# 多轮对话 chat.completions接口是无状态的，不会存储历史对话。为了实现多轮对话，模型需要在每次请求时，将历史信息都放在messages中，并通过role字段设置，让模型了解之前不同角色的不同对话内容（系统消息、用户消息、模型回复的消息），以便进行主题相关的延续性对话。 表1单轮对话与多轮对话的messages对比 | 单轮对话 | 多轮对话 | |:---|:---| | ``` "messages": [ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "9.11和9.8哪个大？"} ] ``` | ``` "messages": [ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "9.11和9.8哪个大？"}, {"role": "assistant", "content": "9.8更大"}, {"role": "user", "content": "它们相加等于多少？"} ] ``` | #### API说明 模型调用的完整参数列表请见[对话Chat/Post](https://support.huaweicloud.com/model-call-maas/model-call-018.html)。 #### 前提条件 - 已在"模型推理 \> 在线推理 \> 预置服务"页签开通预置服务。详情请见[开通MaaS预置服务](https://support.huaweicloud.com/model-call-maas/model-call-052.html)。 - （可选）如果需要控制服务调用流量，可提前创建自定义接入点，详情请参见[创建自定义接入点](https://support.huaweicloud.com/model-call-maas/model-call-048.html#ZH-CN_TOPIC_0000002549717747__zh-cn_topic_0000002397381901_section446813817237)。 - 已获取API Key。详情请见[在MaaS管理API Key](https://support.huaweicloud.com/model-call-maas/model-call-049.html)。 - 已获取模型服务的model参数值。支持的模型信息和接口详情请见[对话Chat/Post](https://support.huaweicloud.com/model-call-maas/model-call-018.html)。 #### 快速入门 以下为多轮对话的示例代码，可通过model参数替换模型，model参数详情请参见[文本生成](https://support.huaweicloud.com/model-list-maas/model_list_0001.html#section1)。 ![](https://support.huaweicloud.com/model-call-maas/public_sys-resources/notice_3.0-zh-cn.png) **思考模式**下，reasoning_content是模型的思考内容，多轮对话场景下，不应作为输入。如果在输入的messages数组中包含此字段，将被忽略，不作为模型输入。进行多轮对话时，应只保留上一轮模型返回的role和content字段。 - [Python] ``` import requests import json if __name__ == '__main__': url = "https://api.modelarts-maas.com/v2/chat/completions" # API地址 api_key = "MAAS_API_KEY" # 把MAAS_API_KEY替换成已获取的API Key # Send request. headers = { 'Content-Type': 'application/json', 'Authorization': f'Bearer {api_key}' } data = { "model": "glm-5.2", # model参数 "messages": [ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "9.11和9.8哪个大？"}, {"role": "assistant", "content": "9.8更大"}, {"role": "user", "content": "它们相加等于多少？"} ] } response = requests.post(url, headers=headers, data=json.dumps(data), verify=False) # Print result. print(response.status_code) print(response.text) ``` 模型返回的content： ``` 它们相加等于18.91。 ``` - [Curl] ``` curl -X POST "https://api.modelarts-maas.com/v2/chat/completions" \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $MAAS_API_KEY" \ -d '{ "model": "glm-5.2", "messages": [ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "9.11和9.8哪个大？"}, {"role": "assistant", "content": "9.8更大"}, {"role": "user", "content": "它们相加等于多少？"} ] }' ``` 模型返回的content： ``` 它们相加等于18.91。 ``` - [Java] 建议JDK版本为15+。 ``` import java.net.URI; import java.net.http.HttpClient; import java.net.http.HttpRequest; import java.net.http.HttpResponse; import java.time.Duration; public class ChatCompletionsExample { public static void main(String[] args) { // 接口地址 String apiUrl = "https://api.modelarts-maas.com/v2/chat/completions"; // 把MAAS_API_KEY替换成已获取的API Key String apiKey = "MAAS_API_KEY"; // 替换为你要调用的模型名称，例如 "glm-5.2" 等 String modelName = "glm-5.2"; // 构造请求体 String requestBody = String.format( """ { "model": "%s", "messages": [ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "9.11和9.8哪个大？"}, {"role": "assistant", "content": "9.8更大"}, {"role": "user", "content": "它们相加等于多少？"} ] }""", modelName); // 创建 HttpClient HttpClient client = HttpClient.newBuilder() .connectTimeout(Duration.ofSeconds(10)) .build(); // 创建请求 HttpRequest request = HttpRequest.newBuilder() .uri(URI.create(apiUrl)) .header("Content-Type", "application/json") .header("Authorization", "Bearer " + apiKey) .POST(HttpRequest.BodyPublishers.ofString(requestBody)) .build(); try { // 发送请求并打印结果 HttpResponse response = client.send( request, HttpResponse.BodyHandlers.ofString()); System.out.println("HTTP Status: " + response.statusCode()); System.out.println("Response Body:\n" + response.body()); } catch (Exception e) { e.printStackTrace(); } } } ``` 模型返回的content： ``` 它们相加等于18.91。 ``` #### 设置模型回答长度限制 多轮对话场景下，随着对话轮数的增加，每次调用消耗的Token数量也会增加，从而增加了使用成本。 这种情况下，可在请求时设置max_tokens字段明确限制模型生成的最大token数量，来限制模型回答长度。各模型的max_tokens取值可参考模型详情页的**最大输出长度**。 下面是设置模型回答长度限制的示例代码，可通过model参数替换模型，model参数详情请参见[文本生成](https://support.huaweicloud.com/model-list-maas/model_list_0001.html#section1)。 - [Python] ``` import requests import json if __name__ == '__main__': url = "https://api.modelarts-maas.com/v2/chat/completions" # API地址 api_key = "MAAS_API_KEY" # 把MAAS_API_KEY替换成已获取的API Key # Send request. headers = { 'Content-Type': 'application/json', 'Authorization': f'Bearer {api_key}' } data = { "model": "glm-5.2", # model参数 "messages": [ {"role": "system", "content": "You are a helpful assistant." }, {"role": "user","content": "你好" } ], "max_tokens": 1024 } response = requests.post(url, headers=headers, data=json.dumps(data), verify=False) # Print result. print(response.status_code) print(response.text) ``` - [Curl] ``` curl -X POST "https://api.modelarts-maas.com/v2/chat/completions" \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $MAAS_API_KEY" \ -d '{ "model": "glm-5.2", "messages": [ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "你好"} ], "max_tokens": 1024 }' ``` - [Java] 建议JDK版本为15+。 ``` import java.net.URI; import java.net.http.HttpClient; import java.net.http.HttpRequest; import java.net.http.HttpResponse; import java.time.Duration; public class ChatCompletionsExample { public static void main(String[] args) { // 接口地址 String apiUrl = "https://api.modelarts-maas.com/v2/chat/completions"; // 把MAAS_API_KEY替换成已获取的API Key String apiKey = "MAAS_API_KEY"; // 替换为你要调用的模型名称，例如 "glm-5.2" 等 String modelName = "glm-5.2"; // 构造请求体 String requestBody = String.format( """ { "model": "%s", "messages": [ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "你好"} ], "max_tokens": 1024 }""", modelName); // 创建 HttpClient HttpClient client = HttpClient.newBuilder() .connectTimeout(Duration.ofSeconds(10)) .build(); // 创建请求 HttpRequest request = HttpRequest.newBuilder() .uri(URI.create(apiUrl)) .header("Content-Type", "application/json") .header("Authorization", "Bearer " + apiKey) .POST(HttpRequest.BodyPublishers.ofString(requestBody)) .build(); try { // 发送请求并打印结果 HttpResponse response = client.send( request, HttpResponse.BodyHandlers.ofString()); System.out.println("HTTP Status: " + response.statusCode()); System.out.println("Response Body:\n" + response.body()); } catch (Exception e) { e.printStackTrace(); } } } ``` #### 错误码 模型调用过程中，如有报错，请参考[错误码](https://support.huaweicloud.com/model-call-maas/model-call-035.html)排查并处理。