add zhipu glm3-turbo glm4-v error #988

Closed
opened 2026-02-21 17:29:22 -05:00 by yindo · 4 comments
Owner

Originally created by @Sunwc0 on GitHub (Jan 29, 2024).

Self Checks

Dify version

0.5.2

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

WeChat0c19525d4d6ce3427fd07429123de000

✔️ Expected Behavior

No response

Actual Behavior

No response

Originally created by @Sunwc0 on GitHub (Jan 29, 2024). ### Self Checks - [X] I have searched for existing issues [search for existing issues](https://github.com/langgenius/dify/issues), including closed ones. - [X] I confirm that I am using English to file this report (我已阅读并同意 [Language Policy](https://github.com/langgenius/dify/issues/1542)). ### Dify version 0.5.2 ### Cloud or Self Hosted Self Hosted (Docker) ### Steps to reproduce ![WeChat0c19525d4d6ce3427fd07429123de000](https://github.com/langgenius/dify/assets/31982984/4712e8f8-b4a9-4d61-a5dd-dc6a47122cf9) ### ✔️ Expected Behavior _No response_ ### ❌ Actual Behavior _No response_
yindo added the 🙏 help wanted label 2026-02-21 17:29:22 -05:00
yindo closed this issue 2026-02-21 17:29:22 -05:00
Author
Owner

@dosubot[bot] commented on GitHub (Jan 29, 2024):

🤖

Hello @Sunwc0, it's good to see you again! I hope you're having a wonderful day. Let's see what we can do about this issue.

Based on the information provided, it seems you want to add the modules 'zhipu', 'glm3-turbo', and 'glm4-v' to the dify codebase. However, without more information about these modules, it's difficult to provide a specific process for adding them.

Generally, to add new modules to the dify codebase, you would define a new function or class in the appropriate Python file. For example, new commands are added to the api/commands.py file by defining new functions decorated with the @click.command() decorator. Here's an example of how a new command is added:

@click.command('new-command', help='This is a new command.')
@click.option('--option1', prompt=True, help='This is an option for the new command.')
def new_command(option1):
    # Implementation of the command goes here
    pass

In a Docker environment, you would create your new module in the appropriate directory of your local dify codebase, add any new dependencies to the appropriate requirements file, build a new Docker image that includes your new module and its dependencies, and update the docker-compose.yaml file to use the new Docker image.

However, without more information about the 'zhipu', 'glm3-turbo', and 'glm4-v' modules, it's difficult to provide more specific guidance. Could you provide more details about these modules, such as their functionalities, any specific dependencies they require, and their purpose in the context of the dify application? This information would help in providing a more accurate and detailed response.

Sources


This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.

@dosubot[bot] commented on GitHub (Jan 29, 2024): _🤖_ <!-- Greeting --> Hello @Sunwc0, it's good to see you again! I hope you're having a wonderful day. Let's see what we can do about this issue. <!-- Answer --> Based on the information provided, it seems you want to add the modules 'zhipu', 'glm3-turbo', and 'glm4-v' to the dify codebase. However, without more information about these modules, it's difficult to provide a specific process for adding them. Generally, to add new modules to the dify codebase, you would define a new function or class in the appropriate Python file. For example, new commands are added to the `api/commands.py` file by defining new functions decorated with the `@click.command()` decorator. Here's an example of how a new command is added: ```py @click.command('new-command', help='This is a new command.') @click.option('--option1', prompt=True, help='This is an option for the new command.') def new_command(option1): # Implementation of the command goes here pass ``` In a Docker environment, you would create your new module in the appropriate directory of your local dify codebase, add any new dependencies to the appropriate requirements file, build a new Docker image that includes your new module and its dependencies, and update the `docker-compose.yaml` file to use the new Docker image. However, without more information about the 'zhipu', 'glm3-turbo', and 'glm4-v' modules, it's difficult to provide more specific guidance. Could you provide more details about these modules, such as their functionalities, any specific dependencies they require, and their purpose in the context of the dify application? This information would help in providing a more accurate and detailed response. ## Sources - [api/commands.py](https://github.com/langgenius/dify/blob/main/api/commands.py) - [docker/docker-compose.yaml](https://github.com/langgenius/dify/blob/main/docker/docker-compose.yaml) --- This response is meant to be useful and save you time. It is **not meant to be a precise solution**, but rather a starting point for your own research. Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant. If you want to continue the conversation, start your reply with @dosu-bot.
Author
Owner

@crazywoola commented on GitHub (Jan 29, 2024):

Please check your key is correct. You can paste the request payload as well.

@crazywoola commented on GitHub (Jan 29, 2024): Please check your key is correct. You can paste the request payload as well.
Author
Owner

@Sunwc0 commented on GitHub (Jan 30, 2024):

两个问题:
1.宿主机的时区
2.dify的时区选择成中国时区
zhipu的token校验机制有时间戳校验逻辑

@Sunwc0 commented on GitHub (Jan 30, 2024): 两个问题: 1.宿主机的时区 2.dify的时区选择成中国时区 zhipu的token校验机制有时间戳校验逻辑
Author
Owner

@SongSongK commented on GitHub (Jul 15, 2024):

两个问题: 1.发起机的时区 2.dify的时区选择成为中国时区 zhipu的token验证机制有时间戳验证逻辑

1.dify的时区已设置为中国
2.宿主机也是上海时区
但是看docker-api容器的程序日志显示还是UTC的时间,你可以尝试下修改zhipu apikey ,看看有没有办法修改成功
image
image

@SongSongK commented on GitHub (Jul 15, 2024): > 两个问题: 1.发起机的时区 2.dify的时区选择成为中国时区 zhipu的token验证机制有时间戳验证逻辑 1.dify的时区已设置为中国 2.宿主机也是上海时区 但是看docker-api容器的程序日志显示还是UTC的时间,你可以尝试下修改zhipu apikey ,看看有没有办法修改成功 ![image](https://github.com/user-attachments/assets/ffc62048-e1fa-4de6-b90d-5383d3a0638a) ![image](https://github.com/user-attachments/assets/7a5593a2-a57f-4e7c-8d93-8625429c555d)
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langgenius/dify#988