You can list available models on Ollama’s library .
String answer = model.generate("What is the capital of France?"); System.out.println(answer); ollamac java work
OllamaChatModel model = OllamaChatModel.builder() .baseUrl("http://localhost:11434") .modelName("llama3:8b") .temperature(0.7) .build(); You can list available models on Ollama’s library
// Simple POJOs for request and response class ChatRequest private String model; private String prompt; private Boolean stream; /* getters/setters / class ChatResponse private String response; / getters/setters */ private String prompt
Ensure you adjust the context window ( num_ctx ) during the initialization block if your application handles long documents. By default, many models default to a 2048 or 4096 token limit, which can truncate extensive RAG data.