OpenAI Chat Completions 与 Spring AI

HTTP client
  -> POST /v1/chat/completions
  -> request JSON containing messages and options
  -> model inference
  <- response JSON containing choices and usage

POST /v1/chat/completions HTTP/1.1
Host: api.example.com
Authorization: Bearer ...
Content-Type: application/json

{
  "model": "gpt-4.1",
  "messages": [
    {
      "role": "system",
      "content": "Answer concisely."
    },
    {
      "role": "user",
      "content": "Explain optimistic locking."
    }
  ],
  "temperature": 0.3,
  "max_tokens": 1000,
  "stream": false
}

[
  {
    "role": "system",
    "content": "You are a support assistant."
  },
  {
    "role": "user",
    "content": "Where is order 42?"
  },
  {
    "role": "assistant",
    "content": "I need to look up that order."
  },
  {
    "role": "user",
    "content": "It belongs to account 7."
  }
]

load conversation history
  -> append current user message
  -> send all selected messages
  -> receive assistant message
  -> save new user and assistant messages

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1784778339,
  "model": "gpt-4.1",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Optimistic locking detects concurrent updates..."
      },
      "finish_reason": "stop",
      "logprobs": null
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 18,
    "total_tokens": 43
  }
}

{
  "model": "gpt-4.1",
  "messages": [
    {
      "role": "user",
      "content": "What is the status of order 42?"
    }
  ],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "find_order",
        "description": "Look up an order by ID",
        "parameters": {
          "type": "object",
          "properties": {
            "order_id": {
              "type": "string",
              "description": "Canonical order ID"
            }
          },
          "required": [
            "order_id"
          ]
        }
      }
    }
  ]
}

{
  "role": "assistant",
  "content": null,
  "tool_calls": [
    {
      "id": "call_123",
      "type": "function",
      "function": {
        "name": "find_order",
        "arguments": "{\"order_id\":\"42\"}"
      }
    }
  ]
}

{
  "role": "tool",
  "tool_call_id": "call_123",
  "content": "{\"status\":\"SHIPPED\"}"
}

model request with tool schemas
  <- assistant tool-call request
application executes tool
  -> model request with tool result
  <- final assistant answer

data: {"object":"chat.completion.chunk","choices":[{"delta":{"role":"assistant"}}]}

data: {"object":"chat.completion.chunk","choices":[{"delta":{"content":"Optimistic"}}]}

data: {"object":"chat.completion.chunk","choices":[{"delta":{"content":" locking"}}]}

data: [DONE]

ChatOptions options = OpenAiChatOptions.builder()
    .model("gpt-4.1")
    .temperature(0.3)
    .maxTokens(1000)
    .build();

Prompt prompt = new Prompt(
    List.of(
        new SystemMessage("Answer concisely."),
        new UserMessage("Explain optimistic locking.")
    ),
    options
);

ChatResponse response = chatModel.call(prompt);
AssistantMessage answer = response.getResult().getOutput();

ChatResponse response = chatClient.prompt()
    .system("Answer concisely.")
    .user("Explain optimistic locking.")
    .options(options)
    .call()
    .chatResponse();

Spring AI Prompt
  messages:
    SystemMessage
    UserMessage
    AssistantMessage
    ToolResponseMessage
  options:
    ChatOptions
       |
       v
OpenAI adapter
  OpenAI request DTOs
  role/content conversion
  option and tool-schema conversion
       |
       v
JSON serializer
       |
       v
POST /v1/chat/completions

HTTP response JSON
  -> OpenAI response DTOs
  -> AssistantMessage
  -> Generation
  -> ChatResponseMetadata and Usage
  -> ChatResponse

ChatMemory memory = MessageWindowChatMemory.builder()
    .maxMessages(20)
    .build();

ChatClient client = builder
    .defaultAdvisors(
        MessageChatMemoryAdvisor.builder(memory).build()
    )
    .build();

ChatResponse response = client.prompt()
    .user(question)
    .advisors(spec -> spec.param(
        ChatMemory.CONVERSATION_ID,
        conversationId
    ))
    .call()
    .chatResponse();

ChatMemory.get(conversationId)
  -> add historical messages to Prompt
  -> ChatModel.call(Prompt)
  -> ChatMemory.add(current user and assistant messages)

public class OrderTools {

    @Tool(description = "Look up an order by ID")
    public OrderStatus findOrder(
            @ToolParam(description = "Canonical order ID") String orderId) {
        return orderService.find(orderId);
    }
}

String answer = chatClient.prompt()
    .user("Where is order 42?")
    .tools(orderTools)
    .call()
    .content();