[PR #8717] [CLOSED] refac: improve chat performance for slow platform(#8538). #9073

Closed
opened 2025-11-11 18:13:28 -06:00 by GiteaMirror · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/open-webui/open-webui/pull/8717
Author: @okamototk
Created: 1/21/2025
Status: Closed

Base: devHead: improve-performance-for-slowPC


📝 Commits (1)

  • 20279ff refac: improve chat performance for slow platform(#8538).

📊 Changes

1 file changed (+3 additions, -3 deletions)

View changed files

📝 backend/open_webui/config.py (+3 -3)

📄 Description

Pull Request Checklist

Note to first-time contributors: Please open a discussion post in [Discussions]

https://github.com/open-webui/open-webui/discussions/8538

Description

For slow Laptop, currently Open WebUI is very very slow. It's improve performance some by disable some LLM inference during tag, search, retrival query. If you accept this PR, it's good for a lot of beginner. But for more professional use, current configuration is better for accurate answer in chat.

Disable LLM utilization for:

  • TAG GENERATION
  • SEARCH QUERY GENERATION
  • RETRIVAL QUERY GENERATION

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/open-webui/open-webui/pull/8717 **Author:** [@okamototk](https://github.com/okamototk) **Created:** 1/21/2025 **Status:** ❌ Closed **Base:** `dev` ← **Head:** `improve-performance-for-slowPC` --- ### 📝 Commits (1) - [`20279ff`](https://github.com/open-webui/open-webui/commit/20279ffcf9d69e3e4710c0307c722084a4e8b1d6) refac: improve chat performance for slow platform(#8538). ### 📊 Changes **1 file changed** (+3 additions, -3 deletions) <details> <summary>View changed files</summary> 📝 `backend/open_webui/config.py` (+3 -3) </details> ### 📄 Description # Pull Request Checklist ### Note to first-time contributors: Please open a discussion post in [Discussions] https://github.com/open-webui/open-webui/discussions/8538 ### Description For slow Laptop, currently Open WebUI is very very slow. It's improve performance some by disable some LLM inference during tag, search, retrival query. If you accept this PR, it's good for a lot of beginner. But for more professional use, current configuration is better for accurate answer in chat. Disable LLM utilization for: * TAG GENERATION * SEARCH QUERY GENERATION * RETRIVAL QUERY GENERATION --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
GiteaMirror added the pull-request label 2025-11-11 18:13:28 -06:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#9073