Request request = new Request.Builder() .url(OLLAMA_URL) .post(RequestBody.create(json, MediaType.parse("application/json"))) .build();
"model": "%s", "prompt": "%s", "stream": false
An OllamaEmbeddingModel converts text segments into vector arrays. ollamac java work
(For Windows, a graphical installer is available.)
OllamaAPI ollamaAPI = new OllamaAPI("http://localhost:11434"); ollamaAPI.setRequestTimeout(60); OllamaResult result = ollamaAPI.generate("llama3.1", "Tell me a joke.", false); System.out.println(result.getResponse()); Use code with caution. 4. Advanced "Ollama + Java" Workflows Request request = new Request
| Endpoint | Purpose | |-------------------------|-------------------------------------------------------------------------| | POST /api/generate | Generate a completion from a prompt. | | POST /api/chat | Multi‑turn conversation with system, user, and assistant roles. | | GET /api/tags | List models you have pulled. | | POST /api/embeddings | Get vector embeddings from a model (useful for Retrieval‑Augmented Generation). |
Java runs on industrial controllers. With OllamaC Java work, edge devices can run TinyLlama or Phi-3-mini to make local decisions (e.g., predictive maintenance) without internet connectivity. Advanced "Ollama + Java" Workflows | Endpoint |
public class Ollama4jChatExample public static void main(String[] args) throws Exception String host = "http://localhost:11434"; String model = "llama3"; OllamaAPI ollamaAPI = new OllamaAPI(host); ollamaAPI.setRequestTimeoutSeconds(60); // Set a timeout
@Service public class AIService private final ChatClient chatClient;
OllamaChatModel model = OllamaChatModel.builder() .baseUrl("http://localhost:11434") .modelName("qwen2.5:7b") .temperature(0.7) .build();