How to Customize HTTP Clients for LangChain4j LLM Integration in Java

0 Introduction

Some LangChain4j modules (currently OpenAI and Ollama) allow you to provide a custom HTTP client for calling LLM provider APIs.

The langchain4j-http-client module defines an HttpClient SPI that these modules use to invoke the provider's REST API. By implementing this SPI you can integrate any HTTP client.

1 Implementation Options

There are two ready‑made implementations:

1.1 JdkHttpClient

The langchain4j-http-client-jdk module contains JdkHttpClient. When you use a supported module such as langchain4j-open-ai, this client is used by default.

1.2 SpringRestClient

The langchain4j-http-client-spring-restclient module provides SpringRestClient. If you use a Spring Boot starter like langchain4j-open-ai-spring-boot-starter, this client becomes the default.

2 Customizing the JDK HttpClient

HttpClient.Builder httpClientBuilder = HttpClient.newBuilder()
        .sslContext(...);

JdkHttpClientBuilder jdkHttpClientBuilder = JdkHttpClient.builder()
        .httpClientBuilder(httpClientBuilder);

OpenAiChatModel model = OpenAiChatModel.builder()
        .httpClientBuilder(jdkHttpClientBuilder)
        .apiKey(System.getenv("OPENAI_API_KEY"))
        .modelName("gpt-4o-mini")
        .build();

3 Customizing Spring's RestClient

RestClient.Builder restClientBuilder = RestClient.builder()
        .requestFactory(new HttpComponentsClientHttpRequestFactory());

SpringRestClientBuilder springRestClientBuilder = SpringRestClient.builder()
        .restClientBuilder(restClientBuilder)
        .streamingRequestExecutor(new VirtualThreadTaskExecutor());

OpenAiChatModel model = OpenAiChatModel.builder()
        .httpClientBuilder(springRestClientBuilder)
        .apiKey(System.getenv("OPENAI_API_KEY"))
        .modelName("gpt-4o-mini")
        .build();

The article is part of the Java-Interview-Tutorial GitHub repository, which collects these technical notes.