OpenAI 聊天

ChatResponse response = chatModel.call(
    new Prompt(
        "Explain quantum computing in simple terms.",
        OpenAiChatOptions.builder()
            .model("gpt-4o")
            .maxTokens(150)  // Use maxTokens for non-reasoning models
        .build()
    ));

ChatResponse response = chatModel.call(
    new Prompt(
        "Solve this complex math problem step by step: ...",
        OpenAiChatOptions.builder()
            .model("o1-preview")
            .maxCompletionTokens(1000)  // Use maxCompletionTokens for reasoning models
        .build()
    ));

// This will automatically clear maxTokens and use maxCompletionTokens
OpenAiChatOptions options = OpenAiChatOptions.builder()
    .maxTokens(100)           // Set first
    .maxCompletionTokens(200) // This clears maxTokens and logs a warning
    .build();

// Result: maxTokens = null, maxCompletionTokens = 200

String jsonSchema = """
        {
            "type": "object",
            "properties": {
                "steps": {
                    "type": "array",
                    "items": {
                        "type": "object",
                        "properties": {
                            "explanation": { "type": "string" },
                            "output": { "type": "string" }
                        },
                        "required": ["explanation", "output"],
                        "additionalProperties": false
                    }
                },
                "final_answer": { "type": "string" }
            },
            "required": ["steps", "final_answer"],
            "additionalProperties": false
        }
        """;

Prompt prompt = new Prompt("how can I solve 8x + 7 = -23",
        OpenAiChatOptions.builder()
            .model(ChatModel.GPT_4_O_MINI)
            .responseFormat(new ResponseFormat(ResponseFormat.Type.JSON_SCHEMA, this.jsonSchema))
            .build());

ChatResponse response = this.openAiChatModel.call(this.prompt);

spring.ai.openai.api-key=YOUR_API_KEY
spring.ai.openai.chat.options.model=gpt-4o-mini

spring.ai.openai.chat.options.response-format.type=JSON_SCHEMA
spring.ai.openai.chat.options.response-format.name=MySchemaName
spring.ai.openai.chat.options.response-format.schema={"type":"object","properties":{"steps":{"type":"array","items":{"type":"object","properties":{"explanation":{"type":"string"},"output":{"type":"string"}},"required":["explanation","output"],"additionalProperties":false}},"final_answer":{"type":"string"}},"required":["steps","final_answer"],"additionalProperties":false}
spring.ai.openai.chat.options.response-format.strict=true

// Configure to use DeepSeek R1 or vLLM with a reasoning model
ChatResponse response = chatModel.call(
    new Prompt("Which number is larger: 9.11 or 9.8?")
);

// Get the assistant message
AssistantMessage message = response.getResult().getOutput();

// Access the reasoning content from metadata
String reasoning = message.getMetadata().get("reasoningContent");
if (reasoning != null && !reasoning.isEmpty()) {
    System.out.println("Model's reasoning process:");
    System.out.println(reasoning);
}

// The final answer is in the regular content
System.out.println("\nFinal answer:");
System.out.println(message.getContent());

ChatClient chatClient = ChatClient.create(chatModel);

String result = chatClient.prompt()
    .user("Which number is larger: 9.11 or 9.8?")
    .call()
    .chatResponse()
    .getResult()
    .getOutput()
    .getContent();

// To access reasoning content with ChatClient, retrieve the full response
ChatResponse response = chatClient.prompt()
    .user("Which number is larger: 9.11 or 9.8?")
    .call()
    .chatResponse();

AssistantMessage message = response.getResult().getOutput();
String reasoning = message.getMetadata().get("reasoningContent");

Flux<ChatResponse> responseFlux = chatModel.stream(
    new Prompt("Solve this logic puzzle...")
);

StringBuilder reasoning = new StringBuilder();
StringBuilder answer = new StringBuilder();

responseFlux.subscribe(chunk -> {
    AssistantMessage message = chunk.getResult().getOutput();

    // Accumulate reasoning if present
    String reasoningChunk = message.getMetadata().get("reasoningContent");
    if (reasoningChunk != null) {
        reasoning.append(reasoningChunk);
    }

    // Accumulate the final answer
    if (message.getContent() != null) {
        answer.append(message.getContent());
    }
});

spring.ai.openai.api-key=${DEEPSEEK_API_KEY}
spring.ai.openai.base-url=https://api.deepseek.com
spring.ai.openai.chat.options.model=deepseek-reasoner

vllm serve deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B \
    --enable-reasoning \
    --reasoning-parser deepseek_r1

spring.ai.openai.base-url=http://localhost:8000/v1
spring.ai.openai.chat.options.model=deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B