[GH-ISSUE #20642] feat: Web search consumes a lot of context #122556

New Issue

GiteaMirror · 2026-05-21T01:26:53-05:00

GiteaMirror commented

2026-05-21 01:26:53 -05:00

Originally created by @belugaming on GitHub (Jan 13, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/20642

Check Existing Issues

I have searched for all existing open AND closed issues and discussions for similar requests. I have found none that is comparable to my request.

Verify Feature Scope

I have read through and understood the scope definition for feature requests in the Issues section. I believe my feature request meets the definition and belongs in the Issues section instead of the Discussions.

Problem Description

No

Desired Solution you'd like

Version 0.7.2 provides many useful tools for AI, which is great, and I'm very grateful for everyone's contributions. Now I've encountered a problem: when I have the AI search online and engage in multiple rounds of dialogue, the context becomes incredibly complex. I've only had three dialogues, but the token count has reached 200,000. Is there any way to compress the context? I know previous versions could compress it, but their ability to search for information online was very poor.

Alternatives Considered

No response

Additional Context

No response

Originally created by @belugaming on GitHub (Jan 13, 2026). Original GitHub issue: https://github.com/open-webui/open-webui/issues/20642 ### Check Existing Issues - [x] I have searched for all existing **open AND closed** issues and discussions for similar requests. I have found none that is comparable to my request. ### Verify Feature Scope - [x] I have read through and understood the scope definition for feature requests in the Issues section. I believe my feature request meets the definition and belongs in the Issues section instead of the Discussions. ### Problem Description No ### Desired Solution you'd like Version 0.7.2 provides many useful tools for AI, which is great, and I'm very grateful for everyone's contributions. Now I've encountered a problem: when I have the AI search online and engage in multiple rounds of dialogue, the context becomes incredibly complex. I've only had three dialogues, but the token count has reached 200,000. Is there any way to compress the context? I know previous versions could compress it, but their ability to search for information online was very poor. ### Alternatives Considered _No response_ ### Additional Context _No response_

GiteaMirror closed this issue

2026-05-21 01:26:54 -05:00

Sign in to join this conversation.

Branches Tags

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/open-webui#122556