Artificial Intelligence 9 min read

Integrate DeepSeek AI Assistant into IntelliJ IDEA for Java Development

This guide walks Java developers through preparing the environment, installing the CodeGPT plugin, configuring DeepSeek with an API key, and using the AI assistant for code generation, completion, explanation, and token usage monitoring within IntelliJ IDEA.

macrozheng
macrozheng
macrozheng
Integrate DeepSeek AI Assistant into IntelliJ IDEA for Java Development

Introduction

In early 2025, AI tools surged in China, and DeepSeek quickly became popular among developers. Integrating DeepSeek into IntelliJ IDEA provides Java developers with an intelligent coding assistant that boosts productivity.

1. Environment Preparation

IDEA Version Compatibility

Use IntelliJ IDEA 2023.x or newer. Install the CodeGPT plugin, an AI‑driven code assistant that serves as an alternative to GitHub Copilot and similar tools.

Python Environment

DeepSeek requires Python 3.7 or higher. After installation, add Python to the system PATH so the plugin can locate it.

<code>Macbook:GithubCommitSpace Aion$ python --version
Python 3.12.8
Macbook:GithubCommitSpace Aion$</code>

2. Install and Configure DeepSeek

Install the AI Code Assistant Plugin

Open IDEA, go to

Settings

(Windows/Linux) or

IntelliJ IDEA → Preferences

(macOS), select

Plugins

, search for

CodeGPT

in the Marketplace, and install it.

Create and Set API Key

Visit

https://www.deepseek.com/

, open the API Open Platform, and generate an API key. In IDEA, locate the DeepSeek settings and paste the key.

IDEA Integration Settings

In the CodeGPT settings, open

Custom OpenAI

and configure three sections:

API Key : paste the DeepSeek API key.

Chat Model : set URL to

https://api.deepseek.com/chat/completions

and model name to

deepseek-chat

.

Inference Model : enable

Enable code completions

and

Parse response as Chat Completions

, choose FIM template

DeepSeek Coder

, set URL to

https://api.deepseek.com/chat/completions

, and model name to

deepseek-reasoner

.

3. Using DeepSeek for Programming

Generate Ideas and Code

Select the CodeGPT component, choose

Custom OpenAI

, and enter a prompt such as “Write a Java method that filters digits and provide a test.” The assistant returns the following code:

<code>public class TestNumberFilter {
    public static String filterNumbers(String input) {
        // Use regex to keep only digits
        return input.replaceAll("[^0-9]", "");
    }

    public static void main(String[] args) {
        String testInput2 = "SSFSDFS结论萨芬122432的噶大都是4无人区是14认识832safsss";
        String result = filterNumbers(testInput2);
        System.out.println("Filtered numbers: " + result); // Output: 122432414832
    }
}</code>

Code Completion

While typing, press

Ctrl + Space

(or a custom shortcut) and DeepSeek suggests the next code segment.

Code Explanation

Select a code block, right‑click, and choose

CodeGPT

to receive a detailed explanation of its logic.

Ask Questions

Highlight code or describe an issue, then select “CodeGPT: Ask Question” to get targeted solutions.

4. DeepSeek Usage Statistics

Token consumption can be viewed on the DeepSeek website. The following screenshots show daily usage and cost breakdown for the

deepseek-chat

model.

Conclusion

Following these steps integrates DeepSeek into IntelliJ IDEA, allowing Java developers to benefit from AI‑assisted coding, code completion, explanation, and troubleshooting.

JavaDeepSeekCodeGPTIntelliJ IDEAAI code assistantPlugin integration
macrozheng
Written by

macrozheng

Dedicated to Java tech sharing and dissecting top open-source projects. Topics include Spring Boot, Spring Cloud, Docker, Kubernetes and more. Author’s GitHub project “mall” has 50K+ stars.

0 followers
Reader feedback

How this landed with the community

login Sign in to like

Rate this article

Was this worth your time?

Sign in to rate
Discussion

0 Comments

Thoughtful readers leave field notes, pushback, and hard-won operational detail here.