zbparse/flask_app/general/通义千问long.py

import json
import random
import time
from pathlib import Path
from openai import OpenAI
import os

def upload_file(file_path):
    """
    Uploads a file to DashScope and returns the file ID.
    """
    client = OpenAI(
        api_key=os.getenv("DASHSCOPE_API_KEY"),
        base_url="https://dashscope.aliyuncs.com/compatible-mode/v1"
    )
    file = client.files.create(file=Path(file_path), purpose="file-extract")
    return file.id

def qianwen_long(file_id, user_query):
    print("call qianwen-long...")
    """
    Uses a previously uploaded file to generate a response based on a user query.
    """
    client = OpenAI(
        api_key=os.getenv("DASHSCOPE_API_KEY"),
        base_url="https://dashscope.aliyuncs.com/compatible-mode/v1"
    )

    # Generate a response based on the file ID
    completion = client.chat.completions.create(
        model="qwen-long",
        # top_p=0.5,
        temperature=0.5,
        # response_format={"type":"json_object"},
        messages=[
            {
                'role': 'system',
                'content': f'fileid://{file_id}'
            },
            {
                'role': 'user',
                'content': user_query
            }
        ],
        stream=False
    )

    # Return the response content
    # return completion.choices[0].message.content,completion.usage
    return completion.choices[0].message.content

def qianwen_long_text(file_id, user_query):
    print("call qianwen-long text...")
    """
    Uses a previously uploaded file to generate a response based on a user query.
    """
    client = OpenAI(
        api_key=os.getenv("DASHSCOPE_API_KEY"),
        base_url="https://dashscope.aliyuncs.com/compatible-mode/v1"
    )

    # Generate a response based on the file ID
    completion = client.chat.completions.create(
        model="qwen-long",
        # top_p=0.5,
        temperature=0.5,
        messages=[
            {
                'role': 'system',
                'content': f'fileid://{file_id}'
            },
            {
                'role': 'user',
                'content': user_query
            }
        ],
        stream=False
    )

    # Return the response content
    return completion.choices[0].message.content

def qianwen_long_stream(file_id, user_query):
    print("调用 qianwen-long text...")
    """
    使用之前上传的文件，根据用户查询生成响应，并实时显示流式输出。
    """
    client = OpenAI(
        api_key=os.getenv("DASHSCOPE_API_KEY"),
        base_url="https://dashscope.aliyuncs.com/compatible-mode/v1"
    )

    # 生成基于文件ID的响应
    completion = client.chat.completions.create(
        model="qwen-long",
        temperature=0.5,
        messages=[
            {
                'role': 'system',
                'content': f'fileid://{file_id}'
            },
            {
                'role': 'user',
                'content': user_query
            }
        ],
        stream=True  # 启用流式响应
    )

    full_response = ""  # 用于存储完整的响应内容

    try:
        for chunk in completion:
            # 假设chunk是一个对象，先将其转换为字典
            if hasattr(chunk, 'to_dict'):
                chunk_data = chunk.to_dict()
            else:
                # 如果没有to_dict方法，尝试直接转换为JSON
                chunk_data = json.loads(chunk.model_dump_json())
            # 检查是否有'choices'字段
            choices = chunk_data.get('choices', [])
            if not choices:
                continue  # 如果没有choices，跳过当前chunk
            choice = choices[0]  # 获取第一个choice
            delta = choice.get('delta', {})
            # 提取'content'字段
            content = delta.get('content', '')
            if content:
                # print(content, end='', flush=True)  # 实时打印内容
                full_response += content
            # 检查是否有结束条件
            if choice.get('finish_reason'):
                break
    except KeyboardInterrupt:
        print("\n中断流式响应。")
    except Exception as e:
        print(f"\n处理流式响应时出错: {e}")

    print()  # 换行
    return full_response  # 返回完整的响应内容

if __name__ == "__main__":
    # Example file path - replace with your actual file path

    file_path = r"C:\Users\Administrator\Desktop\货物标\output1\陕西省公安厅交通警察总队高速公路交通安全智能感知巡查系统项目 (1)_procurement.pdf"
    file_id = upload_file(file_path)
    #
    # user_query1 = "该招标文件前附表中的项目名称是什么，请以json格式返回给我"
    # user_query2 = ("请提供文件中关于资格审查的具体内容和标准。")
    # start_time=time.time()
    # # First query
    # print("starting qianwen-long...")
    # result1 ,result2= qianwen_long(file_id, user_query1)
    # print("First Query Result:", result1)
    # print(type(result1))
    # print(result2)
    # # Second query
    # print("starting qianwen-long...")
    # result2 = qianwen_long(file_id, user_query2)
    # print("Second Query Result:", result2)
    # end_time=time.time()
    # print("elapsed time:"+str(end_time-start_time))

    user_query = """
请你根据该货物标中采购要求部分的内容，请你给出"高速公路交通安全智能感知巡查系统软件"的技术参数（或采购要求），请以json格式返回结果，键名为"高速公路交通安全智能感知巡查系统软件", 键值为一个列表，列表中包含若干描述\"{}\"的技术参数（或采购要求）的字符串，需与原文完全一致，即若技术参数前存在序号也要保留，但你不可擅自增添或删减。以下为需要考虑的特殊情况：如果该货物没有相关采购要求或技术参数要求，键值为空列表。示例输出格式如下：
{{
    "摄像机控制键盘": [
        "1、支持串行 RS232/RS422 和 IP 混合控制，允许在一个控制器上使用 RS232/RS422/IP 控制单个系统中的摄像机；",
        "2、支持 2 组 RS422 串口 VISCA 协议菊花链控制 2x7 台摄像机。"
    ]
}}
            """
    response = qianwen_long_stream(file_id, user_query)
    print("完整响应内容：")
    print(response)