NextChat 如何使用v2.13.0的自定义模型功能（how to use 2.13.0 multi models)

在v2.13.0版本扩展了CUSTOM_MODELS支持的语法

支持通过@指定provider，支持通过=指定deploy_name

解决Azure和OpenAI的模型不能共存的问题

+gpt-3.5-turbo@openai,+gpt-3.5-turbo@azure=gpt-3.5 以上配置会分别展示两个模型gpt-3.5-turbo(OpenAI)以及gpt-3.5(Azure) 并且使用Azure部署的gpt-3.5-turbo模型会把请求发送到deploy_name=gpt-3.5这个部署的服务上面

新增使用字节跳动提供的豆包模型的时候定义deploy_id

+Doubao-lite-4k@bytedance=ep-2024xxxx-xxx 以上配置会新增一个Doubao-lite-4k(ByteDance)的模型，当选择这个模型的时候，会将请求发送到ep-2024xxxx-xxx这个deploy-id服务上面

支持自定义厂商发布的不在内置模型列表中的新模型

假如openai发布了gpt-4.5，但是nextchat未及时发布新版可以配置+gpt-4.5@OpenAI，模型列表会新增gpt-4.5(OpenAI)选项，并且按openai的消息格式发送请求

考虑到一些厂商做中转的时候会将多家厂商的模型都按OpenAI的格式做转发，也可以通过CUSTOM_MODELS配置使用：

例如，厂商同时中转了gpt-3.5-turbo和claude-2.1，都走兼容openai的格式配置+gpt-3.5-turbo@OpenAI,+claude-2.1@OpenAI（这里使用OpenAI而不是openai代表不是内置的服务商列表，只是符合OpenAI的消息格式）会新增gpt-3.5-turbo(OpenAI)和 claude-2.1(OpenAI)两个模型选项。请求都会发送到/api/openai/* 这个时候可以在.env通过配置BASE_URL+OPENAI_API_KEY的模式，或者签到配置自定义接口走这家中转供应商的服务

Jul 14 '24 05:07 lloydzhou

Please follow the issue template to update title and description of your issue.

Jul 14 '24 05:07 nextchat-manager[bot]

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

Title: How to use the custom model function of v2.13.0 (how to use 2.13.0 multi models)

The syntax supported by CUSTOM_MODELS has been expanded in version v2.13.0

Supports specifying provider through @, and supports specifying deploy_name through =

Solve the problem that Azure and OpenAI models cannot coexist

+gpt-3.5-turbo@openai,+gpt-3.5-turbo@azure=gpt-3.5 The above configuration will display two models gpt-3.5-turbo(OpenAI) and gpt-3.5(Azure) respectively And using the gpt-3.5-turbo model deployed by Azure will send the request to the deployed service deploy_name=gpt-3.5

Added the definition of deploy_id when using the beanbao model provided by ByteDance.

+Doubao-lite-4k@bytedance=ep-2024xxxx-xxx The above configuration will add a Doubao-lite-4k(ByteDance) model. When this model is selected, the request will be sent to the ep-2024xxxx-xxx deploy-id service

Support new models released by custom manufacturers that are not in the built-in model list

If openai releases gpt-4.5, but nextchat does not release the new version in time You can configure +gpt-4.5@OpenAI, the gpt-4.5(OpenAI) option will be added to the model list, and the request will be sent according to the message format of openai

Considering that some manufacturers will forward models from multiple manufacturers according to the OpenAI format when transferring, they can also be configured and used through CUSTOM_MODELS:

For example, the manufacturer forwarded gpt-3.5-turbo and claude-2.1 at the same time, both in formats compatible with openai. Configure +gpt-3.5-turbo@OpenAI,+claude-2.1@OpenAI (the use of OpenAI instead of openai here means that it is not a built-in service provider list, but only conforms to the message format of OpenAI) Two new model options, gpt-3.5-turbo(OpenAI) and claude-2.1(OpenAI), will be added. Requests will be sent to /api/openai/* At this time, you can configure the BASE_URL+OPENAI_API_KEY mode in .env, or sign in to configure a custom interface to use the services of this transit provider

Jul 14 '24 05:07 Issues-translate-bot

感谢提供的帮助。有个疑问，怎么对模型进行排序，比如自定义模型排列在最前面。

Jul 14 '24 08:07 siwuxei

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

Thanks for the help. I have a question, how to sort the models, such as custom models at the front.

Jul 14 '24 08:07 Issues-translate-bot

另外想问一下如何支持多个相同的自定义部署呢比如Azure #4398
当前已知的是可以支持相同的资源使用不同的部署，但是无法使用跨区域资源的不同部署

Jul 15 '24 01:07 ice-lemon

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

Also, I would like to ask how to support multiple custom deployments #4398

Jul 15 '24 01:07 Issues-translate-bot

docker compose部署发现按描述配置：+gpt-3.5-turbo@azure=gpt-3.5，无法正常生效，没有配置任何openai的参数，但默认走openai导致返回错误

Jul 15 '24 09:07 aiyurui

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

The docker compose deployment found that it was configured as described: +gpt-3.5-turbo@azure=gpt-3.5, which could not take effect normally. No openai parameters were configured, but openai was used by default.

Jul 15 '24 09:07 Issues-translate-bot

自定义模型的url，在env中是配置哪个变量？

Jul 20 '24 16:07 kele527

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

Which variable is configured in env for the custom model url?

Jul 20 '24 16:07 Issues-translate-bot

问答时报错：Unknown parameter: 'path' chatgpt-next的配置: gpt-4o@openai，代理地址是one-api，one-api对接的是azure的api。

请求one-api的参数： { "messages": [ { "role": "system", "content": "\nYou are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2023-10\nCurrent model: gpt-4o\nCurrent time: Mon Jul 22 2024 16:32:39 GMT+0800 (中国标准时间)\nLatex inline: $x^2$ \nLatex block: $$e=mc^2$$\n\n" }, { "role": "user", "content": "你好呀，gpt" } ], "stream": true, "model": "gpt-4o", "temperature": 0.5, "presence_penalty": 0, "frequency_penalty": 0, "top_p": 1, "path": "completions" }

Jul 22 '24 08:07 huelsgp27

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

Error during Q&A: Unknown parameter: 'path' The configuration of chatgpt-next: gpt-4o@openai, the proxy address is one-api, and one-api is connected to the azure api.

Parameters for requesting one-api: { "messages": [ { "role": "system", "content": "\nYou are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2023-10\nCurrent model: gpt-4o\nCurrent time: Mon Jul 22 2024 16:32:39 GMT+0800 (China Standard time)\nLatex inline: $x^2$ \nLatex block: $$e=mc^2$$\n\n" }, { "role": "user", "content": "Hello, gpt" } ], "stream": true, "model": "gpt-4o", "temperature": 0.5, "presence_penalty": 0, "frequency_penalty": 0, "top_p": 1, "path": "completions" }

Jul 22 '24 08:07 Issues-translate-bot

谢谢，解决了第三方api的问题

Jul 23 '24 17:07 geek2024811

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

Thank you, the problem with the third-party API has been solved

Jul 23 '24 17:07 Issues-translate-bot

弱弱地问下，插件里面的Artifacts是干嘛的，谷歌、百度了一遍，还是没看明白。。。

Jul 30 '24 03:07 hp0912

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

I asked weakly what the Artifacts in the plug-in are for. I searched Google and Baidu, but I still don’t understand. . .

Jul 30 '24 03:07 Issues-translate-bot

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

I asked weakly what the Artifacts in the plug-in are for. I searched Google and Baidu, but I still don’t understand. . .

适用Claude模型的一个插件，具体可以看一下官方的说明 https://www.anthropic.com/news/claude-3-5-sonnet

Aug 09 '24 03:08 wenzhaoabc

我在使用该项目调用自己微调的大模型接口时，输出的token被限制在了100，请问我应该如何修改。

Sep 12 '24 05:09 Qshuangyan

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

When I use this project to call the large model interface I fine-tuned, the output token is limited to 100. How should I modify it?

Sep 12 '24 05:09 Issues-translate-bot

@lloydzhou v2.15.5版本尝试+claude-3-5-sonnet-20240620@OpenAI,+claude-3-haiku-20240307@OpenAI ，在OpenAI渠道下没看到相关模型选项

Oct 28 '24 03:10 JIeJaitt

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

@lloydzhou v2.15.5 version tried +claude-3-5-sonnet-20240620@OpenAI, +claude-3-haiku-20240307@OpenAI, but did not see the relevant model options under the OpenAI channel

Oct 28 '24 03:10 Issues-translate-bot

使用+Doubao-lite-4k@bytedance=ep-2024xxxx-xxx并不会显示Doubao-lite-4k(ByteDance)而是会显示ep-2024xxxx-xxx（在模型选择里会显示Doubao-lite-4k(ByteDance)，但在聊天界面显示的是ep-2024xxxx-xxx）

Dec 13 '24 06:12 NP-Prob

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

Using +Doubao-lite-4k@bytedance=ep-2024xxxx-xxx will not display Doubao-lite-4k(ByteDance) but will display ep-2024xxxx-xxx (it will be displayed in the model selection) Doubao-lite-4k(ByteDance), but the chat interface displays ep-2024xxxx-xxx`)

Dec 13 '24 06:12 Issues-translate-bot

使用豆包模式，返回如下信息，为什么呢，key都是配置好的，求大佬解答！ { "error": true, "message": "you are not allowed to use ep-20241229112559-tjhth model" }

Dec 29 '24 03:12 zjsmonkey

使用豆包模式，返回如下信息，为什么呢，key都是配置好的，求大佬解答！ { "error": true, "message": "you are not allowed to use ep-20241229112559-tjhth model" }

模型添加后缀 @OpenAI 了吗

没有呢，要加@OpenAI吗，我是直接这样添加的+Doubao-pro-32k@bytedance=ep-20241229112559-tjhth

Dec 29 '24 11:12 zjsmonkey

目前使用的api2d这个api提供商分别尝试了增加api端点，填入apikey到openai 和 Anthropic的配置中；也尝试了增加+claude-3-sonnet-20240229@OpenAI,+claude-3-sonnet-20240229@Anthropic 勾选默认Anthropic的claude-3-sonnet-20240229的时候报错Only /v1/chat/completions && /v1/embeddings allowed now , your path {/v1/messages} 勾选默认openai和新增OpenAI的claude-3-sonnet-20240229的时候报错Only gpt-3.5-turbo-0613 && gpt-3.5-turbo-0125 && gpt-3.5-turbo-16k-0613 && gpt-3.5-turbo-1106 && gpt-3.5-turbo-16k && gpt-3.5-turbo-0301 && gpt-3.5-turbo && text-embedding-ada-002 && text-embedding-3-large && text-embedding-3-small && gpt-4 && gpt-4o && gpt-4o-2024-05-13 && gpt-4o-2024-08-06 && gpt-4o-2024-11-20 && gpt-4o-mini-2024-07-18 && gpt-4o-mini && o1-preview && o1-preview-2024-09-12 && o1 && o1-2024-12-17 && o1-mini && o1-mini-2024-09-12 && gpt-4-0314 && gpt-4-0613 && gpt-4-0125-preview && gpt-4-1106-preview && gpt-4-vision-preview && gpt-4-turbo-preview && gpt-4-turbo && gpt-4-turbo-2024-04-09 && gpt-4-1106-vision-preview allowed now, your model {claude-3-sonnet-20240229}",

都无法完成通信，我是不是理解的有问题，

Jan 12 '25 08:01 qianzyGit

使用+Doubao-lite-4k@bytedance=ep-2024xxxx-xxx并不会显示Doubao-lite-4k(ByteDance)而是会显示ep-2024xxxx-xxx（在模型选择里会显示Doubao-lite-4k(ByteDance)，但在聊天界面显示的是ep-2024xxxx-xxx）

使用豆包模式，返回如下信息，为什么呢，key都是配置好的，求大佬解答！ { "error": true, "message": "you are not allowed to use ep-20241229112559-tjhth model" }

对于默认模型库里没有的字节模型（其他的没测试，起码字节是这样），一定要写成CUSTOM_MODELS: Doubao-1.5-pro-32k@ByteDance=ep-XXXXX（注意 ByteDance 的大小写），前面不要写 + 号。写了加号，列表里就显示成了 + Doubao-1.5-pro-32k (ByteDance)

Feb 08 '25 15:02 Chandler-Lu