issue: web page extracting not working with 0.6.16 #5785

New Issue

2025-11-11T16:33:37-06:00

GiteaMirror commented

2025-11-11 16:33:37 -06:00

Originally created by @Fredson001 on GitHub (Jul 16, 2025).

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

0.6.16

Ollama Version (if applicable)

No response

Operating System

Windows 11

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

When entering #URL in prompt, the web page text will be extracted and included in the prompt when submitted.

Actual Behavior

When entering #URL in prompt, the web page text is extracted but is NOT included in the prompt when submitted.

Steps to Reproduce

Enter "#https://www.sciencedaily.com/releases/2025/07/250713031449.htm" in prompt
Click link above prompt to load text from web page.
Add "give me a summary" to prompt
Submit prompt
I get message that there is nothing to summarize

Logs & Screenshots

None

Additional Information

Work fine with 0.6.15 but not 0.6.16. Also will works properly is submitting a Youtube URL. It will fetch the YT transcript and include it as context inthe prompt.

Originally created by @Fredson001 on GitHub (Jul 16, 2025). ### 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 0.6.16 ### Ollama Version (if applicable) _No response_ ### Operating System Windows 11 ### 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 When entering #URL in prompt, the web page text will be extracted and included in the prompt when submitted. ### Actual Behavior When entering #URL in prompt, the web page text is extracted but is NOT included in the prompt when submitted. ### Steps to Reproduce 1. Enter "#https://www.sciencedaily.com/releases/2025/07/250713031449.htm" in prompt 2. Click link above prompt to load text from web page. 3. Add "give me a summary" to prompt 4. Submit prompt 5. I get message that there is nothing to summarize ### Logs & Screenshots None ### Additional Information Work fine with 0.6.15 but not 0.6.16. Also will works properly is submitting a Youtube URL. It will fetch the YT transcript and include it as context inthe prompt.

GiteaMirror added the bug label 2025-11-11 16:33:37 -06:00

GiteaMirror closed this issue

2025-11-11 16:33:38 -06:00

GiteaMirror commented

2025-11-11 16:33:38 -06:00

@guenhter commented on GitHub (Jul 16, 2025):

@Fredson001 Could you update the issue title to something like: "issue: web page extracting not working with 0.6.16.

@guenhter commented on GitHub (Jul 16, 2025): @Fredson001 Could you update the issue title to something like: "issue: web page extracting not working with 0.6.16.

GiteaMirror commented

2025-11-11 16:33:39 -06:00

@tjbck commented on GitHub (Jul 16, 2025):

Unable to reproduce from our end, this might've been a network issue.

@tjbck commented on GitHub (Jul 16, 2025): <img width="1137" height="743" alt="Image" src="https://github.com/user-attachments/assets/68d73029-20ff-4e21-9c96-bda30563e552" /> Unable to reproduce from our end, this might've been a network issue.

GiteaMirror referenced this issue

2026-04-19 20:35:42 -05:00

[GH-ISSUE #5785] text-embedding-3-large, error hugging face ??? #14126

GiteaMirror referenced this issue

2026-04-25 04:02:40 -05:00

[GH-ISSUE #5785] text-embedding-3-large, error hugging face ??? #29654

GiteaMirror referenced this issue

2026-05-05 13:55:46 -05:00

[GH-ISSUE #5785] text-embedding-3-large, error hugging face ??? #52792

GiteaMirror referenced this issue

2026-05-13 01:06:38 -05:00

[GH-ISSUE #5785] text-embedding-3-large, error hugging face ??? #68730