Install Model Studio SDK - Alibaba Cloud Model Studio - Alibaba Cloud Documentation Center

Model Studio provides SDKs for Python and Java (also called DashScope SDK), and invocation methods compatible with OpenAI SDKs for Python, Node.js, Java, and Go. This topic describes how to install Open AI SDK and DashScope SDK.

Procedure

Python

Step 1: Check Python version

Run the following command in the terminal to check whether Python is installed:

Make sure that you have Python version 3.8 or higher, see Install Python.

python -V
pip --version

Take Windows CMD as an example:

FAQ

Q: An error occurs when executing python -V, pip --version:

'python' is not recognized as an internal or external command, operable program or batch file.
'pip' is not recognized as an internal or external command, operable program or batch file.
-bash: python: command not found
-bash: pip: command not found

A: Take the following steps:

Windows

Make sure that you have installed Python in your computing environment and that you have added python.exe to PATH.
If you have installed Python and added the environment variable, but the error still occurs, close the current terminal and open a new terminal to try again.

Linux and macOS

Make sure you have installed Python in your computing environment.
If you have installed Python but the error still occurs, run which python pip to check whether python and pip exist in the system.
- If the following result is returned, close the current terminal and open a new terminal to try again.
```
/usr/bin/python
/usr/bin/pip
```
- If the following result is returned, run which python3 pip3 to check again.
```
/usr/bin/which: no python in (/root/.local/bin:/root/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin)
/usr/bin/which: no pip in (/root/.local/bin:/root/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin)
```
  If the following result is returned, run python3 -V, pip3 --version to check the version.
```
/usr/bin/python3
/usr/bin/pip3
```

Step 2: Configure virtual environment (optional)

After Python is installed, you can set up a virtual environment to manage dependencies for OpenAI Python SDK or DashScope Python SDK. The virtual environment can avoid conflicts with your other projects.

Create a virtual environment
Run the following command to create a virtual environment named .venv:
```
# If the operation fails, replace python with python3 and run again
python -m venv .venv
```
Activate the virtual environment
For Windows:
```
.venv\Scripts\activate
```
For macOS or Linux:
```
source .venv/bin/activate
```

Step 3: Install Python SDK

Install OpenAI Python SDK or DashScope Python SDK to call models in Model Studio.

OpenAI Python SDK

Run the following command:

# If the operation fails, replace pip with pip3 and run again
pip install -U openai

When the terminal displays Successfully installed ... openai-x.x.x, OpenAI Python SDK is installed.

DashScope Python SDK

Run the following command:

# If the operation fails, replace pip with pip3 and run again
pip install -U dashscope

When the terminal displays Successfully installed ... dashscope-x.x.x, DashScope Python SDK is installed.

Note

When installing the SDK, you may see WARNING: You are using pip version xxx; however, version xxx is available. This is an update notification of the pip tool, and is not related to the SDK. You can safely ignore it.

Java

Step 1: Check Java version

Run the following command in the terminal:

java -version
# (Optional) If you use Maven to manage and build Java projects, make sure that Maven is installed in your development environment
mvn --version

Take Windows CMD as an example:

DashScope Java SDK requires Java 8 or higher. The first line of the output shows your Java version. For example, openjdk version "16.0.1" 2021-04-20 indicates Java 16 is installed. If Java is not installed or the installed version is earlier than Java 8, go to Java Downloads to download and install the appropriate version.

Step 2: Install Java SDK

DashScope

After Step 1 is complete, you can install DashScope SDK for Java. Run the following command to include the Java SDK dependency in your project. Replace the-latest-version with the actual latest version number.

XML

Open the pom.xml file of your Maven project.

Add the dependency information within the <dependencies> tag.

<dependency>
    <groupId>com.alibaba</groupId>
    <artifactId>dashscope-sdk-java</artifactId>
    <!-- Replace 'the-latest-version' with the latest version number: https://mvnrepository.com/artifact/com.alibaba/dashscope-sdk-java -->
    <version>the-latest-version</version>
</dependency>

Save pom.xml.
Use Maven commands, such as mvn compile or mvn clean install, to refresh your project's dependencies. DashScope Java SDK will be downloaded and integrated into your project automatically.

Take Windows IDEA as an example:

Gradle

Open the build.gradle file of your Gradle project.

Add the dependency information within the dependencies block.

dependencies {
    // Replace 'the-latest-version' with the latest version number: https://mvnrepository.com/artifact/com.alibaba/dashscope-sdk-java
    implementation group: 'com.alibaba', name: 'dashscope-sdk-java', version: 'the-latest-version'
}

Save build.gradle.
Navigate to your project's root directory in the command line and run the following Gradle command to refresh your project dependencies. DashScope Java SDK will be downloaded and integrated into your project automatically.
```
./gradlew build --refresh-dependencies
```

Take Windows IDEA as an example:

OpenAI

After Step 1 is complete, you can install OpenAI SDK for Java. Run the following command to include the Java SDK dependency in your project. Replace the-latest-version with the actual latest version number.

XML

Open the pom.xml file of your Maven project.

Add the dependency information within the <dependencies> tag.

<dependency>
    <groupId>com.openai</groupId>
    <artifactId>openai-java</artifactId>
    <version>the-latest-version</version>
</dependency>

Save pom.xml.
Use Maven commands, such as mvn compile or mvn clean install, to refresh your project's dependencies. OpenAI Java SDK will be downloaded and integrated into your project automatically.

Gradle

Open the build.gradle file of your Gradle project.

Add the dependency information within the dependencies block.

dependencies {
    // Replace 'the-latest-version' with the latest version number: https://mvnrepository.com/artifact/com.openai/openai-java
    implementation group: 'com.openai', name: 'openai-java', version: 'the-latest-version'
}

Save build.gradle.
Navigate to your project's root directory in the command line and run the following Gradle command to refresh your project dependencies. OpenAI Java SDK will be downloaded and integrated into your project automatically.
```
./gradlew build --refresh-dependencies
```

This SDK is currently in beta.

Node.js

Step 1: Check Node.js installation status

Run the following command in the terminal to check whether Node.js and npm are installed in the current computing environment:

node -v
npm -v

Take Windows CMD as an example:

This command displays your current Node.js version. If Node.js is not installed in your environment, you can download it from Node.js official website.

Step 2: Install the SDK

Run the following command in the terminal:

npm install --save openai
# Or
yarn add openai

Note

If the installation fails, you can run the following command to configure a repository mirror:

npm config set registry https://registry.npmmirror.com/

Then, run the installation command to install the SDK again.

When the terminal displays added xx package in xxs, the OpenAI SDK is installed. You can run npm list openai to check the version information.

Go

OpenAI provides an SDK for Go. You can install it by running the following command:

go get github.com/openai/openai-go@v0.1.0-alpha.62

Version v0.1.0-alpha.62 is tested to be relatively stable.

This SDK is currently in beta.

What to do next

Explore sample codes to call models with the OpenAI SDK or DashScope SDK.

References

For a list of models that support the OpenAI SDK, see Compatibility with OpenAI.