github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-05-24 03:18:21 -05:00
Code Issues 2.4k Packages Projects Releases 129 Wiki Activity

[GH-ISSUE #14795] issue: Model Response Extremely Slow #120675

New Issue
Closed
opened 2026-05-20 22:20:54 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-05-20 22:20:54 -05:00
Owner
Copy Link

Originally created by @JoeChen2me on GitHub (Jun 9, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/14795

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

0.6.13

Ollama Version (if applicable)

unused

Operating System

Deploy on Ubuntu, Use on Mac

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

When I initiate a question, the model's response should return quickly.

Actual Behavior

In actual use, it takes a long time to receive a response from the model. According to the Docker logs, a lot of time is spent requesting the application version before the model's API request is initiated.

Steps to Reproduce

ask a question in openwebui and record the TFTT .

Logs & Screenshots

Docker Log

Task IDs for chat 153a9e2e-eeb2-4abf-abae-f54b90c1a4cb: []
2025-06-09 10:44:15.092 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "GET /api/tasks/chat/153a9e2e-eeb2-4abf-abae-f54b90c1a4cb HTTP/1.1" 200 - {}
2025-06-09 10:44:15.357 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "GET /ollama/api/version HTTP/1.1" 200 - {}
2025-06-09 10:44:19.711 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "GET /_app/version.json HTTP/1.1" 200 - {}
2025-06-09 10:44:20.869 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 205.198.68.146:0 - "GET /_app/version.json HTTP/1.1" 304 - {}
2025-06-09 10:44:38.960 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "POST /api/v1/chats/153a9e2e-eeb2-4abf-abae-f54b90c1a4cb HTTP/1.1" 200 - {}
2025-06-09 10:44:39.157 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {}
2025-06-09 10:44:53.174 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 110.65.147.203:0 - "GET /_app/version.json HTTP/1.1" 200 - {}
2025-06-09 10:44:55.569 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 216.247.110.21:0 - "GET /_app/version.json HTTP/1.1" 200 - {}
2025-06-09 10:45:20.813 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "GET /_app/version.json HTTP/1.1" 200 - {}
2025-06-09 10:45:20.861 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 205.198.68.146:0 - "GET /_app/version.json HTTP/1.1" 304 - {}
2025-06-09 10:45:50.841 | INFO     | open_webui.routers.openai:get_all_models:391 - get_all_models() - {}
2025-06-09 10:45:51.991 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "POST /api/chat/completions HTTP/1.1" 200 - {}
2025-06-09 10:45:52.173 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {}
2025-06-09 10:45:53.188 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 110.65.147.203:0 - "GET /_app/version.json HTTP/1.1" 200 - {}
2025-06-09 10:45:55.467 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 216.247.110.21:0 - "GET /_app/version.json HTTP/1.1" 200 - {}
2025-06-09 10:45:59.392 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "GET /_app/immutable/assets/KaTeX_Size2-Regular.Dy4dx90m.woff2 HTTP/1.1" 200 - {

Browser

Image

Additional Information

I don't understand why each time a chat request is initiated, it needs to obtain the app's version, which causes a large amount of redundant performance overhead, resulting in significant performance loss.


Task IDs for chat 153a9e2e-eeb2-4abf-abae-f54b90c1a4cb: []
2025-06-09 10:53:52.409 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "GET /api/tasks/chat/153a9e2e-eeb2-4abf-abae-f54b90c1a4cb HTTP/1.1" 200 - {}
2025-06-09 10:53:52.845 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "GET /ollama/api/version HTTP/1.1" 200 - {}
2025-06-09 10:53:53.263 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 110.65.147.203:0 - "GET /_app/version.json HTTP/1.1" 200 - {}
2025-06-09 10:53:55.746 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 216.247.110.21:0 - "GET /_app/version.json HTTP/1.1" 200 - {}
2025-06-09 10:54:04.955 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "GET /manifest.json HTTP/1.1" 200 - {}
2025-06-09 10:54:04.958 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "GET /_app/immutable/assets/26.wEbTgpRj.css HTTP/1.1" 200 - {}
2025-06-09 10:54:15.285 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "POST /api/v1/chats/153a9e2e-eeb2-4abf-abae-f54b90c1a4cb HTTP/1.1" 200 - {}
2025-06-09 10:54:15.696 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {}
2025-06-09 10:54:19.420 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "GET /_app/version.json HTTP/1.1" 200 - {}
2025-06-09 10:54:53.285 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 110.65.147.203:0 - "GET /_app/version.json HTTP/1.1" 200 - {}
2025-06-09 10:55:19.699 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "GET /_app/version.json HTTP/1.1" 200 - {}
2025-06-09 10:55:53.288 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 110.65.147.203:0 - "GET /_app/version.json HTTP/1.1" 200 - {}
2025-06-09 10:55:55.573 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 216.247.110.21:0 - "GET /_app/version.json HTTP/1.1" 200 - {}
2025-06-09 10:56:19.743 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "GET /_app/version.json HTTP/1.1" 200 - {}
2025-06-09 10:56:53.297 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 110.65.147.203:0 - "GET /_app/version.json HTTP/1.1" 200 - {}
2025-06-09 10:56:55.472 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 216.247.110.21:0 - "GET /_app/version.json HTTP/1.1" 200 - {}
2025-06-09 10:57:20.895 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "GET /_app/version.json HTTP/1.1" 200 - {}
2025-06-09 10:57:25.852 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 205.198.68.146:0 - "GET /_app/version.json HTTP/1.1" 304 - {}
Originally created by @JoeChen2me on GitHub (Jun 9, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/14795 ### 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 0.6.13 ### Ollama Version (if applicable) unused ### Operating System Deploy on Ubuntu, Use on Mac ### 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 When I initiate a question, the model's response should return quickly. ### Actual Behavior In actual use, it takes a long time to receive a response from the model. According to the Docker logs, a lot of time is spent requesting the application version before the model's API request is initiated. ### Steps to Reproduce ask a question in openwebui and record the TFTT . ### Logs & Screenshots Docker Log ```sh Task IDs for chat 153a9e2e-eeb2-4abf-abae-f54b90c1a4cb: [] 2025-06-09 10:44:15.092 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "GET /api/tasks/chat/153a9e2e-eeb2-4abf-abae-f54b90c1a4cb HTTP/1.1" 200 - {} 2025-06-09 10:44:15.357 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "GET /ollama/api/version HTTP/1.1" 200 - {} 2025-06-09 10:44:19.711 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "GET /_app/version.json HTTP/1.1" 200 - {} 2025-06-09 10:44:20.869 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 205.198.68.146:0 - "GET /_app/version.json HTTP/1.1" 304 - {} 2025-06-09 10:44:38.960 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "POST /api/v1/chats/153a9e2e-eeb2-4abf-abae-f54b90c1a4cb HTTP/1.1" 200 - {} 2025-06-09 10:44:39.157 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {} 2025-06-09 10:44:53.174 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 110.65.147.203:0 - "GET /_app/version.json HTTP/1.1" 200 - {} 2025-06-09 10:44:55.569 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 216.247.110.21:0 - "GET /_app/version.json HTTP/1.1" 200 - {} 2025-06-09 10:45:20.813 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "GET /_app/version.json HTTP/1.1" 200 - {} 2025-06-09 10:45:20.861 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 205.198.68.146:0 - "GET /_app/version.json HTTP/1.1" 304 - {} 2025-06-09 10:45:50.841 | INFO | open_webui.routers.openai:get_all_models:391 - get_all_models() - {} 2025-06-09 10:45:51.991 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "POST /api/chat/completions HTTP/1.1" 200 - {} 2025-06-09 10:45:52.173 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {} 2025-06-09 10:45:53.188 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 110.65.147.203:0 - "GET /_app/version.json HTTP/1.1" 200 - {} 2025-06-09 10:45:55.467 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 216.247.110.21:0 - "GET /_app/version.json HTTP/1.1" 200 - {} 2025-06-09 10:45:59.392 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "GET /_app/immutable/assets/KaTeX_Size2-Regular.Dy4dx90m.woff2 HTTP/1.1" 200 - { ``` Browser ![Image](https://github.com/user-attachments/assets/5f0374e0-0a00-4a00-a574-b1842a594dc1) ### Additional Information I don't understand why each time a chat request is initiated, it needs to obtain the app's version, which causes a large amount of redundant performance overhead, resulting in significant performance loss. ```sh Task IDs for chat 153a9e2e-eeb2-4abf-abae-f54b90c1a4cb: [] 2025-06-09 10:53:52.409 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "GET /api/tasks/chat/153a9e2e-eeb2-4abf-abae-f54b90c1a4cb HTTP/1.1" 200 - {} 2025-06-09 10:53:52.845 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "GET /ollama/api/version HTTP/1.1" 200 - {} 2025-06-09 10:53:53.263 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 110.65.147.203:0 - "GET /_app/version.json HTTP/1.1" 200 - {} 2025-06-09 10:53:55.746 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 216.247.110.21:0 - "GET /_app/version.json HTTP/1.1" 200 - {} 2025-06-09 10:54:04.955 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "GET /manifest.json HTTP/1.1" 200 - {} 2025-06-09 10:54:04.958 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "GET /_app/immutable/assets/26.wEbTgpRj.css HTTP/1.1" 200 - {} 2025-06-09 10:54:15.285 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "POST /api/v1/chats/153a9e2e-eeb2-4abf-abae-f54b90c1a4cb HTTP/1.1" 200 - {} 2025-06-09 10:54:15.696 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {} 2025-06-09 10:54:19.420 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "GET /_app/version.json HTTP/1.1" 200 - {} 2025-06-09 10:54:53.285 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 110.65.147.203:0 - "GET /_app/version.json HTTP/1.1" 200 - {} 2025-06-09 10:55:19.699 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "GET /_app/version.json HTTP/1.1" 200 - {} 2025-06-09 10:55:53.288 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 110.65.147.203:0 - "GET /_app/version.json HTTP/1.1" 200 - {} 2025-06-09 10:55:55.573 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 216.247.110.21:0 - "GET /_app/version.json HTTP/1.1" 200 - {} 2025-06-09 10:56:19.743 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "GET /_app/version.json HTTP/1.1" 200 - {} 2025-06-09 10:56:53.297 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 110.65.147.203:0 - "GET /_app/version.json HTTP/1.1" 200 - {} 2025-06-09 10:56:55.472 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 216.247.110.21:0 - "GET /_app/version.json HTTP/1.1" 200 - {} 2025-06-09 10:57:20.895 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 139.162.17.136:0 - "GET /_app/version.json HTTP/1.1" 200 - {} 2025-06-09 10:57:25.852 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 205.198.68.146:0 - "GET /_app/version.json HTTP/1.1" 304 - {} ```
GiteaMirror added the bug label 2026-05-20 22:20:54 -05:00
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#120675
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?