阿里云百炼

https://help.aliyun.com/zh/model-studio/
Admin
阿里云百炼是一站式大模型开发与应用平台，集成了通义千问及主流第三方模型，为开发者提供兼容OpenAI的API和全链路模型服务，并支持可视化应用构建，快速创建智能体和AI应用。
Tokens:151,272
Snippets:890
Trust Score:10
Update:2 months ago
Show doc for...
Tokens:
Raw
### Install langchain_openai SDK

Source: https://help.aliyun.com/zh/model-studio/compatibility-of-openai-with-dashscope

Command to install the necessary SDK for integrating with DashScope via LangChain.

```bash
pip install langchain-openai
```

--------------------------------

### Install langchain_openai

Source: https://help.aliyun.com/zh/model-studio/compatibility-of-openai-with-dashscope

Install the required library to enable OpenAI-compatible SDK support.

```bash
pip install -U langchain_openai
```

--------------------------------

### Install OpenAI SDK for Node.js

Source: https://help.aliyun.com/zh/model-studio/first-api-call-to-qwen

Commands to install the OpenAI SDK using npm or yarn.

```bash
npm install --save openai
# 或者
yarn add openai
```

--------------------------------

### Start Recognition Dialog

Source: https://help.aliyun.com/zh/model-studio/android-sdk-for-paraformer-real-time-service

Method signature for starting the recognition process, including an example of updating the API key.

```java
public synchronized int startDialog(VadMode vad_mode, String dialog_params)
```

```json
{
  "apikey": "st-****"
}
```

--------------------------------

### Check Java and Maven Versions

Source: https://help.aliyun.com/zh/model-studio/first-api-call-to-qwen

Verify that Java and Maven are correctly installed in the environment.

```bash
java -version
# （可选）如果使用maven管理和构建java项目，还需确保maven已正确安装到您的开发环境中
mvn --version
```

--------------------------------

### startDialog

Source: https://help.aliyun.com/zh/model-studio/android-sdk-for-paraformer-real-time-service

Starts the speech recognition process.

```APIDOC
## startDialog

### Method
`public synchronized int startDialog(VadMode vad_mode, String dialog_params)`

### Parameters
- **vad_mode** (VadMode) - VAD mode, fixed to VadMode.TYPE_P2T.
- **dialog_params** (String) - Optional JSON string to update API Key if expired.
```

--------------------------------

### Configure npm Registry

Source: https://help.aliyun.com/zh/model-studio/first-api-call-to-qwen

Use this command if the standard installation fails due to network restrictions.

```bash
npm config set registry https://registry.npmmirror.com/
```

--------------------------------

### SFT-ChatML Format Example

Source: https://help.aliyun.com/zh/model-studio/data-processing

The standard JSONL structure required for SFT-ChatML training datasets.

```json
{
  "messages": [
    {
      "role": "user",
      "content": "你经常锻炼身体吗？"
    },
    {
      "role": "assistant",
      "content": "经常锻炼身体。"
    }
  ]
}
```

--------------------------------

### Initialize SDK Instance

Source: https://help.aliyun.com/zh/model-studio/android-sdk-for-paraformer-real-time-service

Method signature for initializing the SDK. This call is blocking and should be performed on a non-UI thread.

```java
public synchronized int initialize(final INativeNuiCallback callback,
                                   String parameters,
                                   final Constants.LogLevel level,
                                   final boolean save_log)
```

--------------------------------

### Invoke Qwen API with Node.js

Source: https://help.aliyun.com/zh/model-studio/first-api-call-to-qwen

Example script to initialize the OpenAI client and send a chat completion request.

```javascript
import OpenAI from "openai";

try {
    const openai = new OpenAI(
        {
            // 若没有配置环境变量，请用阿里云百炼API Key将下行替换为: apiKey: "sk-xxx",
            apiKey: process.env.DASHSCOPE_API_KEY,
            // 以下为华北2（北京）地域的URL，各地域的URL不同。调用时请将{WorkspaceId}替换为真实的业务空间ID。
            baseURL: "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1"
        }
    );
    const completion = await openai.chat.completions.create({
        model: "qwen-plus",  //模型列表: https://help.aliyun.com/model-studio/getting-started/models
        messages: [
            { role: "system", content: "You are a helpful assistant." },
            { role: "user", content: "你是谁？" }
        ],
    });
    console.log(completion.choices[0].message.content);
} catch (error) {
    console.log(`错误信息：${error}`);
    console.log("请参考文档：https://help.aliyun.com/model-studio/developer-reference/error-code");
}
```

--------------------------------

### Data Augmentation Output Example

Source: https://help.aliyun.com/zh/model-studio/data-processing

Example of an augmented data entry containing a system-generated foreignKey.

```json
{
  "messages": [
    {
      "role": "user",
      "content": "你喜欢阅读哪种类型的书籍？"
    },
    {
      "role": "assistant",
      "content": "我喜欢阅读科幻类和历史类的书籍。"
    }
  ],
  "foreignKey": "8ba0304e2452476d89ed6a60c4xxxxxx"
}
```

--------------------------------

### SDK初始化与连接参数配置

Source: https://help.aliyun.com/zh/model-studio/android-sdk-for-paraformer-real-time-service

通过initialize接口传入JSON格式的连接与控制参数，配置服务地址、API Key及运行模式。

```APIDOC
## SDK 初始化参数配置

### Description
初始化SDK时，通过传入JSON字符串配置连接与控制参数。

### Parameters
- **url** (String) - Required - 服务地址，固定为 wss://dashscope.aliyuncs.com/api-ws/v1/inference
- **apikey** (String) - Required - API Key
- **service_mode** (String) - Required - 运行模式，实时语音识别固定为 "1"
- **device_id** (String) - Required - 终端用户唯一标识符
- **debug_path** (String) - Optional - 日志文件存储路径
- **save_wav** (String) - Optional - 是否保存调试音频文件，默认 "false"
- **max_log_file_size** (int) - Optional - 日志文件最大字节数，默认 104857600
- **log_track_level** (int) - Optional - 日志过滤级别，默认 2

### Request Example
{
    "url": "wss://dashscope.aliyuncs.com/api-ws/v1/inference",
    "apikey": "st-****",
    "device_id": "my_device_id",
    "service_mode": "1"
}
```

--------------------------------

### Model Output Example

Source: https://help.aliyun.com/zh/model-studio/deep-thinking

Example of the console output generated by the deep thinking model, showing the reasoning process followed by the final response.

```text
====================思考过程====================
好的，用户问“你是谁？”，我需要根据之前的设定来回答。首先，我的角色是千问，阿里巴巴集团旗下的超大规模语言模型。要保持口语化，简洁易懂。

用户可能刚接触我，或者想确认我的身份。应该先直接回答我是谁，然后简要说明我的功能和用途，比如回答问题、创作文字、编程等。还要提到支持多语言，这样用户知道我可以处理不同语言的需求。

另外，根据指导方针，要保持拟人性，所以语气要友好，可能用表情符号增加亲切感。同时，可能需要引导用户进一步提问或使用我的功能，比如问他们需要什么帮助。

需要注意不要使用复杂术语，避免冗长。检查是否有遗漏的关键点，比如多语言支持和具体能力。确保回答符合所有要求，包括口语化和简洁。
====================完整回复====================
你好！我是千问，阿里巴巴集团旗下的超大规模语言模型。我能够回答问题、创作文字，比如写故事、写公文、写邮件、写剧本、逻辑推理、编程等，还能表达观点，玩游戏等。我熟练掌握多种语言，包括但不限于中文、英文、德语、法语、西班牙语等。有什么需要我帮忙的吗？
```

--------------------------------

### Initialize Anthropic Client

Source: https://help.aliyun.com/zh/model-studio/anthropic-api-messages

Basic setup for the Anthropic Python client with API key and base URL configuration.

```python
import anthropic
import os

client = anthropic.Anthropic(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/apps/anthropic",
)
```

--------------------------------

### Model Response Output Example

Source: https://help.aliyun.com/zh/model-studio/deep-thinking

Example of the structured output received when deep thinking is enabled, showing separated reasoning and final answer content.

```text
====================思考过程====================

嗯，用户问“你是谁？”，我需要先确定他们想知道什么。可能他们第一次接触我，或者想确认我的身份。首先，我应该介绍自己的名字，千问，然后说明我是通义实验室研发的超大规模语言模型。接下来，可能需要解释我的功能，比如回答问题、创作文字、编程等，这样用户能了解我的用途。还要提到我支持多种语言，这样国际用户也能知道他们可以用不同语言交流。最后，保持友好，邀请他们提问，这样能促进进一步的互动。要注意用简洁易懂的语言，避免技术术语太多，让用户容易理解。可能用户有更深层的需求，比如测试我的能力，或者寻找帮助，所以提供具体的例子会更好，比如写故事、写公文、写邮件等。还要确保回答结构清晰，分点说明功能，但可能不需要用项目符号，而是自然过渡。另外，要强调我是AI助手，没有个人意识，所有回答都基于训练数据，这样避免误解。可能需要检查有没有遗漏的重要信息，比如多模态能力，或者最新的更新，但根据之前的回复，可能不需要太深入。总之，回答要全面但简洁，友好且有帮助，让用户感到被理解和支持。
====================完整回复====================

我是千问，阿里巴巴集团旗下的通义实验室自主研发的超大规模语言模型。我可以帮助你：

1. **回答问题**：无论是学术问题、常识问题还是专业领域问题，我都可以尝试为你解答。
2. **创作文字**：写故事、写公文、写邮件、写剧本等，我都可以帮你完成。
3. **逻辑推理**：我可以帮助你进行逻辑推理和解决问题。
4. **编程**：我可以理解并生成多种编程语言的代码。
5. **多语言支持**：我支持多种语言，包括但不限于中文、英文、德语、法语、西班牙语等。

如果你有任何问题或需要帮助，随时告诉我！
====================Token 消耗====================

{"input_tokens": 11, "output_tokens": 405, "total_tokens": 416, "output_tokens_details": {"reasoning_tokens": 256}, "prompt_tokens_details": {"cached_tokens": 0}}
```

--------------------------------

### 检查Node.js环境

Source: https://help.aliyun.com/zh/model-studio/first-api-call-to-qwen

验证Node.js和npm的安装版本。

```bash
node -v
npm -v
```

--------------------------------

### Prepare JSONL Input File for Multimodal Models

Source: https://help.aliyun.com/zh/model-studio/batch-interfaces-compatible-with-openai

Example content for a JSONL file supporting image URL and Base64 encoded inputs for multimodal models.

```json
{"custom_id":"image-url","method":"POST","url":"/v1/chat/completions","body":{"model":"qwen-vl-plus","messages":[{"role":"user","content":[{"type":"image_url","image_url":{"url":"https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"}},{"type":"text","text":"请描述这张图片"}]}]}}
{"custom_id":"image-base64","method":"POST","url":"/v1/chat/completions","body":{"model":"qwen-vl-plus","messages":[{"role":"user","content":[{"type":"image_url","image_url":{"url":"data:image/jpeg;base64,/9j/4AAQSkZJRgABAQEA8ADwAAD..."}},{"type":"text","text":"请描述这张图片"}]}]}}
```

--------------------------------

### GET /api/v1/tasks/{task_id}

Source: https://help.aliyun.com/zh/model-studio/first-call-to-image-and-video-api

根据任务 ID 查询生成任务的状态及结果。

```APIDOC
## GET /api/v1/tasks/{task_id}

### Description
使用 task_id 通过轮询方式查询任务状态，直到任务完成并获取最终的图像或视频 URL。

### Method
GET

### Endpoint
https://dashscope.aliyuncs.com/api/v1/tasks/{task_id}

### Parameters
#### Path Parameters
- **task_id** (string) - Required - 任务唯一标识

### Response
#### Success Response (200)
- **results** (array) - 包含生成结果的数组，包含 url

#### Response Example
{
    "results": [
        {
            "orig_prompt": "一间有着精致窗户的花店，漂亮的木质门，摆放着花朵",
            "actual_prompt": "...",
            "url": "https://dashscope-result-wlcb.oss-cn-wulanchabu.aliyuncs.com/..."
        }
    ]
}
```

--------------------------------

### Error Response Example

Source: https://help.aliyun.com/zh/model-studio/compatibility-of-openai-with-dashscope

The structure of an error response when a request fails.

```json
{
    "error": {
        "message": "Incorrect API key provided. ",
        "type": "invalid_request_error",
        "param": null,
        "code": "invalid_api_key"
    }
}
```

--------------------------------

### Streaming Response Example

Source: https://help.aliyun.com/zh/model-studio/compatibility-of-openai-with-dashscope

The format of the server-sent events during a streaming request.

```text
data: {"choices":[{"delta":{"content":"","role":"assistant"},"index":0,"logprobs":null,"finish_reason":null}],"object":"chat.completion.chunk","usage":null,"created":1715931028,"system_fingerprint":null,"model":"qwen-plus","id":"chatcmpl-3bb05cf5cd819fbca5f0b8d67a025022"}

data: {"choices":[{"finish_reason":null,"delta":{"content":"我是"},"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1715931028,"system_fingerprint":null,"model":"qwen-plus","id":"chatcmpl-3bb05cf5cd819fbca5f0b8d67a025022"}

data: {"choices":[{"delta":{"content":"来自"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1715931028,"system_fingerprint":null,"model":"qwen-plus","id":"chatcmpl-3bb05cf5cd819fbca5f0b8d67a025022"}

data: {"choices":[{"delta":{"content":"阿里"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1715931028,"system_fingerprint":null,"model":"qwen-plus","id":"chatcmpl-3bb05cf5cd819fbca5f0b8d67a025022"}

data: {"choices":[{"delta":{"content":"云的大规模语言模型"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1715931028,"system_fingerprint":null,"model":"qwen-plus","id":"chatcmpl-3bb05cf5cd819fbca5f0b8d67a025022"}

data: {"choices":[{"delta":{"content":"，我叫千问。"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1715931028,"system_fingerprint":null,"model":"qwen-plus","id":"chatcmpl-3bb05cf5cd819fbca5f0b8d67a025022"}

data: {"choices":[{"delta":{"content":""},"finish_reason":"stop","index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1715931028,"system_fingerprint":null,"model":"qwen-plus","id":"chatcmpl-3bb05cf5cd819fbca5f0b8d67a025022"}

data: [DONE]
```

--------------------------------

### Generate Music with Lyrics in Java

Source: https://help.aliyun.com/zh/model-studio/fun-music

Demonstrates how to send a POST request to the music generation endpoint with lyrics and gender parameters.

```java
import java.io.*;
import java.net.HttpURLConnection;
import java.net.URL;

public class FunMusicLyricsDemo {
    public static void main(String[] args) throws Exception {
        String apiKey = System.getenv("DASHSCOPE_API_KEY");
        String endpoint = "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/audio/music/generation";

        HttpURLConnection conn = (HttpURLConnection) new URL(endpoint).openConnection();
        conn.setRequestMethod("POST");
        conn.setRequestProperty("Authorization", "Bearer " + apiKey);
        conn.setRequestProperty("Content-Type", "application/json");
        conn.setDoOutput(true);

        String lyrics = "[verse]\n清晨的阳光穿过窗帘,\n"
            + "咖啡的香气弥漫房间.\n"
            + "翻开昨天未读完的书,\n"
            + "时光就这样悄悄流转.\n\n"
            + "[chorus]\n慢慢来不着急,\n"
            + "生活本该如此惬意.\n"
            + "把烦恼都丢进风里,\n"
            + "拥抱每一个晴天雨季.";

        String jsonBody = "{\"model\":\"fun-music-v1\","
            + "\"input\":{\"lyrics\":\"" + lyrics + "\","
            + "\"gender\":\"female\"}}";

        try (OutputStream os = conn.getOutputStream()) {
            os.write(jsonBody.getBytes("UTF-8"));
        }

        try (BufferedReader reader = new BufferedReader(
                new InputStreamReader(conn.getInputStream(), "UTF-8"))) {
            StringBuilder sb = new StringBuilder();
            String line;
            while ((line = reader.readLine()) != null) {
                sb.append(line);
            }
            System.out.println(sb.toString());
        }
    }
}
```

--------------------------------

### Get SDK Version

Source: https://help.aliyun.com/zh/model-studio/android-sdk-for-paraformer-real-time-service

Retrieves the current version information of the SDK.

```java
public synchronized String GetVersion();
```

--------------------------------

### Prepare JSONL Input File for Test Model

Source: https://help.aliyun.com/zh/model-studio/batch-interfaces-compatible-with-openai

Example content for a JSONL file using the batch-test-model for validation.

```json
{"custom_id":"1","method":"POST","url":"/v1/chat/ds-test","body":{"model":"batch-test-model","messages":[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"你好！有什么可以帮助你的吗？"}]}}
{"custom_id":"2","method":"POST","url":"/v1/chat/ds-test","body":{"model":"batch-test-model","messages":[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is 2+2?"}]}}
```

--------------------------------

### 调用深度思考模型（DashScope 接口）

Source: https://help.aliyun.com/zh/model-studio/deep-thinking

使用 DashScope SDK 调用模型，直接设置 enable_thinking 参数。推荐使用流式调用以实时查看思考过程。

```python
# 导入依赖...

response = Generation.call(
    # 若没有配置环境变量，请用阿里云百炼API Key将下行替换为：api_key = "sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # 可按需更换为其它深度思考模型
    model="qwen-plus",
    messages=messages,
    result_format="message",
    enable_thinking=True,
    stream=True,
    incremental_output=True
)
```

--------------------------------

### 查询任务结果

Source: https://help.aliyun.com/zh/model-studio/first-call-to-image-and-video-api

使用 GET 请求根据 task_id 查询任务状态。建议每隔 3-5 秒轮询一次，直到任务状态不再为 RUNNING。

```bash
curl -X GET https://dashscope.aliyuncs.com/api/v1/tasks/{task_id} \
--header "Authorization: Bearer $DASHSCOPE_API_KEY"
```

```json
curl -X GET https://dashscope.aliyuncs.com/api/v1/tasks/2de3f7e1-52ce-4cf4-a466-f2d3f8061c43 \
--header "Authorization: Bearer $DASHSCOPE_API_KEY"
{"request_id":"24143559-9964-4898-8f9c-d968bba182b9","output":{"task_id":"2de3f7e1-52ce-4cf4-a466-f2d3f8061c43","task_status":"SUCCEEDED","submit_time":"2025-12-03 10:19:18.293","scheduled_time":"2025-12-03 10:19:18.320","end_time":"2025-12-03 10:19:31.890","results":[{"orig_prompt":"一间有着精致窗户的花店，漂亮的木质门，摆放着花朵","actual_prompt":"一间温馨雅致的花店，外墙装饰着精致的雕花窗户，窗框为深褐色木质结构，玻璃洁净透亮，透出店内柔和的光线。花店正门是一扇漂亮的实木门，表面保留天然木纹，配以黄铜门把手和复古门牌，散发出浓厚的手工艺气息。门前台阶两侧和店内窗台、门口区域错落有致地摆放着各式鲜花——有盛开的玫瑰、淡雅的绣球、清新的雏菊和翠绿的尤加利叶，色彩丰富而和谐。背景为宁静的欧洲小镇街景，石板路与爬满藤蔓的邻墙烘托出浪漫氛围。整体画面采用写实摄影风格，光线柔和自然，突出木质纹理与花卉细节。","url":"https://dashscope-result-wlcb.oss-cn-wulanchabu.aliyuncs.com/1d/59/20251203/7a2bee47/2de3f7e1-52ce-4cf4-a466-f2d3f8061c43.png?Expires=1764814771&OSSAccessKeyId=xxx"}],"task_metrics":{"TOTAL":1,"FAILED":0,"SUCCEEDED":1}},"usage":{"image_count":1}}
```

--------------------------------

### Tool Use with Anthropic API

Source: https://help.aliyun.com/zh/model-studio/anthropic-api-messages

Examples for defining and using tools with the Anthropic API.

```python
import anthropic
import os

client = anthropic.Anthropic(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/apps/anthropic",
)

tools = [
    {
        "name": "get_weather",
        "description": "获取指定城市的天气信息",
        "input_schema": {
            "type": "object",
            "properties": {
                "city": {
                    "type": "string",
                    "description": "城市名称"
                }
            },
            "required": ["city"]
        }
    }
]

message = client.messages.create(
    model="qwen3.7-plus",
    max_tokens=1024,
    tools=tools,
    messages=[
        {
            "role": "user",
            "content": "杭州今天天气怎么样？"
        }
    ]
)

print(message.content)
```

```typescript
import Anthropic from "@anthropic-ai/sdk";

async function main() {
  const anthropic = new Anthropic({
    apiKey: process.env.DASHSCOPE_API_KEY,
    baseURL: "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/apps/anthropic",
  });

  const message = await anthropic.messages.create({
    model: "qwen3.7-plus",
    max_tokens: 1024,
    tools: [
      {
        name: "get_weather",
        description: "获取指定城市的天气信息",
        input_schema: {
          type: "object",
          properties: {
            city: { type: "string", description: "城市名称" }
          },
          required: ["city"],
        },
      },
    ],
    messages: [{
      role: "user",
      content: "杭州今天天气怎么样？"
    }],
  });

  console.log(JSON.stringify(message.content, null, 2));
}
```

--------------------------------

### Chat Completion Response Example

Source: https://help.aliyun.com/zh/model-studio/compatibility-of-openai-with-dashscope

The standard JSON response structure returned by the API.

```json
{
    "choices": [
        {
            "message": {
                "role": "assistant",
                "content": "我是来自阿里云的大规模语言模型，我叫千问。"
            },
            "finish_reason": "stop",
            "index": 0,
            "logprobs": null
        }
    ],
    "object": "chat.completion",
    "usage": {
        "prompt_tokens": 11,
        "completion_tokens": 16,
        "total_tokens": 27
    },
    "created": 1715252778,
    "system_fingerprint": "",
    "model": "qwen-plus",
    "id": "chatcmpl-xxx"
}
```

--------------------------------

### initialize

Source: https://help.aliyun.com/zh/model-studio/android-sdk-for-paraformer-real-time-service

Initializes the speech recognition SDK instance. This method is blocking and should be called on a non-UI thread.

```APIDOC
## initialize

### Method
`public synchronized int initialize(final INativeNuiCallback callback, String parameters, final Constants.LogLevel level, final boolean save_log)`

### Parameters
- **callback** (INativeNuiCallback) - Implementation of the event and data callback interface.
- **parameters** (String) - JSON string containing authentication, connection, and debugging parameters.
- **level** (Constants.LogLevel) - Log level for the SDK.
- **save_log** (boolean) - Whether to save local logs.
```

--------------------------------

### 使用OpenAI SDK调用模型

Source: https://help.aliyun.com/zh/model-studio/first-api-call-to-qwen

通过OpenAI兼容接口调用Qwen模型。

```python
import os
from openai import OpenAI

try:
    client = OpenAI(
        # 若没有配置环境变量，请用阿里云百炼API Key将下行替换为: api_key="sk-xxx",
        api_key=os.getenv("DASHSCOPE_API_KEY"),
        # 以下为华北2（北京）地域的URL，各地域的URL不同。调用时请将{WorkspaceId}替换为真实的业务空间ID。
        base_url="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
    )

    completion = client.chat.completions.create(
        model="qwen-plus",  # 模型列表: https://help.aliyun.com/model-studio/getting-started/models
        messages=[
            {'role': 'system', 'content': 'You are a helpful assistant.'},
            {'role': 'user', 'content': '你是谁？'}
        ]
    )
    print(completion.choices[0].message.content)
except Exception as e:
    print(f"错误信息：{e}")
    print("请参考文档：https://help.aliyun.com/model-studio/developer-reference/error-code")
```

--------------------------------

### Prompt Configuration Template

Source: https://help.aliyun.com/zh/model-studio/data-processing

Template structure for defining LLM training tasks including Question, Context, and Answer fields.

```text
一个完整的大语言模型的训练示例可以定义为以下的结构：
Question: 描述期待大语言模型要做的任务。
Context: 描述期待大语言模型要分析的内容。
Answer: 期待大语言模型输出的正确结果。

给定的Question: 
${Question}
给定的<Context, Answer>数据对：
Context: ${Context}
Answer: ${Answer}

【注意事项】
1. 为了保证你编写的答案的准确性，你需要先根据你对给定Question和Answer的理解来构造一个新的Answer。
2. 你编写的新Answer要和给定的Question匹配。
3. 你编写的新Answer格式要和给定的Answer匹配。
4. 根据你编写的Answer来构造蕴含这个Answer的Context。
5. 你编写的Context长度要和示例Context长度相当。
6. 把你编写的Answer和Context组合在一个JSON中，具体格式为${Format_Constraint}

请首先分析给定的<Question>和<Context, Answer>数据的特点，然后构造新的<Answer, Context>，满足【注意事项】中的所有要求，你可以参考这个执行步骤：
1. 首先分析给定的<Question>和<Context, Answer>数据的特点。
2. 理解【注意事项】中的每一条内容。
3. 构造新的Answer和Context，按照指定格式输出。
按照参考步骤，一步一步地执行给定的任务。
```

--------------------------------

### Set Recognition Parameters

Source: https://help.aliyun.com/zh/model-studio/android-sdk-for-paraformer-real-time-service

Method signature for setting recognition parameters before starting the dialog.

```java
public synchronized int setParams(String params)
```

--------------------------------

### GET /compatible-mode/v1/batches

Source: https://help.aliyun.com/zh/model-studio/batch-interfaces-compatible-with-openai

Retrieves a list of Batch tasks with optional filtering and pagination parameters.

```APIDOC
## GET /compatible-mode/v1/batches

### Description
Retrieves a list of Batch tasks. Supports filtering by status, file IDs, name, and creation time, as well as pagination.

### Method
GET

### Endpoint
/compatible-mode/v1/batches

### Parameters
#### Query Parameters
- **after** (String) - Optional - Cursor for pagination, the ID of the last task from the previous page.
- **limit** (Integer) - Optional - Number of tasks to return per page, range [1, 100], default 20.
- **ds_name** (String) - Optional - Fuzzy match by task name.
- **input_file_ids** (String) - Optional - Filter by file IDs, comma-separated, max 20.
- **status** (String) - Optional - Filter by task status, comma-separated.
- **create_after** (String) - Optional - Filter tasks created after this time, format: yyyyMMddHHmmss.
- **create_before** (String) - Optional - Filter tasks created before this time, format: yyyyMMddHHmmss.

### Response
#### Success Response (200)
- **object** (String) - Type, fixed value 'list'.
- **data** (Array) - List of Batch task objects.
- **first_id** (String) - ID of the first task on the current page.
- **last_id** (String) - ID of the last task on the current page.
- **has_more** (Boolean) - Whether there is a next page.
```

--------------------------------

### OpenCode 运行命令

Source: https://help.aliyun.com/zh/model-studio/explicit-cache-guide

设置API Key并启动OpenCode。

```bash
export DASHSCOPE_API_KEY=sk-xxxxx
opencode run -m "bailian/qwen3.7-max" "..."
```
Tokens:
Raw