[GH-ISSUE #16452] issue: Streaming response not iterable error - Organization Not Verified #56575

Closed
opened 2026-05-05 19:43:43 -05:00 by GiteaMirror · 4 comments
Owner

Originally created by @jamesmalin on GitHub (Aug 10, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/16452

Check Existing Issues

  • I have searched the existing issues and discussions.
  • I am using the latest version of Open WebUI.

Installation Method

Docker

Open WebUI Version

0.6.21

Ollama Version (if applicable)

No response

Operating System

macOS Sequoia

Browser (if applicable)

No response

Confirmation

  • I have read and followed all instructions in README.md.
  • I am using the latest version of both Open WebUI and Ollama.
  • I have included the browser console logs.
  • I have included the Docker container logs.
  • I have provided every relevant configuration, setting, and environment variable used in my setup.
  • I have clearly listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc).
  • I have documented step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation. My steps:
  • Start with the initial platform/version/OS and dependencies used,
  • Specify exact install/launch/configure commands,
  • List URLs visited, user input (incl. example values/emails/passwords if needed),
  • Describe all options and toggles enabled or changed,
  • Include any files or environmental changes,
  • Identify the expected and actual result at each stage,
  • Ensure any reasonably skilled user can follow and hit the same issue.

Expected Behavior

{"error":{"message":"Your organization must be verified to stream this model. Please go to: https://platform.openai.com/settings/organization/general and click on Verify Organization. If you just verified, it can take up to 15 minutes for access to propagate.","type":"invalid_request_error","param":"stream","code":"unsupported_value"}}

Actual Behavior

{"detail":"argument of type 'JSONResponse' is not iterable"}

Steps to Reproduce

NOTE: This is PRIOR to organization verification. If you are seeing the following in your OpenAI account, you will not get the error:
Image

  1. Clone fresh repo of open-webui: git clone git@github.com:open-webui/open-webui.git
  2. Run docker with your API key: docker run -d -p 3000:8080 -e OPENAI_API_KEY=your_secret_key -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main
  3. In a new chat, from the models drop-down, select External -> gpt-5
  4. Open Network tab in developer console (Firefox, Chrome, etc.)
  5. In chat, type: Hello
  6. Gives error, find the recent post request
  7. See the post response
    {"detail":"argument of type 'JSONResponse' is not iterable"}

Logs & Screenshots

Unfortunately, I did not take a screenshot before fixing the issue. I solved the problem which is ready for a PR, saw the real error, and then verified my organization.

Additional Information

You should see that you need to verify your organization if it has not yet been. This is helpful for users that have no idea why the response is not working.

Currently, without implementing a fix, you only see:
"argument of type 'JSONResponse' is not iterable"

Originally created by @jamesmalin on GitHub (Aug 10, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/16452 ### Check Existing Issues - [x] I have searched the existing issues and discussions. - [x] I am using the latest version of Open WebUI. ### Installation Method Docker ### Open WebUI Version 0.6.21 ### Ollama Version (if applicable) _No response_ ### Operating System macOS Sequoia ### Browser (if applicable) _No response_ ### Confirmation - [x] I have read and followed all instructions in `README.md`. - [x] I am using the latest version of **both** Open WebUI and Ollama. - [x] I have included the browser console logs. - [x] I have included the Docker container logs. - [x] I have **provided every relevant configuration, setting, and environment variable used in my setup.** - [x] I have clearly **listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup** (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc). - [x] I have documented **step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation**. My steps: - Start with the initial platform/version/OS and dependencies used, - Specify exact install/launch/configure commands, - List URLs visited, user input (incl. example values/emails/passwords if needed), - Describe all options and toggles enabled or changed, - Include any files or environmental changes, - Identify the expected and actual result at each stage, - Ensure any reasonably skilled user can follow and hit the same issue. ### Expected Behavior {"error":{"message":"Your organization must be verified to stream this model. Please go to: https://platform.openai.com/settings/organization/general and click on Verify Organization. If you just verified, it can take up to 15 minutes for access to propagate.","type":"invalid_request_error","param":"stream","code":"unsupported_value"}} ### Actual Behavior {"detail":"argument of type 'JSONResponse' is not iterable"} ### Steps to Reproduce NOTE: This is PRIOR to organization verification. If you are seeing the following in your OpenAI account, you will not get the error: <img width="330" height="106" alt="Image" src="https://github.com/user-attachments/assets/74de1ad0-a7fb-4087-8aa5-6db602e91d5a" /> 1. Clone fresh repo of open-webui: `git clone git@github.com:open-webui/open-webui.git` 2. Run docker with your API key: `docker run -d -p 3000:8080 -e OPENAI_API_KEY=your_secret_key -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main` 3. In a new chat, from the models drop-down, select External -> gpt-5 4. Open Network tab in developer console (Firefox, Chrome, etc.) 4. In chat, type: `Hello` 5. Gives error, find the recent post request 6. See the post response {"detail":"argument of type 'JSONResponse' is not iterable"} ### Logs & Screenshots Unfortunately, I did not take a screenshot before fixing the issue. I solved the problem which is ready for a PR, saw the real error, and then verified my organization. ### Additional Information You should see that you need to verify your organization if it has not yet been. This is helpful for users that have no idea why the response is not working. Currently, without implementing a fix, you only see: "argument of type 'JSONResponse' is not iterable"
GiteaMirror added the bug label 2026-05-05 19:43:43 -05:00
Author
Owner

@cory2005 commented on GitHub (Aug 10, 2025):

I have a similar error(I think?) using openai models but not anthropic models.

Image
<!-- gh-comment-id:3172874290 --> @cory2005 commented on GitHub (Aug 10, 2025): I have a similar error(I think?) using openai models but not anthropic models. <img width="1532" height="492" alt="Image" src="https://github.com/user-attachments/assets/51350a91-1b80-4ede-8519-52cc9d65e6a8" />
Author
Owner

@jayzhoukj commented on GitHub (Aug 10, 2025):

I am getting the same error, but only certain OpenAI models are not working.

The following models are tested and confirmed to be working:

  • gpt-4
  • gpt-4o
  • gpt-4.1
  • gpt-5-chat-latest
  • o3-mini

The following models are tested and confirmed to be NOT working:

  • o4-mini-deep-research
  • o3
  • gpt-5
<!-- gh-comment-id:3172876827 --> @jayzhoukj commented on GitHub (Aug 10, 2025): I am getting the same error, but only certain OpenAI models are not working. The following models are tested and confirmed to be working: - `gpt-4` - `gpt-4o` - `gpt-4.1` - `gpt-5-chat-latest` - `o3-mini` The following models are tested and confirmed to be NOT working: - `o4-mini-deep-research` - `o3` - `gpt-5`
Author
Owner

@tjbck commented on GitHub (Aug 10, 2025):

Should be addressed with 059cc636f6c28c6e496ffc0dc05cc0e2390981f3!

@jayzhoukj those models require responses API and not chat completions.

<!-- gh-comment-id:3172877540 --> @tjbck commented on GitHub (Aug 10, 2025): Should be addressed with 059cc636f6c28c6e496ffc0dc05cc0e2390981f3! @jayzhoukj those models require responses API and not chat completions.
Author
Owner

@jamesmalin commented on GitHub (Aug 10, 2025):

It looks like your new commit has the dictionary added in -- would have been cool to use the PR I put in (same code for that portion), but I understand you would have needed to pull it in first.

chat completions actually still works for gpt-5 btw. But, responses API allows additional functionality that was not previously available in gpt-4:
Image

With that said, I do not see any changes that are adding that functionality. See:
https://platform.openai.com/docs/guides/latest-model?reasoning-effort-mode=chat#migrating-from-chat-completions-to-responses-api

It would be great to add the new functionality released with gpt-5 for "chain of thought (CoT)".

Edit, adding for clarity, but can be found in the URL above:
Image

Image
<!-- gh-comment-id:3172903920 --> @jamesmalin commented on GitHub (Aug 10, 2025): It looks like your new commit has the dictionary added in -- would have been cool to use the PR I put in (same code for that portion), but I understand you would have needed to pull it in first. chat completions actually still works for gpt-5 btw. But, responses API allows additional functionality that was not previously available in gpt-4: <img width="732" height="462" alt="Image" src="https://github.com/user-attachments/assets/45214cfb-a4e2-4d8a-ab82-622d8933e22f" /> With that said, I do not see any changes that are adding that functionality. See: https://platform.openai.com/docs/guides/latest-model?reasoning-effort-mode=chat#migrating-from-chat-completions-to-responses-api It would be great to add the new functionality released with gpt-5 for "chain of thought (CoT)". Edit, adding for clarity, but can be found in the URL above: <img width="761" height="416" alt="Image" src="https://github.com/user-attachments/assets/8b6fcb02-8479-4d1d-b43d-52ad7e64f98b" /> <img width="720" height="229" alt="Image" src="https://github.com/user-attachments/assets/fec8ff0b-c370-4e57-9a35-3c51248343fb" />
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#56575