Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Question]: 知识库里面解析文件时全部报错,日志如下,请问该如何解决 #4908

Open
grswxt opened this issue Feb 12, 2025 · 0 comments
Labels
question Further information is requested

Comments

@grswxt
Copy link

grswxt commented Feb 12, 2025

Describe your problem

在centos7,宝塔面板的docker中安装了ragflow,使用的是0.15.1完全版9GB的。在知识库中建立了两个库,分别用智谱清言embedding和BAAI/bge-large-zh-v.15做嵌入模型,两个都没有成功。请问是什么原因导致的?
docker列表如下:
容器名 容器ID 状态 镜像 端口(主机-->容器) 操作
ragflow-server 6bf5ddab25c6 运行中 registry.cn-hangzhou.aliyuncs.com/infiniflow/ragflow:nightly 0.0.0.0:9380-->9380/tcp 0.0.0.0:443-->443/tcp 0.0.0.0:80-->80/tcp
ragflow-minio b968e23139d4 运行中 quay.io/minio/minio:RELEASE.2023-12-20T01-00-02Z 0.0.0.0:9000-->9000/tcp 0.0.0.0:9001-->9001/tcp
ragflow-mysql a13c12ec2396 运行中 mysql:8.0.39 0.0.0.0:5455-->3306/tcp
ragflow-redis e7308df5e61d 运行中 valkey/valkey:8 0.0.0.0:6379-->6379/tcp
ragflow-infinity f99ded12b5b1 运行中 infiniflow/infinity:v0.6.0-dev2 0.0.0.0:23817-->23817/tcp 0.0.0.0:23820-->23820/tcp 0.0.0.0:5432-->5432/tcp

错误日志如下:
1. zhipu embedding3:
开始于:
Tue, 11 Feb 2025 11:02:01 GMT
持续时间:
15837.10 s
进度:
15:20:42 Task has been received.
15:20:43 Page(113): OCR started
15:20:49 Page(1
13): OCR finished (6.67s)
15:21:12 Page(113): Layout analysis (22.64s)
15:21:12 Page(1
13): Table analysis (0.00s)
15:21:12 Page(113): Text merged (0.00s)
15:21:13 Page(1
13): Start to generate keywords for every chunk ...
15:21:13 [ERROR][Exception]: Model(qwen-plus) not authorized
15:21:13 Task has been received.
15:21:13 Page(1325): OCR started
15:21:21 Page(13
25): OCR finished (7.07s)
15:21:44 Page(1325): Layout analysis (23.50s)
15:21:44 Page(13
25): Table analysis (0.17s)
15:21:44 Page(1325): Text merged (0.00s)
15:21:46 Page(13
25): Start to generate keywords for every chunk ...
15:21:46 [ERROR][Exception]: Model(qwen-plus) not authorized
15:21:46 Task has been received.
15:21:49 Page(2537): OCR started
15:21:56 Page(25
37): OCR finished (7.39s)
15:22:19 Page(2537): Layout analysis (22.40s)
15:22:19 Page(25
37): Table analysis (0.09s)
15:22:19 Page(2537): Text merged (0.00s)
15:22:20 Page(25
37): Start to generate keywords for every chunk ...
15:22:20 [ERROR][Exception]: Model(qwen-plus) not authorized
.....都是上述的错误

2. BAAI/bge-large-zh-v.15开始于:Tue, 11 Feb 2025 12:17:10 GMT持续时间:
21233.80 s
进度:
17:00:02 Task has been received.
17:09:10 Page(113): [ERROR]Fail to bind embedding model: An error happened while trying to locate the files on the Hub and we cannot find the appropriate snapshot folder for the specified revision on the local disk. Please check your internet connection and try again.
17:09:10 [ERROR][Exception]: An error happened while trying to locate the files on the Hub and we cannot find the appropriate snapshot folder for the specified revision on the local disk. Please check your internet connection and try again.
17:09:10 Task has been received.
17:18:18 Page(13
25): [ERROR]Fail to bind embedding model: An error happened while trying to locate the files on the Hub and we cannot find the appropriate snapshot folder for the specified revision on the local disk. Please check your internet connection and try again.
17:18:18 [ERROR][Exception]: An error happened while trying to locate the files on the Hub and we cannot find the appropriate snapshot folder for the specified revision on the local disk. Please check your internet connection and try again.
17:18:18 Task has been received.
17:27:26 Page(2537) 之后一直到18:11:00 Page(8586)都是上述的错误。

@grswxt grswxt added the question Further information is requested label Feb 12, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
question Further information is requested
Projects
None yet
Development

No branches or pull requests

1 participant