar Jan 19 '24 01:01 fire717

我也有这样的问题,F12发现前端访问的url是“localhost”,那么原因就找到了:qanything是部署在公司机房的服务器,并不是浏览器所在的“本地电脑”。 故解决办法:启动时选择cloud,输入服务器的IP地址。

感谢,请问启动时具体如何操作呢?我是按照README执行docker-compose -f docker-compose-linux.yaml up qanything_local就直接启动了,没有选择的步骤,尝试在.env.production修改localhost为ip也没效果

docker-compose -f docker-compose-linux.yaml up qanything_local 这种方式会有不少坑存在。不是卡在这儿就是卡在那儿

建议使用最新代码,"bash run.sh",执行的时候会让你选择 cloud or local

now-101 avatar Jan 19 '24 01:01 now-101

我也有这样的问题,F12发现前端访问的url是“localhost”,那么原因就找到了:qanything是部署在公司机房的服务器,并不是浏览器所在的“本地电脑”。 故解决办法:启动时选择cloud,输入服务器的IP地址。

感谢,请问启动时具体如何操作呢?我是按照README执行docker-compose -f docker-compose-linux.yaml up qanything_local就直接启动了,没有选择的步骤,尝试在.env.production修改localhost为ip也没效果

docker-compose -f docker-compose-linux.yaml up qanything_local 这种方式会有不少坑存在。不是卡在这儿就是卡在那儿

建议使用最新代码,"bash run.sh",执行的时候会让你选择 cloud or local

的确换成run.sh的形式可以了

fire717 avatar Jan 19 '24 02:01 fire717

我也有这样的问题,F12发现前端访问的url是“localhost”,那么原因就找到了:qanything是部署在公司机房的服务器,并不是浏览器所在的“本地电脑”。 故解决办法:启动时选择cloud,输入服务器的IP地址。

感谢,请问启动时具体如何操作呢?我是按照README执行docker-compose -f docker-compose-linux.yaml up qanything_local就直接启动了,没有选择的步骤,尝试在.env.production修改localhost为ip也没效果

docker-compose -f docker-compose-linux.yaml up qanything_local 这种方式会有不少坑存在。不是卡在这儿就是卡在那儿 建议使用最新代码,"bash run.sh",执行的时候会让你选择 cloud or local

的确换成run.sh的形式可以了

我改用run.sh后仍出现此报错,是否能解答 细节如#45所示

Cordy27 avatar Feb 15 '24 19:02 Cordy27

蟹蟹解答

shu1ao2han3 avatar Mar 12 '24 07:03 shu1ao2han3