Comments (22)
Please follow the issue template to update title and description of your issue.
from chatgpt-next-web.
Bot detected the issue body's language is not English, translate it automatically.
Title: [Add related instructions for Alibaba Cloud Tongyi Qianwen (qwen)]
🥰 Description of requirements
It seems that in the latest (v2.13.0) release, support for the Alibaba Cloud model API has been added, but I am not sure what the correct usage method is, specifically:
What should be filled in for the interface address? (or keep default?)
Is the interface key created from Alibaba Cloud Bailian?
Is qwen-long supported? qwen-long supports very long contexts and is able to parse uploaded documents
🧐 Solution
Add relevant instructions for use
📝 Supplementary information
No response
from chatgpt-next-web.
阿里渠道默认的接口地址是: ALIBABA_BASE_URL = "https://dashscope.aliyuncs.com/api/"
到密钥生成的地方看看是不是对应这个地址,如果是的话保持默认就行
from chatgpt-next-web.
Bot detected the issue body's language is not English, translate it automatically.
The default interface address of Ali channel is: ALIBABA_BASE_URL = "https://dashscope.aliyuncs.com/api/"
Go to the place where the key is generated to see if it corresponds to this address. If so, just keep the default.
from chatgpt-next-web.
阿里渠道默认的接口地址是:
ALIBABA_BASE_URL = "https://dashscope.aliyuncs.com/api/"
到密钥生成的地方看看是不是对应这个地址,如果是的话保持默认就行
感谢您的回复,我尝试了您提到的地址以及阿里云百炼平台使用curl方法访问模型的地址https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation,并填入了阿里云百炼平台生成的key,选择了正确的模型,仍旧没有成功
from chatgpt-next-web.
Bot detected the issue body's language is not English, translate it automatically.
The default interface address of Ali channel is:
ALIBABA_BASE_URL = "https://dashscope.aliyuncs.com/api/"
Go to the place where the key is generated to see if it corresponds to this address. If so, just keep the default.
Thanks for your reply, I tried the address you mentioned and the address where Alibaba Cloud Bailian platform uses curl method to access the model https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation, And filled in the key generated by Alibaba Cloud Bailian platform and selected the correct model, but still no success
from chatgpt-next-web.
我进一步尝试了官方文档中提到的OpenAI Chat接口兼容中的两个url,同样没有成功,错误信息同上。
from chatgpt-next-web.
如果是从阿里官方申请的,直接填写申请的密钥即可,无需填写 base url @qNwNp
from chatgpt-next-web.
Bot detected the issue body's language is not English, translate it automatically.
If you apply from Alibaba official website, you can directly fill in the application key without filling in the base url.
from chatgpt-next-web.
如果是从阿里官方申请的,直接填写申请的密钥即可,无需填写 base url @qNwNp
@LiuElric 您好,我按照您图中所写的,其不再像原来一样报错,但是其仍旧没有正常工作,它回复了一段HTML,展示效果如下图所示:
from chatgpt-next-web.
Bot detected the issue body's language is not English, translate it automatically.
If you apply from Alibaba official website, you can directly fill in the application key without filling in the base url @qNwNp
@LiuElric Hello, I followed what you wrote in the picture. It no longer reports the same error as before, but it still does not work normally. It replies with a piece of HTML, and the display effect is as shown in the figure below:
from chatgpt-next-web.
我是通过docker部署的,没有添加任何环境变量。在模型中选择通义大模型,然后自定义模型中选Alibaba,填上阿里云百炼申请的SK就可以了
from chatgpt-next-web.
Bot detected the issue body's language is not English, translate it automatically.
I deployed via docker without adding any environment variables. Select Tongyi Large Model in the model, then select Alibaba in the custom model, and fill in the SK applied for by Alibaba Cloud Bailian.
from chatgpt-next-web.
我是通过docker部署的,没有添加任何环境变量。在模型中选择通义大模型,然后自定义模型中选Alibaba,填上阿里云百炼申请的SK就可以了
from chatgpt-next-web.
Bot detected the issue body's language is not English, translate it automatically.
![image](https://private-user-images.githubusercontent.com/36125147/350051523-5574c5d9-148d-49e6-a7a8-99c28001c1cc.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3 MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3MjEzMTk4ODksIm5iZiI6MTcyMTMxOTU4OSwicGF0aCI6Ii8zNjEyNTE0N y8zNTAwNTE1MjMtNTU3NGM1ZDktMTQ4ZC00OWU2LWE3YTgtOTljMjgwMDFjMWNjLnBuZz9YLUFtei 1BbGdvcml0aG09QVdTNC1ITUFDLVNIQTI1NiZYLUFtei1DcmVkZW50aWFsPUFLSUFWQ09EWUxTQTU zUFFLNFpBJTJGMjAyNDA3MTglMkZ1cy1lYXN0LTElMkZzMyUyRmF3czRfcmVxdWVzdCZYLUFtei1EYXRlPTIwMjQwNzE4VDE2MTk0OVomWC1BbXotRXhwaXJlcz0zMDAmWC1BbXotU2lnbmF0dXJlP TQ2NTFiM2VlYjBjNDI2OWQ5ZWJiNDlkZjQxZjg5M2NlZjUwYWE4NmZmZjAyMTZkNjFkMTI3NDgxODhkMzhiNDcmWC1BbXotU2lnbmVkSGVhZGVycz1ob3N0JmFjdG9yX2lkPTAma2V5X2lkPTAmcm Vwb19pZD0wIn0.iuYYVIatpOoEGzQ2bmurPmHcsPMUirUWPcQFNtHWnFY)
I deployed via docker without adding any environment variables. Select Tongyi Large Model in the model, then select Alibaba in the custom model, and fill in the SK applied for by Alibaba Cloud Bailian.
from chatgpt-next-web.
如果是从阿里官方申请的,直接填写申请的密钥即可,无需填写 base url @qNwNp
@LiuElric 您好,我按照您图中所写的,其不再像原来一样报错,但是其仍旧没有正常工作,它回复了一段HTML,展示效果如下图所示:
收到,你有在环境变量里面做什么操作吗?如果没有的话,可能需要检查一下 key 是否正确,我这边尝试直接填 key 是OK的
from chatgpt-next-web.
Bot detected the issue body's language is not English, translate it automatically.
If you apply from Alibaba official website, you can directly fill in the application key without filling in the base url @qNwNp
@LiuElric Hello, I followed what you wrote in the picture, and it no longer reports the same error as before, but it still does not work normally. It replies with a piece of HTML, and the display effect is as shown in the figure below: ![image](https: //private-user-images.githubusercontent.com/75257874/349985560-83f77a93-4e60-406e-b30f-e6f3459656bd.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9..rDnTtJvrc0j1 IHBlmNV_2Xqh0_xlE6bIIwMPyN8C6Sk)
Received, have you done anything in the environment variables? If not, you may need to check whether the key is correct. I tried to fill in the key directly and it was OK.
from chatgpt-next-web.
我也出现了这个问题,我下载的mac 2.13的版本返回也是html内容
但是我把这个git项目clone到本地并且切到2.13的tag用npm run dev测试,同样的配置却能正确运行
看起来像是next项目没有找到正确的路径
我本地执行run app:dev时跟mac 2.13版本出现一样的错误,控制台打印就只有这部分
我最后看了下问题出在app打包的时候 next的output为"export",打出来的包情况不太一样,我对next和tauri不太熟,只能看到这儿了
from chatgpt-next-web.
我也出现了这个问题,我下载的mac 2.13的版本返回也是html内容
但是我把这个git项目clone到本地并且切到2.13的tag用npm run dev测试,同样的配置却能正确运行 看起来像是next项目没有找到正确的路径
我本地执行run app:dev时跟mac 2.13版本出现一样的错误,控制台打印就只有这部分
我最后看了下问题出在app打包的时候 next的output为"export",打出来的包情况不太一样,我对next和tauri不太熟,只能看到这儿了
from chatgpt-next-web.
Bot detected the issue body's language is not English, translate it automatically.
I also had this problem. The mac 2.13 version I downloaded also returned html content
But I cloned this git project locally and switched to the 2.13 tag to test it with npm run dev. The same configuration can Running correctly looks like the next project didn't find the correct path
When I execute run app:dev locally, the same error occurs as in the mac version 2.13. The console prints only this part
I last checked that the problem was when the app was packaged, the output of next was "export", and the package situation was different. I am not familiar with next and tauri, so I can only see here.
from chatgpt-next-web.
我也出现了这个问题,我下载的mac 2.13的版本返回也是html内容
但是我把这个git项目clone到本地并且切到2.13的tag用npm run dev测试,同样的配置却能正确运行 看起来像是next项目没有找到正确的路径
我本地执行run app:dev时跟mac 2.13版本出现一样的错误,控制台打印就只有这部分
我最后看了下问题出在app打包的时候 next的output为"export",打出来的包情况不太一样,我对next和tauri不太熟,只能看到这儿了
我的也是Mac客户端,2.13.1版本,完全相同的报错。
from chatgpt-next-web.
Bot detected the issue body's language is not English, translate it automatically.
I also had this problem. The mac 2.13 version I downloaded also returned html content <img alt="image" width="676" src="https://private-user-images.githubusercontent.com/6702568/ But I cloned this git project locally and switched to the 2.13 tag to test it with npm run dev. The same configuration works Running correctly looks like the next project didn't find the correct path
When I execute run app:dev locally, the same error occurs as in the mac version 2.13. The console prints only this part
I last checked that the problem was when the app was packaged, the output of next was "export", and the package situation was different. I am not familiar with next and tauri, so I can only see here.
Mine is also a Mac client, version 2.13.1, with exactly the same error.
from chatgpt-next-web.
Related Issues (20)
- [Bug] When using the claude 3 opus, send a message and reply with data: [DONE], the other claude model succeeds.
- [Feature Request] docker镜像里有计划更新这个功能吗? HOT 1
- [Bug] Mask中不会默认选中azure的模型 HOT 3
- [Bug] "The Quota has been exceeded" - Version 2.14.1 (20240806.144936) - Mac M1 HOT 6
- [Bug] HOT 4
- [Bug] upstash 同步失败 HOT 1
- [Bug] empty response from server HOT 4
- [Bug] Claude3 opus 回复大段文字失败 HOT 5
- [Bug] 更新到 2.14.1 之后 Gemini Free Tier 无法使用 HOT 1
- [Bug] invalid_request_error with claude and anthropic api HOT 2
- [Feature Request] Custom Endpoint API Claude
- [Bug] 当使用让AI识别图片时,对话没有被总结,以至于后续提问完全忽略图片内容。 HOT 1
- [Bug] 新版本检测错误 HOT 4
- [Feature Request] 对话中希望增加模型名称的显示 HOT 1
- [Bug] 升級到 2.14.1 之後, google gemini 無法使用 HOT 1
- [Bug] windows 端exe无法自定义接口 HOT 1
- [Bug] `CUSTOM_MODELS`可选项配置`-all,+xxx`后导致自定义模型无法使用 HOT 1
- [Feature Request] Add support for prompt caching with Claude
- [Feature Request] HOT 1
- [Feature Request] 代码折叠功能完善建议 HOT 1
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 chatgpt-next-web.