GithubHelp home page GithubHelp logo

bclswl0827 / chatgemini Goto Github PK

View Code? Open in Web Editor NEW
904.0 17.0 248.0 18.15 MB

✨ ChatGemini 是一个基于 Google Gemini 的网页客户端,对标 ChatGPT 3.5,操作逻辑同 ChatGPT 3.5 一致,同时支持在聊天中上传图片,应用会自动调用 Gemini-Pro-Vision 模型进行识图。

Home Page: http://ibcl.us/ChatGemini/

License: MIT License

HTML 0.92% TypeScript 86.05% CSS 0.14% JavaScript 9.91% PHP 2.38% Dockerfile 0.25% Shell 0.35%
chatgpt chatgpt3 gemini gemini-api reactjs tailwindcss typescript

chatgemini's People

Contributors

bclswl0827 avatar eltociear avatar muzych avatar roboticsandcloud avatar yuhang1995 avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

chatgemini's Issues

增加图片生成功能

昨天晚上谷歌开放了bard图片生成功能。请问大大有没有计划增加这个功能?

我把端口改成80启动后进不去

我的启动命令docker run -d
--name chatgemini
--restart always
--publish 80:80
--env REACT_APP_GEMINI_API_KEY="xxx"
ghcr.io/bclswl0827/chatgemini
启动成功了,但是80进不去
企业微信截图_20240311174425
企业微信截图_20240311174508

Docker 运行失败

很喜欢这个界面设计。
但是按说明使用 docker 部署无法使用。容器能启动,但网页无法访问。
配置了 REACT_APP_GEMINI_API_KEY 和 REACT_APP_PASSCODE_MD5 两个环境变量(用了引号)。
同样的 KEY,在项目 https://github.com/babaohuang/GeminiProChat 里正常。

如何解决?

When the content generated contains HTML that triggers errors.

When the AI outputs HTML without unquote, it can cause issues with rendering.

For example:

以下是依據您所提供的要求所編寫的使用者對談記錄顯示網頁之HTML、JavaScript及CSS程式碼。請注意,此範例只包含基本結構和功能,若您需要更複雜的設計或額外的功能,可再行修改。

HTML(index.html):
<!DOCTYPE html>
<html lang="en">
<head>
    <meta

Afterwards, the interface displays an error page.

I only modified GetAiChat.tsx to bridge the local LLM API.

Uncaught runtime errors:

ERROR

Failed to execute 'createElement' on 'Document': The tag name provided ('head<div') is not a valid name.
    at createElement (https://development.zonetwelve.io/static/js/bundle.js:40301:38)
    at createInstance (https://development.zonetwelve.io/static/js/bundle.js:41290:24)
    at completeWork (https://development.zonetwelve.io/static/js/bundle.js:50905:32)
    at completeUnitOfWork (https://development.zonetwelve.io/static/js/bundle.js:54664:20)
    at performUnitOfWork (https://development.zonetwelve.io/static/js/bundle.js:54640:9)
    at workLoopSync (https://development.zonetwelve.io/static/js/bundle.js:54554:9)
    at renderRootSync (https://development.zonetwelve.io/static/js/bundle.js:54527:11)
    at recoverFromConcurrentError (https://development.zonetwelve.io/static/js/bundle.js:54019:24)
    at performConcurrentWorkOnRoot (https://development.zonetwelve.io/static/js/bundle.js:53932:26)
    at workLoop (https://development.zonetwelve.io/static/js/bundle.js:71275:38)

If you need the entire output, here's the link: https://gist.github.com/ZoneTwelve/42714f7bdf171b920b742890fadc8ffa.

本地没有代理无法访问gemini

使用docker部署,部署服务端可以访问外网

如果本地没有代理, 浏览器无法访问gemini

返回结果:

[GoogleGenerativeAI Error]: Error fetching from https://generativelanguage.googleapis.com/v1/models/gemini-pro:streamGenerateContent?alt=sse: Failed to fetch

update:
查看了一下请求, 直接页面发起谷歌请求, key直接在浏览器就能看到
建议README写一下, 不要在公网部署

不能直接翻?

用Docker部署在能翻墙的主机中,手机远程使用还要翻墙?

Docker问题:环境变量不带入以及API key会暴露

问题描述:

最新 Docker 没有 403 错误了,但好像环境变量 REACT_APP_GEMINI_API_KEY 和 REACT_APP_PASSCODE_MD5 不起作用了,不会带入。1. 打开没有要求输入 Passcode ,2. 发起一个聊天,则出现错误,API Key 没有问题。“ [GoogleGenerativeAI Error]: Error fetching from https://generativelanguage.googleapis.com/v1/models/gemini-pro:streamGenerateContent?alt=sse: [403 ] Method doesn't allow unregistered callers (callers without established identity). Please use API Key or other form of API consumer identity to call this API.

另外,发现API key会泄露。服务器直接返回的env.json 环境变量(包含API key) 给浏览器。

{
    "REACT_APP_PASSCODE_MD5": "<my-passcode>",
    "REACT_APP_TITLE_SITE": "",
    "REACT_APP_TITLE_HEADER": "",
    "REACT_APP_GEMINI_API_SSE": "",
    "REACT_APP_GEMINI_API_KEY": ""<my-api-key>"",
    "REACT_APP_GEMINI_API_URL": "https://chat.my-domain.com"
}

gemini-1.5-pro出现API错误

已经申请到gemini-1.5-pro使用资格几天了,没想到在今天使用ChatGemini 时,提示错误:[GoogleGenerativeAI Error]: Error fetching from https://generativelanguage.googleapis.com/v1/models/gemini-pro:streamGenerateContent?alt=sse: [403 ] Method doesn't allow unregistered callers (callers without established identity). Please use API Key or other form of API consumer identity to call this API。

到aistudio.google.com去查询,不知道什么时候已将我使用的模型默认改为了gemini-1.5-pro,在aistudio.google.com的API管理页面上看到测试接口地址改为:https://generativelanguage.googleapis.com/v1beta/models/gemini-pro:generateContent?key=YOUR_API_KEY。

本人是通过docker部署的ChatGemini可否通过REACT_APP_GEMINI_API_URL配置项来修改接口地址呢?
同时在此谢谢开发者的无私贡献。

Wanted: internationalization support.

If there are any opportunities for you or your team to implement internationalization, that would be great.

When I have more free time, I'd like to chat and see how I can help.

不会配置反向代理,,,

水平有限。
重装debian10后,按说明,手动部署,把项目配置在美国的vps上,必须开vpn才能和Gemini对话。
试了下 Nginx 反向代理 Gemini API 和 PHP 反向代理 Gemini API
不是报404 就是405 或者 500 ,都没成功,,,
不会配置,,,
能否给个更详细的?

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.