数据挖掘（Qwen-Doc-Turbo）

文档内容上传方式选择

在选择文档内容上传方式时，请考虑以下因素：

1. 通过文件ID 上传

   • 推荐：适合需要频繁引用和管理的文档。可以减少文本输入错误，操作简便。

     模型支持以纯文本提取和结构化方式解析TXT、DOCX、DOC、PPTX、PPT、XLSX、XLS、MD文件。单个文件大小不可超过150MB，单个阿里云账号最多可上传 1 万个文件，总文件大小不得超过 100GB。当任一条件超出限制时，需删除部分文件或文件内容以满足要求后再尝试上传，详情请参见OpenAI文件接口兼容。

2. 通过纯文本上传

   • 适用场景：适合小规模文档或临时内容。如果文档较短且不需要长期存储，可以选择此方式。

请根据您的具体需求和文档特性选择最合适的上传方式。我们建议优先考虑 文件ID 上传，以获得最佳体验。

通过文件ID传入文档信息

您可以通过OpenAI兼容接口上传文档，并将返回的文件ID输入到System Message中，使得模型在回复时参考文档信息。

文件ID目前仅能用于Qwen-Long、Qwen-Doc-Turbo模型以及Batch接口调用。

Qwen-Doc-Turbo模型可以基于您上传的文档进行回复。此处以阿里云百炼系列手机产品介绍.docx作为示例文件。

1. 将文件通过OpenAI兼容接口上传到阿里云百炼平台，保存至平台安全存储空间后获取文件ID。有关文档上传接口的详细参数解释及调用方式，请参考API文档页面进行了解。

   Python

   import os
   from pathlib import Path
   from openai import OpenAI
   
   client = OpenAI(
       api_key=os.getenv("DASHSCOPE_API_KEY"),  # 如果您没有配置环境变量，请在此处替换您的API-KEY
       base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",  # 填写DashScope服务base_url
   )
   
   file_object = client.files.create(file=Path("阿里云百炼系列手机产品介绍.docx"), purpose="file-extract")
   print(file_object.id)

   Java

   import com.openai.client.OpenAIClient;
   import com.openai.client.okhttp.OpenAIOkHttpClient;
   import com.openai.models.*;
   
   import java.nio.file.Path;
   import java.nio.file.Paths;
   
   public class Main {
       public static void main(String[] args) {
           // 创建客户端，使用环境变量中的API密钥
           OpenAIClient client = OpenAIOkHttpClient.builder()
                   .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                   .baseUrl("https://dashscope.aliyuncs.com/compatible-mode/v1")
                   .build();
           // 设置文件路径,请根据实际需求修改路径与文件名
           Path filePath = Paths.get("src/main/java/org/example/阿里云百炼系列手机产品介绍.docx");
           // 创建文件上传参数
           FileCreateParams fileParams = FileCreateParams.builder()
                   .file(filePath)
                   .purpose(FilePurpose.of("file-extract"))
                   .build();
   
           // 上传文件打印fileid
           FileObject fileObject = client.files().create(fileParams);
           System.out.println(fileObject.id());
       }
   }

   curl

   curl --location --request POST 'https://dashscope.aliyuncs.com/compatible-mode/v1/files' \
     --header "Authorization: Bearer $DASHSCOPE_API_KEY" \
     --form 'file=@"阿里云百炼系列手机产品介绍.docx"' \
     --form 'purpose="file-extract"'

   运行以上代码，您可以得到本次上传文件对应的文件ID。

2. 将文件ID传入System Message中，并在User Message中输入问题。

3. Python

   import os
   from openai import OpenAI, BadRequestError
   
   client = OpenAI(
       api_key=os.getenv("DASHSCOPE_API_KEY"),
       base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
   )
   
   try:
       completion = client.chat.completions.create(
           model="qwen-doc-turbo",
           messages=[
               {'role': 'system', 'content': 'You are a helpful assistant.'},
               # 如果您没有配置环境变量，请在此处替换您的API-KEY
               {'role': 'system', 'content': 'fileid://file-fe-xxx'},
               {'role': 'user', 'content': '阿里云百炼都有那些手机?'}
           ],
           # 所有代码示例均采用流式输出，以清晰和直观地展示模型输出过程。如果您希望查看非流式输出的案例，请参见https://help.aliyun.com/zh/model-studio/text-generation
           stream=True,
           stream_options={"include_usage": True}
       )
   
       full_content = ""
       for chunk in completion:
           if chunk.choices and chunk.choices[0].delta.content:
               full_content += chunk.choices[0].delta.content
               print(chunk.model_dump())
       
       print(full_content)
   
   except BadRequestError as e:
       print(f"错误信息：{e}")
       print("请参考文档：https://help.aliyun.com/zh/model-studio/developer-reference/error-code")

   Java

   import com.openai.client.OpenAIClient;
   import com.openai.client.okhttp.OpenAIOkHttpClient;
   import com.openai.core.http.StreamResponse;
   import com.openai.models.*;
   
   public class Main {
       public static void main(String[] args) {
           // 创建客户端，使用环境变量中的API密钥
           OpenAIClient client = OpenAIOkHttpClient.builder()
                   .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                   ////请将 'file-fe-xxx'替换为您实际对话场景所使用的 fileid。
                   .baseUrl("https://dashscope.aliyuncs.com/compatible-mode/v1")
                   .build();
   
           ChatCompletionCreateParams chatParams = ChatCompletionCreateParams.builder()
                   .addSystemMessage("You are a helpful assistant.")
                   .addSystemMessage("fileid://file-fe-xxx")
                   .addUserMessage("阿里云百炼都有那些手机?")
                   .model("qwen-doc-turbo")
                   .build();
   
           try (StreamResponse<ChatCompletionChunk> streamResponse = client.chat().completions().createStreaming(chatParams)) {
               streamResponse.stream().forEach(chunk -> {
                   String content = chunk.choices().get(0).delta().content().orElse("");
                   if (!content.isEmpty()) {
                       System.out.print(content);
                   }
               });
           } catch (Exception e) {
               System.err.println("错误信息：" + e.getMessage());
           }
       }
   }

   curl

   curl --location 'https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions' \
   --header "Authorization: Bearer $DASHSCOPE_API_KEY" \
   --header "Content-Type: application/json" \
   --data '{
       "model": "qwen-doc-turbo",
       "messages": [
           {"role": "system","content": "You are a helpful assistant."},
           {"role": "system","content": "fileid://file-fe-xxx"},
           {"role": "user","content": "阿里云百炼都有那些手机?"}
       ],
       "stream": true,
       "stream_options": {
           "include_usage": true
       }
   }'

4. 通过配置stream及stream_options参数，Qwen-Doc-Turbo模型会流式输出回复，并在最后返回的对象中通过usage字段展示Token使用情况。

   Python

   {'id': 'chatcmpl-ddbb10e9-dba2-930e-9e5b-xxxxxxxxxxxx', 'choices': [{'delta': {'content': '这篇文章', 'function_call': None, 'refusal': None, 'role': None, 'tool_calls': None}, 'finish_reason': None, 'index': 0, 'logprobs': None}], 'created': 1753076578, 'model': 'qwen-doc-turbo', 'object': 'chat.completion.chunk', 'service_tier': None, 'system_fingerprint': None, 'usage': None}
   {'id': 'chatcmpl-ddbb10e9-dba2-930e-9e5b-xxxxxxxxxxxx', 'choices': [{'delta': {'content': '是', 'function_call': None, 'refusal': None, 'role': None, 'tool_calls': None}, 'finish_reason': None, 'index': 0, 'logprobs': None}], 'created': 1753076578, 'model': 'qwen-doc-turbo', 'object': 'chat.completion.chunk', 'service_tier': None, 'system_fingerprint': None, 'usage': None}
   ...
   {'id': 'chatcmpl-ddbb10e9-dba2-930e-9e5b-xxxxxxxxxxxx', 'choices': [{'delta': {'content': '方面的强大功能和', 'function_call': None, 'refusal': None, 'role': None, 'tool_calls': None}, 'finish_reason': None, 'index': 0, 'logprobs': None}], 'created': 1753076578, 'model': 'qwen-doc-turbo', 'object': 'chat.completion.chunk', 'service_tier': None, 'system_fingerprint': None, 'usage': None}
   {'id': 'chatcmpl-ddbb10e9-dba2-930e-9e5b-xxxxxxxxxxxx', 'choices': [{'delta': {'content': '高性价比，吸引', 'function_call': None, 'refusal': None, 'role': None, 'tool_calls': None}, 'finish_reason': None, 'index': 0, 'logprobs': None}], 'created': 1753076578, 'model': 'qwen-doc-turbo', 'object': 'chat.completion.chunk', 'service_tier': None, 'system_fingerprint': None, 'usage': None}
   {'id': 'chatcmpl-ddbb10e9-dba2-930e-9e5b-xxxxxxxxxxxx', 'choices': [{'delta': {'content': '潜在消费者的关注。', 'function_call': None, 'refusal': None, 'role': None, 'tool_calls': None}, 'finish_reason': None, 'index': 0, 'logprobs': None}], 'created': 1753076578, 'model': 'qwen-doc-turbo', 'object': 'chat.completion.chunk', 'service_tier': None, 'system_fingerprint': None, 'usage': None}
   这篇文章是关于“百炼系列手机产品介绍”的内容。文章详细介绍了百炼系列的不同手机型号，包括它们的屏幕尺寸、分辨率、刷新率、存储空间、RAM、电池容量、摄像头配置、特色功能以及参考售价等信息。每一款手机都强调了其在特定领域的优势，如视觉体验、摄影体验、游戏性能、轻薄便携性以及折叠屏创新等。文章旨在展示百炼手机系列在各个方面的强大功能和高性价比，吸引潜在消费者的关注。

   Java

   ChatCompletionChunk{id=chatcmpl-2a9ebb9d-93ed-9342-8139-xxxxxxxxxxxx, choices=[Choice{delta=Delta{content=, functionCall=, refusal=, role=assistant, toolCalls=, additionalProperties={}}, finishReason=null, index=0, logprobs=null, additionalProperties={}}], created=1744943511, model=qwen-doc-turbo, object_=chat.completion.chunk, serviceTier=, systemFingerprint=null, usage=null, additionalProperties={}}
   ChatCompletionChunk{id=chatcmpl-2a9ebb9d-93ed-9342-8139-xxxxxxxxxxxx, choices=[Choice{delta=Delta{content=这篇文章, functionCall=, refusal=, role=, toolCalls=, additionalProperties={}}, finishReason=null, index=0, logprobs=null, additionalProperties={}}], created=1744943511, model=qwen-doc-turbo, object_=chat.completion.chunk, serviceTier=, systemFingerprint=null, usage=null, additionalProperties={}}
   ChatCompletionChunk{id=chatcmpl-2a9ebb9d-93ed-9342-8139-xxxxxxxxxxxx, choices=[Choice{delta=Delta{content=介绍了, functionCall=, refusal=, role=, toolCalls=, additionalProperties={}}, finishReason=null, index=0, logprobs=null, additionalProperties={}}], created=1744943511, model=qwen-doc-turbo, object_=chat.completion.chunk, serviceTier=, systemFingerprint=null, usage=null, additionalProperties={}}
   ...
   ChatCompletionChunk{id=chatcmpl-2a9ebb9d-93ed-9342-8139-xxxxxxxxxxxx, choices=[Choice{delta=Delta{content=手中的“科技艺术品, functionCall=, refusal=, role=, toolCalls=, additionalProperties={}}, finishReason=null, index=0, logprobs=null, additionalProperties={}}], created=1744943511, model=qwen-doc-turbo, object_=chat.completion.chunk, serviceTier=, systemFingerprint=null, usage=null, additionalProperties={}}
   ChatCompletionChunk{id=chatcmpl-2a9ebb9d-93ed-9342-8139-xxxxxxxxxxxx, choices=[Choice{delta=Delta{content=”。, functionCall=, refusal=, role=, toolCalls=, additionalProperties={}}, finishReason=null, index=0, logprobs=null, additionalProperties={}}], created=1744943511, model=qwen-doc-turbo, object_=chat.completion.chunk, serviceTier=, systemFingerprint=null, usage=null, additionalProperties={}}
   ChatCompletionChunk{id=chatcmpl-2a9ebb9d-93ed-9342-8139-xxxxxxxxxxxx, choices=[Choice{delta=Delta{content=, functionCall=, refusal=, role=, toolCalls=, additionalProperties={}}, finishReason=stop, index=0, logprobs=null, additionalProperties={}}], created=1744943511, model=qwen-doc-turbo, object_=chat.completion.chunk, serviceTier=, systemFingerprint=null, usage=null, additionalProperties={}}
   这篇文章介绍了多个品牌的手机产品，具体描述了每一款手机的主要特点和卖点，包括屏幕尺寸.....每款手机都强调了自己的独特之处，力求成为用户手中的“科技艺术品”。

   curl

   data: {"choices":[{"delta":{"content":"","role":"assistant"},"index":0,"logprobs":null,"finish_reason":null}],"object":"chat.completion.chunk","usage":null,"created":1728649489,"system_fingerprint":null,"model":"qwen-doc-turbo","id":"chatcmpl-e2434284-140a-9e3a-8ca5-f81e65e98d01"}
   
   data: {"choices":[{"finish_reason":null,"delta":{"content":"这篇文章"},"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1728649489,"system_fingerprint":null,"model":"qwen-doc-turbo","id":"chatcmpl-e2434284-140a-9e3a-8ca5-f81e65e98d01"}
   
   data: {"choices":[{"delta":{"content":"是"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1728649489,"system_fingerprint":null,"model":"qwen-doc-turbo","id":"chatcmpl-e2434284-140a-9e3a-8ca5-f81e65e98d01"}
   
   data: {"choices":[{"delta":{"content":"关于"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1728649489,"system_fingerprint":null,"model":"qwen-doc-turbo","id":"chatcmpl-e2434284-140a-9e3a-8ca5-f81e65e98d01"}
   
   .....
   
   data: {"choices":[{"delta":{"content":"描述了每款"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1728649489,"system_fingerprint":null,"model":"qwen-doc-turbo","id":"chatcmpl-e2434284-140a-9e3a-8ca5-f81e65e98d01"}
   
   data: {"choices":[{"delta":{"content":"手机的主要特点和"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1728649489,"system_fingerprint":null,"model":"qwen-doc-turbo","id":"chatcmpl-e2434284-140a-9e3a-8ca5-f81e65e98d01"}
   
   data: {"choices":[{"delta":{"content":"规格，并提供了参考"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1728649489,"system_fingerprint":null,"model":"qwen-doc-turbo","id":"chatcmpl-e2434284-140a-9e3a-8ca5-f81e65e98d01"}
   
   data: {"choices":[{"delta":{"content":"售价信息。"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1728649489,"system_fingerprint":null,"model":"qwen-doc-turbo","id":"chatcmpl-e2434284-140a-9e3a-8ca5-f81e65e98d01"}
   
   data: {"choices":[{"finish_reason":"stop","delta":{"content":""},"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1728649489,"system_fingerprint":null,"model":"qwen-doc-turbo","id":"chatcmpl-e2434284-140a-9e3a-8ca5-f81e65e98d01"}
   
   data: {"choices":[],"object":"chat.completion.chunk","usage":{"prompt_tokens":5395,"completion_tokens":71,"total_tokens":5466},"created":1728649489,"system_fingerprint":null,"model":"qwen-doc-turbo","id":"chatcmpl-e2434284-140a-9e3a-8ca5-f81e65e98d01"}
   
   data: [DONE]

纯文本传入文档信息

除了通过 文件ID 传入文档信息外，您还可以直接使用字符串传入文档内容。在此方法下，为避免模型混淆角色设定与文档内容，请确保在 messages 的第一条消息中添加用于角色设定的信息。

import os
from openai import OpenAI, BadRequestError

client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
)

try:
    completion = client.chat.completions.create(
        model="qwen-doc-turbo",
        messages=[
            {'role': 'system', 'content': 'You are a helpful assistant.'},
            # 如果您没有配置环境变量，请在此处替换您的API-KEY
            {'role': 'system', 'content': '阿里云百炼手机产品介绍 阿里云百炼X1 ——————畅享极致视界：搭载6.7英寸1440 x 3200像素超清屏幕...'},
            {'role': 'user', 'content': '阿里云百炼都有那些手机?'}
        ],
        # 所有代码示例均采用流式输出，以清晰和直观地展示模型输出过程。如果您希望查看非流式输出的案例，请参见https://help.aliyun.com/zh/model-studio/text-generation
        stream=True,
        stream_options={"include_usage": True}
    )

    full_content = ""
    for chunk in completion:
        if chunk.choices and chunk.choices[0].delta.content:
            full_content += chunk.choices[0].delta.content
            print(chunk.model_dump())
    
    print(full_content)

except BadRequestError as e:
    print(f"错误信息：{e}")
    print("请参考文档：https://help.aliyun.com/zh/model-studio/developer-reference/error-code")

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.core.http.StreamResponse;
import com.openai.models.*;

public class Main {
    public static void main(String[] args) {
        // 创建客户端，使用环境变量中的API密钥
        OpenAIClient client = OpenAIOkHttpClient.builder()
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                ////请将 'file-fe-xxx'替换为您实际对话场景所使用的 fileid。
                .baseUrl("https://dashscope.aliyuncs.com/compatible-mode/v1")
                .build();

        ChatCompletionCreateParams chatParams = ChatCompletionCreateParams.builder()
                .addSystemMessage("You are a helpful assistant.")
                .addSystemMessage("阿里云百炼手机产品介绍 阿里云百炼X1 ——————畅享极致视界：搭载6.7英寸1440 x 3200像素超清屏幕...")
                .addUserMessage("阿里云百炼都有那些手机?")
                .model("qwen-doc-turbo")
                .build();

        try (StreamResponse<ChatCompletionChunk> streamResponse = client.chat().completions().createStreaming(chatParams)) {
            streamResponse.stream().forEach(chunk -> {
                String content = chunk.choices().get(0).delta().content().orElse("");
                if (!content.isEmpty()) {
                    System.out.print(content);
                }
            });
        } catch (Exception e) {
            System.err.println("错误信息：" + e.getMessage());
        }
    }
}

curl --location 'https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header "Content-Type: application/json" \
--data '{
    "model": "qwen-doc-turbo",
    "messages": [
        {"role": "system","content": "You are a helpful assistant."},
        {"role": "system","content": "阿里云百炼X1 —— 畅享极致视界：搭载6.7英寸1440 x 3200像素超清屏幕，搭配120Hz刷新率，..."},
        {"role": "user","content": "阿里云百炼都有那些手机?"}
    ],
    "stream": true,
    "stream_options": {
        "include_usage": true
    }
}'