<\/div> <\/div><\/p>\n
import com.openai.OpenAI;\nimport com.openai.OpenAIClient;\nimport com.openai.api.completion.*;\nimport com.openai.api.chat.*;\nimport com.openai.api.assistants.*;\nimport com.openai.api.threads.*;\n\nimport java.util.List;\n\n\/**\n * Demonstrates usage of the Java OpenAI API Client.\n * \n * This class showcases how to perform three types of interactions with OpenAI's services:\n * 1. Simple text completion using the Completion API.\n * 2. Conversational interaction using Chat Completion.\n * 3. Stateful assistant interaction using Threads and the Assistants API.\n *\/\npublic class Main {\n\n \/**\n * The entry point of the Java program.\n *\n * @param args command-line arguments (not used)\n * @throws InterruptedException if the thread waiting on assistant completion is interrupted\n *\/\n public static void main(String[] args) throws InterruptedException {\n \/\/ Replace with your actual OpenAI API key\n String apiKey = \"your-api-key-here\";\n\n \/\/ Initialize the OpenAI client with the API key\n OpenAIClient client = OpenAI.builder()\n .apiKey(apiKey)\n .build();\n\n try {\n \/\/ -------------------- 1. Simple Completion --------------------\n \/\/ Create a completion request with a static prompt using the \"text-davinci-003\" model\n CompletionRequest simpleRequest = CompletionRequest.builder()\n .model(\"text-davinci-003\")\n .prompt(\"What is the capital of France?\")\n .maxTokens(10) \/\/ Limit the number of tokens in the response\n .build();\n\n \/\/ Send the request and get the response\n CompletionResponse simpleResponse = client.createCompletion(simpleRequest);\n System.out.println(\"Simple Completion Output:\");\n System.out.println(simpleResponse.getChoices().get(0).getText().trim());\n\n \/\/ -------------------- 2. Conversational Chat Completion --------------------\n \/\/ Create a user message for chat-based conversation\n ChatMessage userMsg = ChatMessage.userMessage(\"Who won the FIFA World Cup in 2018?\");\n ChatCompletionRequest chatRequest = ChatCompletionRequest.builder()\n .model(\"gpt-3.5-turbo\")\n .messages(List.of(userMsg)) \/\/ Pass the message as a list\n .build();\n\n \/\/ Send the chat request and retrieve the response\n ChatCompletionResponse chatResponse = client.createChatCompletion(chatRequest);\n System.out.println(\"\\nChat Completion Output:\");\n System.out.println(chatResponse.getChoices().get(0).getMessage().getContent());\n\n \/\/ -------------------- 3. Assistant-Based Interaction --------------------\n \/\/ Create an Assistant using the GPT-4 model with tutoring instructions\n Assistant assistant = client.createAssistant(\n AssistantRequest.builder()\n .model(\"gpt-4\")\n .name(\"TutorBot\")\n .instructions(\"You are a math tutor. Explain answers in simple terms.\")\n .build()\n );\n\n \/\/ Create a new thread for the assistant interaction\n Thread thread = client.createThread(CreateThreadRequest.builder().build());\n\n \/\/ Add a user message to the thread asking a math question\n client.addMessage(thread.getId(), MessageRequest.builder()\n .role(\"user\")\n .content(\"What is 7 multiplied by 8?\")\n .build()\n );\n\n \/\/ Create a run that connects the thread with the assistant\n Run run = client.createRun(thread.getId(), RunRequest.builder()\n .assistantId(assistant.getId())\n .build()\n );\n\n \/\/ Wait until the assistant completes its response generation\n System.out.println(\"\\nWaiting for assistant response...\");\n Run finalRun = client.waitForRunCompletion(thread.getId(), run.getId());\n\n \/\/ Retrieve all messages from the conversation thread\n List<Message> messages = client.listMessages(thread.getId());\n\n \/\/ Display the full assistant conversation\n System.out.println(\"\\nAssistant Conversation:\");\n for (Message msg : messages) {\n System.out.println(msg.getRole() + \": \" + msg.getContent());\n }\n\n } catch (Exception e) {\n \/\/ Handle any runtime errors (e.g., network issues, bad requests)\n e.printStackTrace();\n }\n }\n}\n<\/pre>\n2.2.1 Code Explanation<\/h4>\n
This Java program demonstrates how to work with the OpenAI API through the official Java OpenAI API client. It is structured into three distinct sections, each showcasing a different interaction type. The program begins by importing necessary classes and initializing an OpenAIClient<\/code> using an API key.<\/p>\nIn the first section, a basic text completion is executed using the text-davinci-003<\/code> model. The prompt “What is the capital of France?” is sent, and a short response is generated with a maximum of 10 tokens. This demonstrates the simplest usage of the completion API, ideal for short factual answers.<\/p>\nIn the second section, the code performs a chat-based interaction using the gpt-3.5-turbo<\/code> model. Here, the user sends a natural language message about the 2018 FIFA World Cup, and the model responds in a conversational tone. This demonstrates how the chat API handles multi-turn conversations.<\/p>\nThe third section showcases an advanced use case with the Assistants API. It creates an assistant called “TutorBot” using the gpt-4<\/code> model and instructs it to explain math problems in simple terms. A new thread is created to manage the conversation, a message is added from the user, and a run is initiated to let the assistant respond contextually. The assistant processes the input asynchronously, and once completed, all messages in the conversation thread are retrieved and printed. This pattern is useful for scenarios where multi-step interactions or persistent context are needed.<\/p>\nException handling is included to catch and print any runtime errors, ensuring the application fails gracefully if any issues arise with the API or network.<\/p>\n
2.2.2 Code Output<\/h4>\n
Upon successful execution, the program will output responses from each interaction, giving a clear understanding of how each part of the API behaves.<\/p>\n
Simple Completion Output:\nParis\n\nChat Completion Output:\nFrance won the FIFA World Cup in 2018.\n\nWaiting for assistant response...\n\nAssistant Conversation:\nuser: What is 7 multiplied by 8?\nassistant: 7 multiplied by 8 is 56. This is because 7 added to itself 8 times equals 56.\n<\/pre>\n