DeepSeek4j 1.4: A Java Framework for Seamless DeepSeek AI Integration with Full Chain‑of‑Thought and Streaming Support

DeepSeek R1 is popular for its chain‑of‑thought capabilities, but mainstream frameworks like Spring AI lack proper support for chain preservation and streaming output. The newly released DeepSeek4j 1.4 addresses these gaps.

Why DeepSeek4j?

DeepSeek4j is a Java‑focused integration framework for DeepSeek models, offering an elegant API that requires only a single line of code to connect to DeepSeek.

Limitations of Existing Frameworks

Chain content loss: The core reasoning process of R1 is ignored.

Incompatible response mode: Cannot handle "think first, conclude later" output.

Parameter restrictions: Settings such as temperature and top_p are ineffective.

Incomplete streaming: Poor user experience.

Solution

The open‑source project Pig, built on the excellent OpenAI4J architecture, created DeepSeek4j as a ready‑to‑use solution specifically for DeepSeek.

Enhanced support for DeepSeek’s unique chain‑of‑thought and billing features.

Full reactive support via Project Reactor.

Spring Boot Starter for automatic configuration.

Core Features

Complete preservation of chain‑of‑thought and billing.

Reactive streaming processing.

Simple and elegant API design.

Out‑of‑box Spring Boot integration for both 2.x and 3.x.

Built‑in debugging page.

Detailed request/response logging.

Flexible proxy configuration.

Comprehensive reactive programming support.

Quick Start

Add Dependency:

<dependency>
  <groupId>io.github.pig-mesh.ai</groupId>
  <artifactId>deepseek-spring-boot-starter</artifactId>
  <version>1.1.0</version>
</dependency>

Configuration (application.yml):

deepseek:
  api-key: your-api-key-here
  base-url: https://api.deepseek.com/v1  # optional, defaults to official API, supports alternatives

Basic Usage:

@Autowired
private DeepSeekClient deepSeekClient;

// SSE streaming response
@GetMapping(value = "/chat", produces = MediaType.TEXT_EVENT_STREAM_VALUE)
public Flux<ChatCompletionResponse> chat(String prompt) {
    return deepSeekClient.chatFluxCompletion(prompt);
}

Front‑end Debugging: Double‑click the sse.html file in the project root to open the debugging page, enter the backend SSE endpoint, and view the inference process and final result in real time. The page includes the complete front‑end implementation for reference.

Project address: https://github.com/pig-mesh/deepseek4j

Documentation: https://javaai.pig4cloud.com/deepseek