issue: Ask a question with a long pasted text, there is a problem #6488

New Issue

2025-11-11T16:56:41-06:00

GiteaMirror commented

2025-11-11 16:56:41 -06:00

Originally created by @leioukupo on GitHub (Sep 24, 2025).

Check Existing Issues

I have searched for any existing and/or related issues.
I have searched for any existing and/or related discussions.
I am using the latest version of Open WebUI.

Installation Method

Docker

Open WebUI Version

0.6.30

Ollama Version (if applicable)

0.12.0

Operating System

debian12

Browser (if applicable)

edge

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

The AI should answer my question

Actual Behavior

I have turned off all web search options

Steps to Reproduce

Paste a long enough code to create a long text file.
Send it to the AI for answers.
Continue the conversation, same as before.
My new API show calling GPT 4O Mini, and only has completion.
For comparison, I opened a new conversation without the long text file and asked a random question. It responded.
My new API shows that the model being called is the selected model.

Logs & Screenshots

Additional Information

No response

Originally created by @leioukupo on GitHub (Sep 24, 2025). ### 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 am using the latest version of Open WebUI. ### Installation Method Docker ### Open WebUI Version 0.6.30 ### Ollama Version (if applicable) 0.12.0 ### Operating System debian12 ### Browser (if applicable) edge ### 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 The AI should answer my question ### Actual Behavior <img width="1412" height="967" alt="Image" src="https://github.com/user-attachments/assets/c360f13d-a03a-4c1a-99d4-4fa09e039d89" /> I have turned off all web search options ### Steps to Reproduce 1. Paste a long enough code to create a long text file. 2. Send it to the AI for answers. 3. Continue the conversation, same as before. My new API show calling GPT 4O Mini, and only has completion. For comparison, I opened a new conversation without the long text file and asked a random question. It responded. My new API shows that the model being called is the selected model. ### Logs & Screenshots <img width="1412" height="967" alt="Image" src="https://github.com/user-attachments/assets/c360f13d-a03a-4c1a-99d4-4fa09e039d89" /> ### Additional Information _No response_

GiteaMirror added the bug label 2025-11-11 16:56:41 -06:00

GiteaMirror closed this issue

2025-11-11 16:56:42 -06:00

GiteaMirror referenced this issue

2026-04-19 20:45:56 -05:00

[GH-ISSUE #6488] MetaAI wrapper #14383

GiteaMirror referenced this issue

2026-04-25 04:17:15 -05:00

[GH-ISSUE #6488] MetaAI wrapper #29911

GiteaMirror referenced this issue

2026-05-05 14:16:16 -05:00

[GH-ISSUE #6488] MetaAI wrapper #53049