github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-07-17 08:21:12 -05:00
Code Issues 2.4k Packages Projects Releases 129 Wiki Activity

[GH-ISSUE #22557] issue: User configured "Advanced Paramters" for Ollama models are sent to Open AI models #74349

New Issue
Closed
opened 2026-05-13 07:03:58 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-13 07:03:58 -05:00
Owner
Copy Link

Originally created by @derek-assurity on GitHub (Mar 11, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/22557

Check Existing Issues

  • I have searched for any existing and/or related issues.
  • I have searched for any existing and/or related discussions.
  • I have also searched in the CLOSED issues AND CLOSED discussions and found no related items (your issue might already be addressed on the development branch!).
  • I am using the latest version of Open WebUI.

Installation Method

Docker

Open WebUI Version

v0.8.8

Ollama Version (if applicable)

v0.17.5

Operating System

Ubuntu 22.04

Browser (if applicable)

Firefox v147.0.2

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

Setting the num_ctx to 10000 in the Advanced Parameters, should not affect calls to non Ollama hosted LLM that are accessed via an Open AI connector.

Actual Behavior

Setting the num_ctx to 10000, in the Advanced Parameters for a user, breaks calls to Bedrock which is accessed via a LiteLLM proxy. With the error message:

File "/usr/lib/python3.13/site-packages/litellm/llms/bedrock/chat/invoke_handler.py", line 271, in make_call
raise BedrockError(status_code=error_code, message=err.response.text)
litellm.llms.bedrock.common_utils.BedrockError: 
{
    "message": "The model returned the following errors: Malformed input request: #: extraneous key [num_ctx] is not permitted, please reformat your input and try again."
}

Debug on litellm shows the following being sent:

[92m23:43:36 - LiteLLM Proxy:DEBUG: common_request_processing.py:716 - Request received by LiteLLM:
{
"stream": true,
"model": "bedrock-nova-lite-v1",
"messages": [
{
"role": "user",
"content": "<query to LLM here>."
}
],
"num_ctx": 10000,
"num_batch": 512,
"metadata": 
{}
}

Litellm has been configured to drop_params: true but this does not catch this issue.

Steps to Reproduce

  1. Deploy litellm as a proxy for AWS Bedrock
  2. Create an Open AI connector in Admin Panel to connect to the litellm proxy
  3. Set the num_ctx parameter to 10000 in the Advanced Parameters for a user
  4. Send a request to a Bedrock based model
  5. Request will failed with a Malformed Exception

Logs & Screenshots

As detailed in steps above

Additional Information

No response

Originally created by @derek-assurity on GitHub (Mar 11, 2026). Original GitHub issue: https://github.com/open-webui/open-webui/issues/22557 ### Check Existing Issues - [x] I have searched for any existing and/or related issues. - [x] I have searched for any existing and/or related discussions. - [x] I have also searched in the CLOSED issues AND CLOSED discussions and found no related items (your issue might already be addressed on the development branch!). - [x] I am using the latest version of Open WebUI. ### Installation Method Docker ### Open WebUI Version v0.8.8 ### Ollama Version (if applicable) v0.17.5 ### Operating System Ubuntu 22.04 ### Browser (if applicable) Firefox v147.0.2 ### 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 Setting the `num_ctx` to 10000 in the Advanced Parameters, should not affect calls to non Ollama hosted LLM that are accessed via an Open AI connector. ### Actual Behavior Setting the `num_ctx` to 10000, in the Advanced Parameters for a user, breaks calls to Bedrock which is accessed via a LiteLLM proxy. With the error message: ``` File "/usr/lib/python3.13/site-packages/litellm/llms/bedrock/chat/invoke_handler.py", line 271, in make_call raise BedrockError(status_code=error_code, message=err.response.text) litellm.llms.bedrock.common_utils.BedrockError: { "message": "The model returned the following errors: Malformed input request: #: extraneous key [num_ctx] is not permitted, please reformat your input and try again." } ``` Debug on `litellm` shows the following being sent: ``` [92m23:43:36 - LiteLLM Proxy:DEBUG: common_request_processing.py:716 - Request received by LiteLLM: { "stream": true, "model": "bedrock-nova-lite-v1", "messages": [ { "role": "user", "content": "<query to LLM here>." } ], "num_ctx": 10000, "num_batch": 512, "metadata": {} } ``` Litellm has been configured to `drop_params: true` but this does not catch this issue. ### Steps to Reproduce 1. Deploy `litellm` as a proxy for AWS Bedrock 2. Create an Open AI connector in Admin Panel to connect to the litellm proxy 3. Set the `num_ctx` parameter to `10000` in the Advanced Parameters for a user 4. Send a request to a Bedrock based model 5. Request will failed with a `Malformed Exception` ### Logs & Screenshots As detailed in steps above ### Additional Information _No response_
GiteaMirror added the bug label 2026-05-13 07:03:58 -05:00
GiteaMirror commented 2026-05-13 07:04:03 -05:00
Author
Owner
Copy Link

@tjbck commented on GitHub (Mar 22, 2026):

Some openai inference providers support this param, you should remove before making a request.

<!-- gh-comment-id:4105999499 --> @tjbck commented on GitHub (Mar 22, 2026): Some openai inference providers support this param, you should remove before making a request.
GiteaMirror commented 2026-05-13 07:04:03 -05:00
Author
Owner
Copy Link

@derek-assurity commented on GitHub (Mar 22, 2026):

I don't understand why this has been closed. The fields are even identified in the UI with "(ollama)" tags, they should not be sent if they are not part of the OpenAI API. This means settings have been changed any time a model is changed and the user has to know if the model is being served from Ollama or via a proxy.

<!-- gh-comment-id:4106902463 --> @derek-assurity commented on GitHub (Mar 22, 2026): I don't understand why this has been closed. The fields are even identified in the UI with "(ollama)" tags, they should not be sent if they are not part of the OpenAI API. This means settings have been changed any time a model is changed and the user has to know if the model is being served from Ollama or via a proxy.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
confirmed
confirmed issue
core
documentation
enhancement
good first issue
help wanted
non-core
pull-request
Mirrored from GitHub Pull Request
 python
question
testing wanted
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#74349
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?