Giter VIP home page Giter VIP logo

lobehub / chat-plugin-web-crawler Goto Github PK

View Code? Open in Web Editor NEW
47.0 2.0 16.0 184 KB

🧩 / 🕸 WebsiteCrawler - This plugin automatically crawls the main content of a specified URL webpage and uses it as context input.

Home Page: http://web-crawler.chat-plugin.lobehub.com

License: MIT License

JavaScript 0.06% Shell 0.03% TypeScript 0.63% HTML 99.29%
lobe-chat-plugin function-calling lobe-chat chatgpt openai ai crawler

chat-plugin-web-crawler's Issues

[Bug] 页面内容太长会报错

💻 系统环境 | Operating System

macOS

🌐 浏览器 | Browser

Chrome

🐛 问题描述 | Bug Description

希望可以根据当前剩余token来限制读取内容的长度

🚦 期望结果 | Expected Behavior

No response

📷 复现步骤 | Recurrence Steps

image

📝 补充信息 | Additional Information

No response

只消耗token,没有任何返回[Bug]

💻 系统环境 | Operating System

macOS

🌐 浏览器 | Browser

Chrome

🐛 问题描述 | Bug Description

调用插件,然后只是消耗大量的token,没有任何返回信息,或者无效返回信息

🚦 期望结果 | Expected Behavior

No response

📷 复现步骤 | Recurrence Steps

提问“搜索eccDNA的最新发现”,调用gpt-4-32k模型,输入28981提示词,消耗3$额度,返回为“无法提供“。
提问”搜索GeminiPro的最新消息“,调用gpt-4-1106-preview, 输入29052和29498提示词,消耗2$额度,返回为空

📝 补充信息 | Additional Information

No response

[Request] 支持非 vercel , 非 BROWSERLESS 的实现方式

🥰 需求描述 | Feature Description

当前商店里提供的插件, 非常好用, 可以解决很多问题, 但是有些时候, 需要抓非公开的, 内网里的文件, 此时本插件就派不上用场, 希望能提供方式, 把插件部署至内网, 让他可以抓取内网的内容.

另外实现方式中, 是调用了 browserless 的 token, 这样肯定是能适配很多的 SPA 应用, 但同时也让部署变得复杂, 希望能提供不使用 browserless 的实现.

🧐 解决方案 | Proposed Solution

提供 docker 等通用部署方案, 提供非 broserless 的实现

📝 补充信息 | Additional Information

我自己尝试了下自己做一个, LeoQuote/lobe-webcrawer-self-host#1 但老是报请求失败.

本地开发的时候, 也是非要先过服务端的网关, 非常的不方便, 难道我必须要 lobe 和插件都在本地运行才可正常进行调试?

[Bug] 在使用gemini1.5 pro的情况下无法使用

💻 系统环境 | Operating System

Windows

🌐 浏览器 | Browser

Chrome

🐛 问题描述 | Bug Description

在使用gemini1.5 pro的情况下无法使用

🚦 期望结果 | Expected Behavior

No response

📷 复现步骤 | Recurrence Steps

No response

📝 补充信息 | Additional Information

No response

[Bug] Does not work with Dolphin-Mixtral

💻 系统环境 | Operating System

Windows

🌐 浏览器 | Browser

Chrome

🐛 问题描述 | Bug Description

With dolphin-mixtral, I contend that it's not able to use the plugin and crawl a web page.

🚦 期望结果 | Expected Behavior

No response

📷 复现步骤 | Recurrence Steps

No response

📝 补充信息 | Additional Information

No response

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo 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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.