langgenius/dify-official-plugins
1
0
Fork 0
mirror of https://github.com/langgenius/dify-official-plugins.git synced 2026-07-21 17:45:23 -04:00
Code Issues 54 Packages Projects Releases Wiki Activity

OpenAI-API-compatible bug #94

New Issue
Closed
opened 2026-02-16 10:18:03 -05:00 by yindo · 4 comments
yindo commented 2026-02-16 10:18:03 -05:00
Owner
Copy Link
Copy Source

Originally created by @XiaoCC on GitHub (Mar 20, 2025).

Self Checks

  • This is only for bug report, if you would like to ask a question, please head to Discussions.
  • I have searched for existing issues search for existing issues, including closed ones.
  • I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
  • [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
  • Please do not modify this template :) and fill in all the required fields.

Dify version

1.1.0

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

添加火山云的联网搜索bot应用模型 成功 但是调用llm没有返回值！
The network search bot application model for adding Volcano Cloud was successful, but calling LLM did not return any value!

✔️ Expected Behavior

希望能正常使用火山云的联网搜索bot应用模型
I hope to be able to use the Volcano Cloud's networked search bot application model normally

❌ Actual Behavior

Image

Image

Image

Image

Originally created by @XiaoCC on GitHub (Mar 20, 2025). ### Self Checks - [x] This is only for bug report, if you would like to ask a question, please head to [Discussions](https://github.com/langgenius/dify/discussions/categories/general). - [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 submit this report (我已阅读并同意 [Language Policy](https://github.com/langgenius/dify/issues/1542)). - [x] [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:） - [x] Please do not modify this template :) and fill in all the required fields. ### Dify version 1.1.0 ### Cloud or Self Hosted Self Hosted (Docker) ### Steps to reproduce 添加火山云的联网搜索bot应用模型 成功 但是调用llm没有返回值！ The network search bot application model for adding Volcano Cloud was successful, but calling LLM did not return any value! ### ✔️ Expected Behavior 希望能正常使用火山云的联网搜索bot应用模型 I hope to be able to use the Volcano Cloud's networked search bot application model normally ### ❌ Actual Behavior ![Image](https://github.com/user-attachments/assets/ac8b9c4e-aa4a-4ac0-8555-314488ad375e) ![Image](https://github.com/user-attachments/assets/4ee30f43-1606-473e-b533-b9a354ee6bf2) ![Image](https://github.com/user-attachments/assets/f5daa2f9-192e-4d24-aa57-c3f86d8c8811) ![Image](https://github.com/user-attachments/assets/85f5a496-85df-40f1-9db4-c49756f28c5c)
yindo closed this issue 2026-02-16 10:18:03 -05:00
yindo commented 2026-02-16 10:18:03 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (Mar 20, 2025):

I found a similar unsolved discussion regarding adding a self-deployed LLM model and encountering errors [1].

For the issue you're experiencing with the LLM not returning values, there are a few common causes and solutions you can consider:

  1. Multiple End Blocks: Ensure your workflow contains only one end block. Restructure your workflow to converge all branches into a single endpoint [2].

  2. Runtime Errors: Check for common runtime errors such as Variable Not Found Error, Invalid Context Structure Error, Invalid Variable Type Error, Model Not Exist Error, LLM Authorization Required Error, and No Prompt Found Error. Ensure variables and prompts are correctly set, the context structure is valid, a model is selected and authorized, and prompts are not empty [3].

  3. IF-ELSE Conditions: If you are using IF-ELSE conditions and experiencing issues with LLM node streaming output, this may be due to a known issue in Dify version 0.14.2. This problem has been resolved in a recent update through PR langgenius/dify#12105. Ensure you are using the latest version of Dify that includes this fix [4].

These steps should help you troubleshoot and resolve the issue with the LLM not returning values.

To continue talking to Dosu, mention @dosu.

Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other

@dosubot[bot] commented on GitHub (Mar 20, 2025): <!-- Answer --> I found a similar unsolved discussion regarding adding a self-deployed LLM model and encountering errors <sup>[[1]](https://github.com/langgenius/dify/discussions/5985)</sup>. For the issue you're experiencing with the LLM not returning values, there are a few common causes and solutions you can consider: 1. **Multiple End Blocks**: Ensure your workflow contains only one end block. Restructure your workflow to converge all branches into a single endpoint <sup>[[2]](https://github.com/langgenius/dify/issues/13532)</sup>. 2. **Runtime Errors**: Check for common runtime errors such as Variable Not Found Error, Invalid Context Structure Error, Invalid Variable Type Error, Model Not Exist Error, LLM Authorization Required Error, and No Prompt Found Error. Ensure variables and prompts are correctly set, the context structure is valid, a model is selected and authorized, and prompts are not empty <sup>[[3]](https://github.com/langgenius/dify-docs/blob/main/en/guides/workflow/error-handling/error-type.md)</sup>. 3. **IF-ELSE Conditions**: If you are using IF-ELSE conditions and experiencing issues with LLM node streaming output, this may be due to a known issue in Dify version 0.14.2. This problem has been resolved in a recent update through PR langgenius/dify#12105. Ensure you are using the latest version of Dify that includes this fix <sup>[[4]](https://github.com/langgenius/dify/issues/12068)</sup>. These steps should help you troubleshoot and resolve the issue with the LLM not returning values. <!-- Dosu Comment Footer --> *To continue talking to [Dosu](https://dosu.dev), mention @dosu.* --- <sup>Help Dosu learn! Give it feedback: [Great Response](https://app.dosu.dev/response-feedback/785c723a-e5b7-4fee-b48b-f55638041ff0?feedback_type=great_response) | [Irrelevant Answer](https://app.dosu.dev/response-feedback/785c723a-e5b7-4fee-b48b-f55638041ff0?feedback_type=irrelevant_answer) | [Incorrect Sources](https://app.dosu.dev/response-feedback/785c723a-e5b7-4fee-b48b-f55638041ff0?feedback_type=incorrect_sources) | [Too Verbose](https://app.dosu.dev/response-feedback/785c723a-e5b7-4fee-b48b-f55638041ff0?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/785c723a-e5b7-4fee-b48b-f55638041ff0?feedback_type=hallucination) | [Bug Report](https://app.dosu.dev/response-feedback/785c723a-e5b7-4fee-b48b-f55638041ff0?feedback_type=bug_report) | [Other](https://app.dosu.dev/response-feedback/785c723a-e5b7-4fee-b48b-f55638041ff0?feedback_type=other)</sup>
yindo commented 2026-02-16 10:18:03 -05:00
Author
Owner
Copy Link
Copy Source

@XiaoCC commented on GitHub (Mar 20, 2025):

{
"text": "",
"usage": {
"prompt_tokens": 0,
"prompt_unit_price": "0",
"prompt_price_unit": "0",
"prompt_price": "0",
"completion_tokens": 0,
"completion_unit_price": "0",
"completion_price_unit": "0",
"completion_price": "0",
"total_tokens": 0,
"total_price": "0",
"currency": "USD",
"latency": 1.062202364206314
},
"finish_reason": "Non-JSON encountered."
}
这是调用模型返回值 Non-JSON encountered. @Dosu

@XiaoCC commented on GitHub (Mar 20, 2025): { "text": "", "usage": { "prompt_tokens": 0, "prompt_unit_price": "0", "prompt_price_unit": "0", "prompt_price": "0", "completion_tokens": 0, "completion_unit_price": "0", "completion_price_unit": "0", "completion_price": "0", "total_tokens": 0, "total_price": "0", "currency": "USD", "latency": 1.062202364206314 }, "finish_reason": "Non-JSON encountered." } 这是调用模型返回值 Non-JSON encountered. @Dosu
yindo commented 2026-02-16 10:18:03 -05:00
Author
Owner
Copy Link
Copy Source

@XiaoCC commented on GitHub (Mar 20, 2025):

{
"model_mode": "chat",
"prompts": [
{
"role": "system",
"text": "回答用户的问题",
"files": []
},
{
"role": "user",
"text": "你好",
"files": []
}
],
"model_provider": "langgenius/openai_api_compatible/openai_api_compatible",
"model_name": "bot-20250320104820-xq7sc"
}

"model_mode": "chat", 是不是OpenAI-API-compatible的类型除了chat还得加一个bot

@XiaoCC commented on GitHub (Mar 20, 2025): { "model_mode": "chat", "prompts": [ { "role": "system", "text": "回答用户的问题", "files": [] }, { "role": "user", "text": "你好", "files": [] } ], "model_provider": "langgenius/openai_api_compatible/openai_api_compatible", "model_name": "bot-20250320104820-xq7sc" } "model_mode": "chat", 是不是OpenAI-API-compatible的类型除了chat还得加一个bot
yindo commented 2026-02-16 10:18:03 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (Aug 18, 2025):

Hi, @XiaoCC. I'm Dosu, and I'm helping the dify-official-plugins team manage their backlog and am marking this issue as stale.

Issue Summary:

  • You reported that in version 1.1.0 (self-hosted via Docker), adding the Volcano Cloud network search bot model works, but invoking the LLM returns no output with a "Non-JSON encountered" finish reason.
  • I suggested troubleshooting steps like checking for multiple end blocks, runtime errors, and ensuring the latest version is used to avoid known IF-ELSE streaming issues.
  • You shared the request payload showing use of a chat model mode with an OpenAI API compatible provider.
  • The core problem seems to be the model invocation returning empty or malformed responses.
  • The issue remains unresolved with no further updates.

What's Next:

  • Please let me know if this issue is still relevant with the latest version of dify-official-plugins by commenting here to keep the discussion open.
  • Otherwise, this issue will be automatically closed in 5 days.

Thank you for your understanding and contribution!

@dosubot[bot] commented on GitHub (Aug 18, 2025): Hi, @XiaoCC. I'm [Dosu](https://dosu.dev), and I'm helping the dify-official-plugins team manage their backlog and am marking this issue as stale. **Issue Summary:** - You reported that in version 1.1.0 (self-hosted via Docker), adding the Volcano Cloud network search bot model works, but invoking the LLM returns no output with a "Non-JSON encountered" finish reason. - I suggested troubleshooting steps like checking for multiple end blocks, runtime errors, and ensuring the latest version is used to avoid known IF-ELSE streaming issues. - You shared the request payload showing use of a chat model mode with an OpenAI API compatible provider. - The core problem seems to be the model invocation returning empty or malformed responses. - The issue remains unresolved with no further updates. **What's Next:** - Please let me know if this issue is still relevant with the latest version of dify-official-plugins by commenting here to keep the discussion open. - Otherwise, this issue will be automatically closed in 5 days. Thank you for your understanding and contribution!
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
bug
bug
dependencies
documentation
enhancement
good first issue
invalid
pull-request
Mirrored from GitHub Pull Request
 question
stale
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langgenius/dify-official-plugins#94
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?