Basic assistant with LangChain4j and Ollama

This example shows the smallest LangChain4j AI service backed by a local Ollama model.

The Assistant interface carries the system instruction as an annotation, and LangChain4j generates the implementation at runtime.

Requirements

• Java 21+
• Maven 3.9+
• Ollama installed locally
• A pulled chat model such as llama3.2:1b

Steps for running this example in the shell

1. Start Ollama and pull the model:

ollama serve
ollama pull llama3.2:1b

2. Run the application:

mvn compile exec:java

Output

LangChain4j is a Java library that lets you build applications on top of large language models.