Comments (13)
Thank you for raising an issue. We will investigate into the matter and get back to you as soon as possible.
Please make sure you have given us as much context as possible.
非常感谢您提交 issue。我们会尽快调查此事,并尽快回复您。 请确保您已经提供了尽可能多的背景信息。
from lobe-chat.
Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑🤝🧑👫🧑🏿🤝🧑🏻👩🏾🤝👨🏿👬🏿
💻 System environment
Windows
📦 Deployment environment
Docker
🌐 Browser
Edge
🐛 Problem description
On a computer with a slightly weaker configuration or a mobile phone with an average configuration (Snapdragon 870), as long as you choose a model with character restrictions, you will obviously feel stuck when typing in the chat input box, and switch to a model without character restrictions ( Such as custom model) will return to normal. This problem is not obvious on new computers with high configuration. I discovered it on an old computer today. The CPU of the old computer is i7-8550U and 16G memory. When this problem occurs, there is no problem in the CPU usage. The memory usage is Nor does it exceed 60%. I looked through the issue and found a similar issue #1701. Is it possible that a model with character limits needs to count the used characters in real time when inputting, and then renders the page, resulting in insufficient CPU or insufficient allocation of front-end threads?
🚦 Expected results
On a computer with a weaker configuration or a mobile phone, using a model with character limits (that is, with a used character statistics function) can make input in the chat box smooth.
📷 Steps to reproduce
On a computer with a weaker configuration or a mobile phone with an average configuration, select the model with character restrictions and enter text in the chat input box. The computer configuration I can reproduce is: i7-8550U, 16G memory, and the mobile phone configuration is: Snapdragon 870, 8G memory.
📝 Supplementary information
No response
from lobe-chat.
在最近版本遇到了相同的问题,在清楚历史记录后有所缓解,但是仍然不如旧版本流畅
from lobe-chat.
Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑🤝🧑👫🧑🏿🤝🧑🏻👩🏾🤝👨🏿👬🏿
I encountered the same problem in the latest version. It was alleviated after clearing the history, but it is still not as smooth as the old version.
from lobe-chat.
实测v0.147.5
不卡,docker compose 使用lobehub/lobe-chat:v0.147.5
from lobe-chat.
Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑🤝🧑👫🧑🏿🤝🧑🏻👩🏾🤝👨🏿👬🏿
Does anyone know which version was the last one without lag? This lag is of no use at all.
from lobe-chat.
@CXwudi 最新版应该修正了,你试了最新版了么?
from lobe-chat.
Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑🤝🧑👫🧑🏿🤝🧑🏻👩🏾🤝👨🏿👬🏿
@CXwudi The latest version should be corrected. Have you tried the latest version?
from lobe-chat.
哦哦,最新版没问题了,感谢修复
from lobe-chat.
Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑🤝🧑👫🧑🏿🤝🧑🏻👩🏾🤝👨🏿👬🏿
Oh, the latest version has no problem, thanks for the fix
from lobe-chat.
刚试了下当前的最新版本 0.147.10,确实已经解决了,感谢修复。
from lobe-chat.
Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑🤝🧑👫🧑🏿🤝🧑🏻👩🏾🤝👨🏿👬🏿
I just tried the latest version 0.147.10, and it has indeed been solved. Thanks for the fix.
from lobe-chat.
This issue is closed, If you have any questions, you can comment and reply.
此问题已经关闭。如果您有任何问题,可以留言并回复。
from lobe-chat.
Related Issues (20)
- Minimax abab6.5 output problem HOT 3
- 调用ollama里的模型会话时长只有5分钟[Bug] HOT 7
- [Bug] 弹窗每次都弹,不能永久关掉 HOT 9
- [Request] Ollama Functions 的计划 HOT 4
- [Bug] HOT 3
- [Request] HOT 5
- [Bug] 移动端自定义模型配置缺少底部按钮 HOT 2
- [Bug] 设置的tab titile显示有问题。 HOT 4
- [Request] Ollama模型能否设置不默认显示 HOT 6
- [Bug] Default Agent Avatar Broken HOT 1
- [Bug] The "images.domains" configuration is deprecated. Please use "images.remotePatterns" configuration instead HOT 6
- ollama导入的自定义模型无法使用 HOT 1
- [Bug] Ollama service is unavailable - MacOs - Vercel HOT 3
- 以前Ollama变量没有配置默认是不开的,现在没有配置Ollama变量模型也是自动开启了 HOT 3
- [Request] 移动端长按显示菜单 HOT 6
- [Request] ability to disable custom api entry. HOT 1
- UK FIFE ❣️🇬🇧 HOT 2
- [Bug] Ollama service is unavailable HOT 11
- 使用docker部署提示如下错误 HOT 2
- [Bug]设置页面,模型选择,平板显示异常 HOT 4
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from lobe-chat.