数据挖掘（Qwen-Doc）

import os
import dashscope

response = dashscope.Generation.call(
  api_key=os.getenv('DASHSCOPE_API_KEY'),
  model='qwen-doc-turbo',
  messages=[
    {"role": "system", "content": "You are a helpful assistant."},
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "从这两份产品手册中，提取所有产品信息，并整理成一个标准的JSON数组。每个对象需要包含：model(产品的型号)、name(产品的名称)、price(价格（去除货币符号和逗号）)"
        },
        {
          "type": "doc_url",
          "doc_url": [
            "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20251107/jockge/%E7%A4%BA%E4%BE%8B%E4%BA%A7%E5%93%81%E6%89%8B%E5%86%8CA.docx",
            "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20251107/ztwxzr/%E7%A4%BA%E4%BE%8B%E4%BA%A7%E5%93%81%E6%89%8B%E5%86%8CB.docx"
          ],
          "file_parsing_strategy": "auto"
        }
      ]
    }
  ]
)
try:
  if response.status_code == 200:
    print(response.output.choices[0].message.content)
  else:
    print(f"请求失败，状态码: {response.status_code}")
    print(f"错误代码: {response.code}")
    print(f"错误信息: {response.message}")
except Exception as e:
  print(f"发生错误: {e}")

import os
from pathlib import Path
from openai import OpenAI

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

file_object = client.files.create(file=Path("示例产品手册A.docx"), purpose="file-extract")
# 打印file-id用于后续模型对话
print(file_object.id)

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.'},
      # 请将 '{FILE_ID}'替换为您实际对话场景所使用的 fileid
      {'role': 'system', 'content': 'fileid://{FILE_ID}'},
      {'role': 'user', 'content': '从这份产品手册中，提取所有产品信息，并整理成一个标准的JSON数组。每个对象需要包含：model(产品的型号)、name(产品的名称)、price(价格（去除货币符号和逗号）) '}
    ],
    # 本代码示例采用流式输出，以清晰和直观地展示模型输出过程
    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}")

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.'},
      {'role': 'system', 'content': '智能办公产品手册 版本：V2.0 发布日期：2024年1月 目录 1.1 产品概述...'},
      {'role': 'user', 'content': '从这份产品手册中，提取所有产品信息，并整理成一个标准的JSON数组。每个对象需要包含：model(产品的型号)、name(产品的名称)、price(价格（去除货币符号和逗号）)'}
    ],
    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}")