Giter Site home page Giter Site logo

hk-gosuto / chatgpt-next-web-langchain Goto Github PK

View Code? Open in Web Editor NEW

This project forked from chatgptnextweb/chatgpt-next-web

952.0 952.0 353.0 19.8 MB

一键拥有你自己的 ChatGPT 网页服务。 One-Click to deploy your own ChatGPT web UI.(基于 langchain 实现的插件版本 Plugin version implemented based on langchain)

Home Page: https://n3xt.chat

License: MIT License

Shell 0.44% JavaScript 0.59% TypeScript 89.28% Dockerfile 0.17% SCSS 9.47% Rust 0.04%
ai chat-bo chat-gpt gpt langchain langchain-js nextjs openai

chatgpt-next-web-langchain's People

Contributors

actions-user avatar algorithm5838 avatar aprilnea avatar clarencedan avatar cyhhao avatar dean-yzg avatar dependabot[bot] avatar eltociear avatar fengzai6 avatar fred-bf avatar fred913 avatar fredliang44 avatar gan-xing avatar h0llyw00dzz avatar hk-gosuto avatar imldy avatar leedom92 avatar leo4life2 avatar pacmandoh avatar parad1se98 avatar pbrambi avatar quark-zju avatar rubujam avatar rugermccarthy avatar sungaomeng avatar tscherrie avatar xiaotianxt avatar yancode avatar yidadaa avatar yorunning 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

chatgpt-next-web-langchain's Issues

大佬,bing搜索我的以前用的好好的,现在报错了

前几天拉取的Docker版本,刚弄好bing搜索还可以,现在怎么使用报错了。
image
其实昨天就想问大佬这个问题,但自己问的太多了。现在还是无法使用,实在抱歉,如果可以,我可以把bing搜索的key给大佬,是我不会玩吗?

使用DALL.E进行绘画时,出现一些问题

无法激活插件作画
image
作画提示饱和
image

试了很多次,只有一次成功。这个什么原因?看大佬以前解答,想问下大佬如何查看 OpenAI token 是否可以使用 dall-e?

无法调用绘图插件

为了提高交流效率,我们设立了官方 QQ 群和 QQ 频道,如果你在使用或者搭建过程中遇到了任何问题,请先第一时间加群或者频道咨询解决,除非是可以稳定复现的 Bug 或者较为有创意的功能建议,否则请不要随意往 Issue 区发送低质无意义帖子。

点击加入官方群聊

反馈须知

⚠️ 注意:不遵循此模板的任何帖子都会被立即关闭,如果没有提供下方的信息,我们无法定位你的问题。

请在下方中括号内输入 x 来表示你已经知晓相关内容。

  • 我确认已经在 常见问题 中搜索了此次反馈的问题,没有找到解答;
  • 我确认已经在 Issues 列表(包括已经 Close 的)中搜索了此次反馈的问题,没有找到解答。
  • 我确认已经在 Vercel 使用教程 中搜索了此次反馈的问题,没有找到解答。

描述问题
我根据项目中已有的Stable Diffusion插件,写了一个Fooocus插件。但是在聊天中无法调用插件。实际上好像所有的插件都不能使用。
我使用的是本地部署的Vicuna-13b-chat模型。

截图
AI Illustrator

一些必要的信息

  • 系统:Windows 10
  • 浏览器: Chrome
  • 版本:v2.9.9
  • 部署方式:Docker

支持本地文生图[Feature]

为了提高交流效率,我们设立了官方 QQ 群和 QQ 频道,如果你在使用或者搭建过程中遇到了任何问题,请先第一时间加群或者频道咨询解决,除非是可以稳定复现的 Bug 或者较为有创意的功能建议,否则请不要随意往 Issue 区发送低质无意义帖子。

点击加入官方群聊

这个功能与现有的问题有关吗?
如果有关,请在此列出链接或者描述问题。

你想要什么功能或者有什么建议?
尽管告诉我们。
考虑支持本地的SDXL等文生图服务吗
有没有可以参考的同类竞品?
可以给出参考产品的链接或者截图。

其他信息
可以说说你的其他考虑。

Failed to get the VQD for query "X"

描述问题
启用联网查找后出现 Failed to get the VQD for query "啊对对对对" 错误
Snazzah/duck-duck-scrape/issues/119
有过相关BUG报告,但似乎已经修复,我检查过package.json 确实也是 2.2.4以上,但仍存在该问题。

如何复现
启用联网查找

截图

chat-chat-1  | [Tools]  Error: Failed to get the VQD for query "jobs是谁?".
chat-chat-1  |     at getVQD (/app/.next/server/chunks/2180.js:1159:15)
chat-chat-1  |     at process.processTicksAndRejections (node:internal/process/task_queues:95:5)
chat-chat-1  |     at async search (/app/.next/server/chunks/2180.js:325:21)
chat-chat-1  |     at async handle (/app/.next/server/app/api/tools/ddg/route.js:350:31)
chat-chat-1  |     at async /app/.next/server/chunks/2180.js:16459:37

一些必要的信息

  • 版本:main分支
  • 部署方式:docker

[Bug] TypeError: Cannot read properties of undefined (reading 'message')] 'writer error'

描述问题
使用讯飞星火认知免费api,对接one-api,在chatgpt-next-web-LangChain中使用。
image
回复一直都带有如下错误。

{
  "error": true,
  "message": "[object Object]"
}

在原版chatgpt-next-web不会出现这个问题。

如何复现
1.填写好配置
image
2.选择模型
image
3.使用出错
image

预期行为
没有如下错误。

{
  "error": true,
  "message": "[object Object]"
}

相关截图
在one-api使用这个项目,one-api会出现下面错误。
image
image

Deployment
Docker

Desktop (please complete the following information):

  • OS: Windows
  • Browser Microsoft Edge
  • Version 版本 116.0.1938.76 (正式版本) (64 位)

Smartphone (please complete the following information):
不会在手机使用。

Additional Logs

[Bug] 开启插件后,搜索时出错

不开启插件,正常输出
1696694459161

开启插件后,无法搜索网络上的内容
1696694502428

注:配置了SERPAPI_API_KEY
1696694746176

一些必要的信息

  • 系统:windows 11
  • 浏览器: edge
  • 版本: 2.9.7
  • 部署方式:vercel部署

考虑加入bing search api作为搜索引擎吗,感觉谷歌的效果并不理想[Feature]

为了提高交流效率,我们设立了官方 QQ 群和 QQ 频道,如果你在使用或者搭建过程中遇到了任何问题,请先第一时间加群或者频道咨询解决,除非是可以稳定复现的 Bug 或者较为有创意的功能建议,否则请不要随意往 Issue 区发送低质无意义帖子。

点击加入官方群聊

这个功能与现有的问题有关吗?
如果有关,请在此列出链接或者描述问题。

你想要什么功能或者有什么建议?
尽管告诉我们。

有没有可以参考的同类竞品?
可以给出参考产品的链接或者截图。

其他信息
可以说说你的其他考虑。

有什么免费的API接口?

有什么免费的API接口可以推介给我,又可以调用插件?因为OpenAI的API很贵,我又没有帐号

请问如何触发搜索功能?

为了提高交流效率,我们设立了官方 QQ 群和 QQ 频道,如果你在使用或者搭建过程中遇到了任何问题,请先第一时间加群或者频道咨询解决,除非是可以稳定复现的 Bug 或者较为有创意的功能建议,否则请不要随意往 Issue 区发送低质无意义帖子。

点击加入官方群聊

反馈须知

⚠️ 注意:不遵循此模板的任何帖子都会被立即关闭,如果没有提供下方的信息,我们无法定位你的问题。

请在下方中括号内输入 x 来表示你已经知晓相关内容。

  • 我确认已经在 常见问题 中搜索了此次反馈的问题,没有找到解答;
  • 我确认已经在 Issues 列表(包括已经 Close 的)中搜索了此次反馈的问题,没有找到解答。
  • 我确认已经在 Vercel 使用教程 中搜索了此次反馈的问题,没有找到解答。

描述问题
感觉搜索功能时好时坏的,有时候触发了有时候又没有触发

如何复现
连续对话

截图
image

一些必要的信息

  • 系统:windows 11
  • 浏览器:chrome
  • 版本:V2.9.6
  • 部署方式:本地部署

大佬,我想作画插件对接one-api

如果我使用此命令创建容器

docker run -d -p 8241:3000 \
	--name chatgpt1 \
	--restart always \
	-e PROXY_URL="http://192.168.1.4:7890" \
	-e BASE_URL="http://192.168.1.4:9150" \
	-e BING_SEARCH_API_KEY="90b3adf5" \
	-e R2_ACCOUNT_ID="1a245e" \
	-e R2_ACCESS_KEY_ID="506df65" \
	-e R2_SECRET_ACCESS_KEY="c773c9815c3486b5" \
	-e R2_BUCKET="gpt" \
	gosuto/chatgpt-next-web-langchain

修改 BASE_URL 为 one-api 地址。那么,one-api 日志会提示 当前分组 svip 下对于模型 dall-e 无可用渠道,在 one-api 如何怎么添加支持画图插件。
image
如果取消掉修改 BASE_URL 为 one-api 地址。那么,会正常作画。

docker run -d -p 8241:3000 \
	--name chatgpt1 \
	--restart always \
	-e PROXY_URL="http://192.168.1.4:7890" \
	-e BING_SEARCH_API_KEY="90b3adf5" \
	-e R2_ACCOUNT_ID="1a245e" \
	-e R2_ACCESS_KEY_ID="506df65" \
	-e R2_SECRET_ACCESS_KEY="c773c9815c3486b5" \
	-e R2_BUCKET="gpt" \
	gosuto/chatgpt-next-web-langchain

最后想问下,作画插件需要开代理吗?

Image not displaying after generation [Bug]

Describe the bug
Dall-E Generated Image not showing in the app.
To Reproduce
Ask to generate any Image, plugin gets activated and it replies with an image , but the image is not showing up in the app.

Expected behavior
Images should be visible after generation.

Screenshots
image

Deployment

  • Vercel

Additional Logs
Add any logs about the problem here.

On Inspect element in browser it shows following error in console:

https://chatgptweb.vercel.com/api/file/1695043350537.png 401 (Unauthorized)
Image (async)
ag @ bce60fc1-76a57db123ee8dbb.js:9
ay @ bce60fc1-76a57db123ee8dbb.js:9
aT @ bce60fc1-76a57db123ee8dbb.js:9
ay @ bce60fc1-76a57db123ee8dbb.js:9
aT @ bce60fc1-76a57db123ee8dbb.js:9
ay @ bce60fc1-76a57db123ee8dbb.js:9
aT @ bce60fc1-76a57db123ee8dbb.js:9
ay @ bce60fc1-76a57db123ee8dbb.js:9
......

aT @ bce60fc1-76a57db123ee8dbb.js:9
  ay @
  (anonymous) @
  oO @
  nG @
  nJ @
  (anonymous) @

[Bug] Cannot read properties of undefined (reading 'delta')

实在是不好意思,一直打扰大佬了。这个问题属实是我个人使用出现的问题,不在大佬解决范围内,如果有打扰冒犯大佬的地方,请接受我的道歉,我不是有意的。
我使用 https://github.com/haibbo/cf-openai-azure-proxy 开源项目来把 Azure OpenAI 转为 ChatGPT 的格式,在 one-api 对接,然后再本项目使用,会出错,如下。
image
但在原版 Yidadaa/ ChatGPT-Next-Web 使用正常,这个问题该怎么解决?
image
我真的不是有意打扰大佬您的,如果大佬有什么需要,我可以提供 Azure OpenAI 所有参数。

gosuto/ddg-api

docker run -p 8000:8000 gosuto/ddg-api
这个docker镜像好像没开放,需要登录才能下载
docker: Error response from daemon: pull access denied for gosuto/ddg-api, repository does not exist or may require 'docker login': denied: requested access to the resource is denied. See 'docker run --help'.

[Feature] Use Fooocus-API To Replace Stable Diffusion

Describe the solution you'd like
Fooocus(lllyasviel/Fooocus#117) 是一个新兴的项目,目标是基于Stable Diffusion打造一个类似MidJourney的图片生成应用。它显著降低了使用Stable Diffusion的门槛,又能获得非常好的图片输出结果。Fooocus API (https://github.com/konieshadow/Fooocus-API) 是一个基于FastAPI的Fooocus Restful API wrapper. 相比SD Webui暴露的API接口,这个项目提供接口更丰富,更简洁。

建议用Fooocus-API 取代Stable Diffusion API。

想问个新手问题

说说我的情况:原项目那边过来的,看到有插件就重新部署的这个。但是没有很明确的教程用法,已经跟着文档有的地方能申请的都申请放进环境变量,然后还是只能用普通对话,无法触发插件。

然后又测试琢磨好久用不了,我就分析原因:

我一开始以为这个是先通过gpt分析语义然后进一步根据关键词自动执行插件,毕竟是langchain嘛应该有分析能力,一直不行跟着文档一样一起问也不行,我才想:这个是不是用的是官方接口,对接的是官方的plus账号才能用的插件,就是需要api4的接口?而且我想着dalle官网是只有4才有权限能用,这个项目填了cf就能用连api都不需要,应该不是因为dalle是免费公开接口,而是通过key来申请对接的,cf只是转存资源反代链接。就更证实了这个想法。

不知道是不是这样,而且我没国外信用卡,用的是搭建的对话转api模拟api,正常聊天可以和3.5一样,如果是根据返回的语义实现的,那么应该没问题才对。可是看到文档说除了两个模型其他又都支持插件我又奇怪了,这么说就是3.5的api也能用这个插件,官网不是不支持吗。那就是说要不api有额外的使用接口,要不就是我这个模拟的api实际上接口还是不全。不过我没有办法弄到key测试了。只能猜想论证,又和上面的想法冲突了,如果3.5key能用dalle,那为什么还要plus会员才能用。又死循环了。

我看issue结果好像都是资深使用的大佬问题,不好意思开issue打扰,怕太低级了。大家都会用就我不会是不是哪里遗漏了。然后自己又花了两天把项目看来看去。重新搞(除了搜索api看了要付费申请和收不到验证码以外想着vercel会反代就写的谷歌还有那个sd画图的项目全英文看不太懂没搭建以外其他都弄了)。看着看着又感觉和官方api没关系,搜索要搜索引擎key,画图要搭建sd,都不是依赖openai的。又绕回去感觉像是根据语义自动使用插件。

实在不知道咋回事了,才想着发一个issue吧,如果真的很没意义就直接关了吧。我也不是不自己花时间找办法就伸手党问问题,实在是不玩这个圈子有点迷糊,项目大部分都是指向langchain链接我不玩人工智能有点看不懂。如果有人能指点一下用法万分感激。如果觉得我这个问题很棘手或者要花比较多的时间,那就算了和我说一下我就用回原项目好了。

如果有打扰到大家实在抱歉。

[Feature] 0613版本的限制建议放开

目前除非显式指定 gpt-4-0314和gpt-3.5-turbo-0301版本
默认的 gpt-4 和 gpt-3.5-turbo 应该都是 0613 版本了,都支持函数调用,没有必要再限制到 0613 了

[Bug] wikipedia-api 查询时报错

Describe the bug
wikipedia-api 进行递归查询的时候,如果层数过深(在本例中,超过 4 层),就会报错:

{
  "error": true,
  "message": "[object Object]"
}

To Reproduce

  1. 使用 Azure GPT4 2023-08-01-preview(OpenAI 官方的 GPT4 应该也一样)作为 GPT4
  2. 询问:Who is the 100th prime minister of japan

Expected behavior
回复:Fumio Kishida(岸田文雄)

Screenshots
image

联网访问网页对外API提供内容

作者你好, 你增加的浏览网页的这插件非常棒,还有联网搜索。
请问能实现 目前的项目提供对外服务API吗? 就是比如,提供个http://localhost:3000/api 我可以在外部post或者get 提交网页或者搜索内容过来,gpt分析和获取内容之后返回给我。

之所以有这想法是因为 好像无法实现非插件的方式访问网页或者搜索。

有尝试过爬取网页获取内容进行分析或者搜索,但是有的网址有反爬机制。但是 插件形式,基本上没有。

本机Docker部署,如何让它走代理

实在抱歉大佬,百度搜索有点不好用,想换回bing搜索,有时网络错误。我在想是不是one-api的问题,导致bing搜索不能用。现在想去掉one-api的base_url,换回openai官方的接口,但需要走代理。我使用下面命令创建容器。

docker run -d -p 8261:3000 \
	--name chatgpt \
	--restart always \
	-e https_proxy="http://192.168.1.4:7890" \
	-e CODE="eRelV54B" \
	-e BING_SEARCH_API_KEY="21ac9b" \
	-e R2_ACCOUNT_ID="1a2fb43cb45e" \
	-e R2_ACCESS_KEY_ID="dfd955" \
	-e R2_SECRET_ACCESS_KEY="c4d5" \
	-e R2_BUCKET="gpt" \
	gosuto/chatgpt-next-web-langchain:1.0.4

之后在设置里的API_Key填入OpenAI的key,不回复我。
image
image

[Bug] 使用nova项目的api时出现的问题

为了提高交流效率,我们设立了官方 QQ 群和 QQ 频道,如果你在使用或者搭建过程中遇到了任何问题,请先第一时间加群或者频道咨询解决,除非是可以稳定复现的 Bug 或者较为有创意的功能建议,否则请不要随意往 Issue 区发送低质无意义帖子。

点击加入官方群聊

反馈须知

⚠️ 注意:不遵循此模板的任何帖子都会被立即关闭,如果没有提供下方的信息,我们无法定位你的问题。

请在下方中括号内输入 x 来表示你已经知晓相关内容。

  • [ x] 我确认已经在 常见问题 中搜索了此次反馈的问题,没有找到解答;
  • [ x] 我确认已经在 Issues 列表(包括已经 Close 的)中搜索了此次反馈的问题,没有找到解答。
  • [x ] 我确认已经在 Vercel 使用教程 中搜索了此次反馈的问题,没有找到解答。

描述问题
请在此描述你遇到了什么问题。
使用nova ai项目的API,会出现两个问题,其一是搜索插件无法调用,会一直转圈,然后直到返回一个空数值,但是页面上会显示正在调用插件,第2个问题,就是这个项目的API在其他的项目中是可以正常使用的,但在本项目中使用会出现以下错误代码

{
  "error": true,
  "message": "<!DOCTYPE html>\n<!--[if lt IE 7]> <html class=\"no-js ie6 oldie\" lang=\"en-US\"> <![endif]-->\n<!--[if IE 7]>    <html class=\"no-js ie7 oldie\" lang=\"en-US\"> <![endif]-->\n<!--[if IE 8]>    <html class=\"no-js ie8 oldie\" lang=\"en-US\"> <![endif]-->\n<!--[if gt IE 8]><!--> <html class=\"no-js\" lang=\"en-US\"> <!--<![endif]-->\n<head>\n<title>Attention Required! | Cloudflare</title>\n<meta charset=\"UTF-8\" />\n<meta http-equiv=\"Content-Type\" content=\"text/html; charset=UTF-8\" />\n<meta http-equiv=\"X-UA-Compatible\" content=\"IE=Edge\" />\n<meta name=\"robots\" content=\"noindex, nofollow\" />\n<meta name=\"viewport\" content=\"width=device-width,initial-scale=1\" />\n<link rel=\"stylesheet\" id=\"cf_styles-css\" href=\"/cdn-cgi/styles/cf.errors.css\" />\n<!--[if lt IE 9]><link rel=\"stylesheet\" id='cf_styles-ie-css' href=\"/cdn-cgi/styles/cf.errors.ie.css\" /><![endif]-->\n<style>body{margin:0;padding:0}</style>\n\n\n<!--[if gte IE 10]><!-->\n<script>\n  if (!navigator.cookieEnabled) {\n    window.addEventListener('DOMContentLoaded', function () {\n      var cookieEl = document.getElementById('cookie-alert');\n      cookieEl.style.display = 'block';\n    })\n  }\n</script>\n<!--<![endif]-->\n\n\n</head>\n<body>\n  <div id=\"cf-wrapper\">\n    <div class=\"cf-alert cf-alert-error cf-cookie-error\" id=\"cookie-alert\" data-translate=\"enable_cookies\">Please enable cookies.</div>\n    <div id=\"cf-error-details\" class=\"cf-error-details-wrapper\">\n      <div class=\"cf-wrapper cf-header cf-error-overview\">\n        <h1 data-translate=\"block_headline\">Sorry, you have been blocked</h1>\n        <h2 class=\"cf-subheadline\"><span data-translate=\"unable_to_access\">You are unable to access</span> nova-oss.com</h2>\n      </div><!-- /.header -->\n\n      <div class=\"cf-section cf-highlight\">\n        <div class=\"cf-wrapper\">\n          <div class=\"cf-screenshot-container cf-screenshot-full\">\n            \n              <span class=\"cf-no-screenshot error\"></span>\n            \n          </div>\n        </div>\n      </div><!-- /.captcha-container -->\n\n      <div class=\"cf-section cf-wrapper\">\n        <div class=\"cf-columns two\">\n          <div class=\"cf-column\">\n            <h2 data-translate=\"blocked_why_headline\">Why have I been blocked?</h2>\n\n            <p data-translate=\"blocked_why_detail\">This website is using a security service to protect itself from online attacks. The action you just performed triggered the security solution. There are several actions that could trigger this block including submitting a certain word or phrase, a SQL command or malformed data.</p>\n          </div>\n\n          <div class=\"cf-column\">\n            <h2 data-translate=\"blocked_resolve_headline\">What can I do to resolve this?</h2>\n\n            <p data-translate=\"blocked_resolve_detail\">You can email the site owner to let them know you were blocked. Please include what you were doing when this page came up and the Cloudflare Ray ID found at the bottom of this page.</p>\n          </div>\n        </div>\n      </div><!-- /.section -->\n\n      <div class=\"cf-error-footer cf-wrapper w-240 lg:w-full py-10 sm:py-4 sm:px-8 mx-auto text-center sm:text-left border-solid border-0 border-t border-gray-300\">\n  <p class=\"text-13\">\n    <span class=\"cf-footer-item sm:block sm:mb-1\">Cloudflare Ray ID: <strong class=\"font-semibold\">81f27b1403e2e656</strong></span>\n    <span class=\"cf-footer-separator sm:hidden\">&bull;</span>\n    <span id=\"cf-footer-item-ip\" class=\"cf-footer-item hidden sm:block sm:mb-1\">\n      Your IP:\n      <button type=\"button\" id=\"cf-footer-ip-reveal\" class=\"cf-footer-ip-reveal-btn\">Click to reveal</button>\n      <span class=\"hidden\" id=\"cf-footer-ip\">2a06:98c0:3600::103</span>\n      <span class=\"cf-footer-separator sm:hidden\">&bull;</span>\n    </span>\n    <span class=\"cf-footer-item sm:block sm:mb-1\"><span>Performance &amp; security by</span> <a rel=\"noopener noreferrer\" href=\"https://www.cloudflare.com/5xx-error-landing\" id=\"brand_link\" target=\"_blank\">Cloudflare</a></span>\n    \n  </p>\n  <script>(function(){function d(){var b=a.getElementById(\"cf-footer-item-ip\"),c=a.getElementById(\"cf-footer-ip-reveal\");b&&\"classList\"in b&&(b.classList.remove(\"hidden\"),c.addEventListener(\"click\",function(){c.classList.add(\"hidden\");a.getElementById(\"cf-footer-ip\").classList.remove(\"hidden\")}))}var a=document;document.addEventListener&&a.addEventListener(\"DOMContentLoaded\",d)})();</script>\n</div><!-- /.error-footer -->\n\n\n    </div><!-- /#cf-error-details -->\n  </div><!-- /#cf-wrapper -->\n\n  <script>\n  window._cf_translation = {};\n  \n  \n</script>\n\n<script defer src=\"https://static.cloudflareinsights.com/beacon.min.js/v84a3a4012de94ce1a686ba8c167c359c1696973893317\" integrity=\"sha512-euoFGowhlaLqXsPWQ48qSkBSCFs3DPRyiwVu3FjR96cMPx+Fr+gpWRhIafcHwqwCqWS42RZhIudOvEI+Ckf6MA==\" data-cf-beacon='{\"rayId\":\"81f27b1403e2e656\",\"version\":\"2023.10.0\",\"r\":1,\"token\":\"a98e01729cc142af98f6a417d0afb2a8\",\"b\":1}' crossorigin=\"anonymous\"></script>\n</body>\n</html>\n"
}

如何复现
添入nova项目的API和base url,然后进行对话

截图
请在此提供控制台截图、屏幕截图或者服务端的 log 截图。

一些必要的信息

  • 系统:[Android13]
  • 浏览器: [雨见(火狐内核)]
  • 版本: [最新源码]
  • 部署方式:[vercel]

[Bug] 不支持Base url

已经修改了app/api/common.ts,还是不行
env也是不能使用
会导向官方
可以查余额

[Bug] 发现个问题

描述问题
单独部署docker的时候没有问题,一切正常
但是部署cloudflare pages出问题了

如何复现
你部署一次pages就可以看到问题了
部署成cloudflare pages的时候发现问题:
1.首先设置next.config.mjs中API_URL不起作用
''' const apiUrl = process.env.API_URL;
if (apiUrl) {
console.log("[Next] using api url ", apiUrl);
ret.push({
source: "/api/:path*",
destination: ${apiUrl}/:path*,
});
}'''
需要单独再填写一次API_URL和key在设置中
2.部署在CF中,搜索功能返回404
截图
请在此提供控制台截图、屏幕截图或者服务端的 log 截图。
不启用搜索功能的时候,可以正常交互,而启用功能后,发起会话返回内容如下

<title>404 Not Found</title>

404 Not Found


nginx 看了下是https://cf的地址/api/langchain/tool/agent 这个页面不存在 **一些必要的信息** - 系统:[windows 10] - 浏览器: [chrome] - 版本: [2.9.3] - 部署方式:[cloudflare page next]

[Bug] 无法回复问题

在serpapi.com获取了Private API Key,配置了SERPAPI_API_KEY环境变量。
但是输入问题不能得到回复,一直显示加载中,切换模型不使用gpt-3.5-turbo-0613后就可以正常回复,但不能联网查询了。
ct

[无法搜索]

曲线的解决了

#25 (comment)


# 原因如下

### 仅 openapi 官方原版接口可用这个搜索。

#19 (comment)


ddg api 搭建成功的。

ddg api部分

访问:http://192.168.10.20:8081/search?q=啊对对对是什么梗&max_results=3
正常json 格式的返回结果。

ChatGPT-Next-Web-LangChain 部分

git reset --hard 933d4c3

https://github.com/Hk-Gosuto/ChatGPT-Next-Web-LangChain/tree/v2.9.6 版本的。

docke 构建镜像
镜像启动参数
-e WEB_SEARCH_BASE_URL="http://192.168.10.20:8081"

容器启动后。

和没接入联网插件一样。

## 来自你的消息:
搜索2023年马斯克

## 来自 ChatGPT 的消息:
很抱歉,我无法进行实时搜索或提供最新的信息,因为我的知识截止日期是2021年9月,而我无法浏览互联网。如果您想了解关于2023年的埃隆·马斯克(Elon Musk)的信息,我建议您访问新闻网站、社交媒体或搜索引擎,以获取最新的新闻和事件。马斯克是特斯拉和SpaceX的创始人,他在科技和太空探索领域有许多活动,因此可以在各种新闻来源中找到相关信息。

其他

  • 第一次用最新版本构建的镜像,启动后无法用搜索。 然后改用 tag:v2.9.6 的仍然用不了。

[Feature] How to easily add other open source models like Falcon or LLaMa 2 as one of the options.

Is your feature request related to a problem? Please describe.
Yes, OpenAI will be too costly for a generic use case. Also, privacy takes a hit.

Describe the solution you'd like
Either an economical API for Falcon180B or LLaMa2 70B integrated with this app.

Describe alternatives you've considered
An API for Falcon180B or LLaMa2 70B or self-hosted on some cloud.
I have startup credits on AWS and Azure. What will be the best way for me to integrate LLaMa 2 or Falcon to ChatGPT Next as one of the options with GPT 3.5-Turbo and GPT-4?

Additional context
Please suggest step-by-step instructions to do this as I am quite a newbie in this.

发现大佬支持Azure OpenAI了,早上使用好好的,现在使用报错了

今天早上打开大佬的项目,发现更新支持 Azure OpenAI,好激动,把我沸腾的。早上弄好可以回复,但现在一直报错,不知道怎么解决,特来求教大佬。

<!DOCTYPE html><html><head><meta charSet="utf-8"/><meta name="viewport" content="width=device-width"/><title>404: This page could not be found</title><meta name="next-head-count" content="3"/><noscript data-n-css=""></noscript><script defer="" nomodule="" src="/_next/static/chunks/polyfills-78c92fac7aa8fdd8.js"></script><script src="/_next/static/chunks/webpack-bdb91cd697c9ddaf.js" defer=""></script><script src="/_next/static/chunks/framework-964c2d6016b0d731.js" defer=""></script><script src="/_next/static/chunks/main-930a44a9a7424b5d.js" defer=""></script><script src="/_next/static/chunks/pages/_app-c4dd4288cf6c1321.js" defer=""></script><script src="/_next/static/chunks/pages/_error-c4f1d7e8888c6b95.js" defer=""></script><script src="/_next/static/9S_s9H1z6DnbbJlNgDDY0/_buildManifest.js" defer=""></script><script src="/_next/static/9S_s9H1z6DnbbJlNgDDY0/_ssgManifest.js" defer=""></script></head><body><div id="__next"><div style="font-family:system-ui,&quot;Segoe UI&quot;,Roboto,Helvetica,Arial,sans-serif,&quot;Apple Color Emoji&quot;,&quot;Segoe UI Emoji&quot;;height:100vh;text-align:center;display:flex;flex-direction:column;align-items:center;justify-content:center"><div style="line-height:48px"><style>body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}</style><h1 class="next-error-h1" style="display:inline-block;margin:0 20px 0 0;padding-right:23px;font-size:24px;font-weight:500;vertical-align:top">404</h1><div style="display:inline-block"><h2 style="font-size:14px;font-weight:400;line-height:28px">This page could not be found<!-- -->.</h2></div></div></div></div><script id="__NEXT_DATA__" type="application/json">{"props":{"pageProps":{"statusCode":404}},"page":"/_error","query":{},"buildId":"9S_s9H1z6DnbbJlNgDDY0","nextExport":true,"isFallback":false,"gip":true,"scriptLoader":[]}</script></body></html>

这个怎么解决,需要我从头在来吗?

[Feature] 搜索代理与原版使用的代理分开

这个功能与现有的问题有关吗?
没有。

你想要什么功能或者有什么建议?
作者大大能把搜索代理分开吗?我对接了one-api,base_url是内网one-api地址,所以在使用ai模型时不需要代理。
但是,使用搜索需要代理,所以大佬能把搜索代理与原版使用的代理分开吗?
有什么冒犯大佬的地方,还请见谅。本人小白一枚,不懂技术,纯属根据自己的需求提问,感谢大佬。

有没有可以参考的同类竞品?
无。

其他信息
暂无。

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.