This article is a mirror article of machine translation, please click here to jump to the original article.

View: 2031|Reply: 1

[AI] (4) Use Open WebUI to call the DeepSeek-R1 model

[Copy link]
Posted on 2025-2-6 21:21:14 | | | |
Requirements: The DeepSeek-R1 model was deployed using ollama, and a dialog tool was used to call it, and the terminal was simply used for testing. You can install an Open WebUI panel to invoke models for conversation.

Review:

【AI】(3) Tencent Cloud Deploys DeepSeek-R1 with HAI tutorial
https://www.itsvse.com/thread-10931-1-1.html

Open WebUI is a scalable, feature-rich, and user-friendly self-hosted AI platform designed to run completely offline. It supports various LLM runners like Ollama and OpenAI-compatible APIs, with a built-in RAG inference engine, making it a powerful solution for AI deployment.

GitHub address:The hyperlink login is visible.
Documentation:The hyperlink login is visible.
Environment Variable Configuration:The hyperlink login is visible.

Ubuntu 20.04 installs Docker containers

In this article, to deploy open-webui using Docker, you first need to install the Docker container, the installation command is as follows:


Ollama deploys the deepseek-r1:32b model

Run the following command:


Docker deploys Open WebUI

Since we already have Ollama installed natively and at the same time on a server, in/data/open-webuiCreate a new compose.yaml file below the folder, which reads:


Run the following command to start the container:


As shown below:



The firewall security group rule lets the TCP 3000 port go for a few moments, and then uses a browser to access it, as shown in the following figure:



For the first visit, set up the administrator account and password, as shown in the following figure:



Test the DeepSeek-R1 model dialog function as shown in the figure below:


(End)




Previous:【AI】(3) Tencent Cloud Deploys DeepSeek-R1 with HAI tutorial
Next:[AI] (5) Print out the Ollama request information
 Landlord| Posted on 2025-2-19 09:09:00 |
Similar to the front-end large model dialogue open source project

NextChat:The hyperlink login is visible.
Lobe Chat:The hyperlink login is visible.
Ollama LLM's full-featured web interface:The hyperlink login is visible.
Disclaimer:
All software, programming materials or articles published by Code Farmer Network are only for learning and research purposes; The above content shall not be used for commercial or illegal purposes, otherwise, users shall bear all consequences. The information on this site comes from the Internet, and copyright disputes have nothing to do with this site. You must completely delete the above content from your computer within 24 hours of downloading. If you like the program, please support genuine software, purchase registration, and get better genuine services. If there is any infringement, please contact us by email.

Mail To:help@itsvse.com