-
Notifications
You must be signed in to change notification settings - Fork 61.2k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Bug]ollama私有化部署,使用nextchat docker启动服务如何配置 #6304
Comments
📦 Deployment methodDocker 📌 Software versionv2.15.8 💻 System environmentOther Linux 📌 System version7 🌐 BrowserChrome 📌 Browser versionLatest 🐛 Question descriptionAfter deploying deepseek via ollama private, I want to use nextchat for the team to use. When starting via docker, the configuration parameters are as follows
Question: How to configure startup information in my usage scenario 📷 Reproduction stepsNo response 🚦 Expected resultsNo response 📝 Supplementary informationNo response |
你应该填ollama在docker的ip而不是127.0.0.1,建议学懂运维再来做技术。 |
You should fill in the ip of ollama in docker instead of 127.0.0.1. It is recommended to learn operation and maintenance before doing the technology. |
@amlkiller 同一台机器 有何区别。。。 |
@amlkiller What is the difference between the same machine. . . |
docker的127是虚拟机的本机,不是物理机的127。去看下docker的文档吧。你找个教程跟着做。 |
Docker's 127 is the native of the virtual machine, not the 127 of the physical machine. Go and read the docker documentation. You find a tutorial to follow. |
那我根本没有配置BASE_URL也一样可以使用 又是为什么呢? 我只是虚心讨教,别上来就上纲上线的。懂一点东西 感觉啥都懂一样 |
Then I didn't configure BASE_URL at all and it can be used. Why? I'm just asking for advice humbly, don't just exaggerate it. Understand something, I feel like I understand everything |
简单来说。就是目前的nextchat 确实有问题,在不绑定任何配置的情况下 同一台机器,依旧可以使用 而且在使用期间,使用的模型会自动变动,这些是问题而已。不在乎什么是不是127.0.0.1 能连接不就可以了么。有什么问题 |
Simply put. There is indeed a problem with the current nextchat. The same machine can still be used without binding any configuration. And during use, the model used will automatically change. These are just problems. Don't care if 127.0.0.1 is enough to connect. What's the problem |
我语气不好致歉,但我确实认为这是运维技术问题。
|
I apologize for a bad tone, but I do think it is an operation and maintenance technical issue. |
我拉取的镜像,正常跑起来后,我没有使用BASE_URL,但还是可以访问ollama对应的服务。我其实很疑惑项目运行使用的配置。 |
I pulled the image. After running normally, I did not use BASE_URL, but I could still access the corresponding service of ollama. I'm actually very confused about the configuration used by the project. |
![]() |
For example, I have not configured BASE_URL now, but the dialogue function can be used normally. I don't know the reason |
这是前端自定义接口 baseurl是环境变量,真的去看下docker文档和运维吧。 |
This is a front-end custom interface. Baseurl is an environment variable. I really go to see the docker documentation and operation and maintenance. |
项目默认的BASE_URL是OpenAI,能连上ollama? 灵异了? 如果是docker desktop,可以使用host.docker.internal访问宿主机端口,如果是Linux直接使用host网络,稍微看一下文档,还是比较容易部署的。 |
The default BASE_URL of the project is OpenAI, can it be connected to ollama? Supernatural? If it is docker desktop, you can use host.docker.internal to access the host port. If it is Linux, it is easier to deploy if it is using the host network directly. |
额 我还是懂这些的。但是部署后确实存在这个问题。 我截图之类的信息 已经证明了。 |
Well, I still understand these. But this problem does exist after deployment. Information like my screenshots have proved. |
![]() ![]() |
![]() ![]() |
📦 部署方式
Docker
📌 软件版本
v2.15.8
💻 系统环境
Other Linux
📌 系统版本
7
🌐 浏览器
Chrome
📌 浏览器版本
latest
🐛 问题描述
通过ollama私有化部署deepseek后,我想使用nextchat给团队使用。通过docker启动时,配置参数如下
docker run -d -p 3000:3000 -e BASE_URL=http://127.0.0.1:11434 -e CUSTOM_MODELS="+deepseek-r1-14b" -e DEFAULT_MODEL="deepseek-r1:14b" yidadaa/chatgpt-next-web
访问页面后
没有使用到自定义接口定义 导致功能无法使用
提问:请问在我这种使用场景下,该如何配置启动信息
📷 复现步骤
No response
🚦 期望结果
No response
📝 补充信息
No response
The text was updated successfully, but these errors were encountered: