Welcome to DOFBOT-Ultra repository

4. Basic Dify Features

Basic Dify Features

Please ensure that the web control program backend process is not running in the background. To close it, refer to the [Get Started Quickly - 2. Access the Terminal] section in [Disable the Auto-Start Web Control Backend Process]. After closing, please restart DofbotUltra!!!

Basic Dify Features1. Course Content2. Start Dify Service3. Basic Usage3.1 Switch Dify Language3.2 Connect to a Model Provider Service3.3 Switch the AI Model Used by an AI Application4. Account Settings5. Development Documentation

1. Course Content

Understand and master the basic operations and functions of Dify.
Dify's Docker startup takes a long time. It is recommended to access the console from the browser after ten minutes.

2. Start Dify Service

The Dify backend runs on the host system of the DofbotUltra motherboard, not inside a Docker container.
After connecting to the device via VNC or SSH, execute the following command in any directory on the host system to start Dify (it is set to auto-start by default; this is only for demonstration when manually restarting after closing):


bringup_dify

After startup, you can check the device's IP address via the OLED screen, ifconfig, or directly in the terminal.
Enter the device IP address in the browser address bar of a computer on the same LAN as DofbotUltra to access the Dify management page. If it is the first login, you need to use the account and password, and you can switch the language in the upper left corner.

Tip

If the browser cannot access it, execute docker ps on the host system to confirm that the langgenius/dify-* related containers are in the Up state.

Note

Account: yahboom@163.com
Password: yahboom123
All account passwords, agent applications, and RAG data are stored locally.

Note: Dify's first startup is slow. Please be patient.

The Dify main interface is as follows:

3. Basic Usage

Tip

If you need to use cloud AI models from a model provider, ensure the device is connected to the internet.

3.1 Switch Dify Language

Generally, the Dify page will follow the browser's language. If you need to switch manually, you can do so in the settings.

3.2 Connect to a Model Provider Service

Dify has built-in model interface plugins for different model providers. These plugins are maintained and updated by the respective model providers. You can install the corresponding model provider plugin to quickly connect to cloud models from different vendors.
Click on the upper left of the homepage: Plugins -> Explore Marketplace -> Models to enter the model interface plugin page.

Here, we take installing and configuring the Tongyi Qianwen plugin as an example. The method is the same for other plugins. Click Install.

Then, in the Settings page's Model Provider, fill in the applied model provider API Key. If the Key is available, the corresponding plugin's API Key status will show a green light.

Tip

For more detailed steps on configuring the model provider API Key and testing methods, refer to the previous 02-Configure API-KEY course.

3.3 Switch the AI Model Used by an AI Application

For already developed AI agent applications, you can quickly switch between different models to test their effects. Here, we take the core agent multi_brains of ROSMASTER-M3 Pro as an example. Click on the agent application on the homepage.

It contains three core AIs: Task Router, Decision Layer AI, and Execution Layer AI.

Taking switching the Decision Layer AI as an example, click on the Decision Layer AI card, and in the model selection bar, pull down to switch between different provider models.
Note: qwen-vl-max will be removed from the platform in July 2026. You need to use another visual large model when switching.

You can also fine-tune the model's response effect parameters. Each parameter can be viewed in detail by hovering the mouse over it.
Taking the temperature parameter as an example:


xxxxxxxxxx
Used to control the degree of randomness and diversity. The temperature value controls the degree of smoothing applied to the probability distribution of each candidate word when generating text. A higher temperature value lowers the peak of the probability distribution, allowing more low-probability words to be selected and making the results more diverse; a lower temperature value enhances the peak of the probability distribution, making high-probability words easier to select and making the results more deterministic.

Tip

Beginners can generally keep the default parameters without adjustment.

Note: After modifying the AI application, you need to click Publish -> Publish Update to save the changes.

Warning

Please note:

For the execution layer model, since it needs to process images, only multimodal models can be used (visual models have special symbol markings as shown below).
The task router and decision layer models have no restrictions.
The task router can use small parameter models to improve response speed.

4. Account Settings

Note

The Dify account information is stored locally and poses no privacy risk. ROSMASTER-M3 Pro comes with a preset administrator account. If you need to modify account information, you can refer to this part of the tutorial.

Click the avatar in the upper right corner -> Account.

The account information is as follows. You can modify the information as needed.

If you need to log out, click the avatar again to log out.

5. Development Documentation

For users with further development needs, you can view more detailed development documentation. Click the avatar in the upper right corner -> View Help Documentation.

This will open Dify's online development documentation page. You can select different content to view from the dropdown list on the left.

Introduction to Dify

AI Large Model Development - chatbot