Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Bug] 开启Markdown渲染,一次性粘贴大量文本时,页面失去响应 #5682

Open
MurphyLo opened this issue Oct 17, 2024 · 7 comments
Labels
bug Something isn't working maybe

Comments

@MurphyLo
Copy link

📦 部署方式

官方安装包

📌 软件版本

2.15.5

💻 系统环境

macOS

📌 系统版本

🌐 浏览器

Edge

📌 浏览器版本

129

🐛 问题描述

开启 预览气泡 功能时,一次性向聊天输入太多文本导致页面失去响应。

📷 复现步骤

将电影 Her 的脚本 复制并一次性粘贴至聊天窗口。

🚦 期望结果

当文本数量超出一定阈值时,可以是停止更新渲染的 Markdown 内容,或不再渲染。

📝 补充信息

也许可以对这个判断加一个字符上限的条件?

代码文件

@MurphyLo MurphyLo added the bug Something isn't working label Oct 17, 2024
@Issues-translate-bot
Copy link

Bot detected the issue body's language is not English, translate it automatically.


Title: [Bug] Enable Markdown rendering, one-time Page becomes unresponsive when pasting large amounts of text

📦 Deployment method

Official installation package

📌 Software version

2.15.5

💻 System environment

macOS

📌 System version

🌐 Browser

Edge

📌 Browser version

129

🐛 Problem description

When the Preview Bubble feature is turned on, entering too much text into the chat at once causes the page to become unresponsive.

📷 Steps to reproduce

Copy and paste the script from the movie Her into the chat window in one go.

🚦 Expected results

When the amount of text exceeds a certain threshold, you can stop updating the rendered Markdown content, or no longer render it.

📝 Supplementary information

Maybe you can add a character upper limit condition to this judgment?

Code file

@lloydzhou
Copy link
Contributor

如果是太大的文本内容,可以放文件里面。然后结合plugin获取文件内容,与大模型进行交互。

@Issues-translate-bot
Copy link

Bot detected the issue body's language is not English, translate it automatically.


If the text content is too large, it can be placed in a file. Then combine the plugin to obtain the file content and interact with the large model.

@kitaev-chen
Copy link

如果是太大的文本内容,可以放文件里面。然后结合plugin获取文件内容,与大模型进行交互。

请问下哪个plugin可以获取文件内容?

@Issues-translate-bot
Copy link

Bot detected the issue body's language is not English, translate it automatically.


If the text content is too large, you can put it in the file. Then combine it with the plugin to obtain the file content and interact with the large model.

Which plugin can get the file content?

@MurphyLo
Copy link
Author

如果是太大的文本内容,可以放文件里面。然后结合plugin获取文件内容,与大模型进行交互。

个人觉得配置三方插件或自行搓一个插件工作流还是比较麻烦的,因为很多时候都需要结合实际参考的文本内容对 prompt 做修改,一套固定的插件工作流相对来说不那么灵活,也不太新手友好。

claude.ai 的网页 UI 很好的一点是能够自动将粘贴输入或模型输出的大量文本自动归结为一个文本块,避免了回顾聊天内容时花大量时间在翻找内容上。nextweb 的 代码折叠 功能也一定程度上实现了这一特性。所以最近个人在大量文本或代码分析时会偏好使用 nextchat,遂有了这个 issue。

仅供讨论,交流个人感受。

@Issues-translate-bot
Copy link

Bot detected the issue body's language is not English, translate it automatically.


If the text content is too large, you can put it in the file. Then combine it with the plugin to obtain the file content and interact with the large model.

Personally, I think it is quite troublesome to configure third-party plug-ins or create a plug-in workflow by yourself, because many times you need to modify the prompt based on the actual reference text content. A fixed set of plug-in workflows is relatively inflexible and inconvenient. Newbie friendly.

A nice thing about claude.ai's web UI is that it can automatically boil large amounts of text pasted into input or model output into a text block, eliminating the need to spend a lot of time rummaging through content when reviewing chat content. nextweb's code folding function also implements this feature to a certain extent. So recently, I prefer to use nextchat when analyzing a large amount of text or code, so I got this issue.

For discussion only and exchange of personal feelings.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working maybe
Projects
None yet
Development

No branches or pull requests

4 participants