11.26 函数级别限制

docker-compose.yml

@@ -9,7 +9,7 @@ services:
       - .env  # 使用 .env 文件中的环境变量
     volumes:
 #      - .:/flask_project  # 将当前目录挂载到容器的 /flask_project 目录（可选，便于开发时实时更新代码）
-      - /home/Z/zbparse_output:/flask_project/flask_app/static/output  # 额外的数据卷挂载
+      - /home/Z/zbparse_output_dev:/flask_project/flask_app/static/output  # 额外的数据卷挂载
     restart: unless-stopped  # 容器退出时自动重启，除非明确停止
     privileged: true
 

flask_app/general/多线程提问.py

@@ -12,7 +12,6 @@ import requests
 from dashscope import Assistants, Messages, Runs, Threads
 from llama_index.indices.managed.dashscope import DashScopeCloudRetriever
 from flask_app.general.通义千问long import qianwen_long, upload_file
-
 prompt = """
 # 角色
 你是一个文档处理专家，专门负责理解和操作基于特定内容的文档任务，这包括解析、总结、搜索或生成与给定文档相关的各类信息。
@@ -268,7 +267,7 @@ def multi_threading(queries, knowledge_name="", file_id="", llm_type=1):
     with concurrent.futures.ThreadPoolExecutor(max_workers=30) as executor:
         future_to_query = {}
         for index, query in enumerate(queries):
-            time.sleep(0.7)  # 每提交一个任务后等待0.5秒
+            # time.sleep(0.5)  # 每提交一个任务后等待0.5秒，目前设置了直接对qianwen-long直接限制，无需sleep
             future = executor.submit(llm_call, query, knowledge_name, file_id, result_queue, index, llm_type)
             future_to_query[future] = index
             retry_counts[index] = 0  # 初始化重试次数

flask_app/general/无效标和废标公共代码.py

@@ -5,8 +5,6 @@ import time
 from concurrent.futures import ThreadPoolExecutor
 from flask_app.general.doubao import doubao_model, generate_full_user_query
 from docx import Document
-
-from flask_app.general.通义千问long import upload_file, qianwen_long_text
 from flask_app.general.通用功能函数 import process_string_list
 
 

flask_app/general/通义千问long.py

@@ -1,4 +1,7 @@
 import json
+from functools import wraps
+
+from ratelimit import limits, sleep_and_retry
 import random
 import time
 from pathlib import Path
@@ -16,6 +19,19 @@ def upload_file(file_path):
     file = client.files.create(file=Path(file_path), purpose="file-extract")
     return file.id
 
+@sleep_and_retry
+@limits(calls=4, period=1)  # 每秒最多调用4次
+def rate_limiter():
+    pass  # 这个函数本身不执行任何操作，只用于限流
+
+# 创建一个共享的装饰器
+def shared_rate_limit(func):
+    @wraps(func)
+    def wrapper(*args, **kwargs):
+        rate_limiter()  # 通过共享的限流器
+        return func(*args, **kwargs)
+    return wrapper
+@shared_rate_limit
 def qianwen_long(file_id, user_query):
     print("call qianwen-long...")
     """
@@ -48,38 +64,7 @@ def qianwen_long(file_id, user_query):
     # 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
-
+@shared_rate_limit
 def qianwen_long_stream(file_id, user_query):
     print("调用 qianwen-long stream...")
     """
@@ -135,10 +120,39 @@ def qianwen_long_stream(file_id, user_query):
         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
 
+@shared_rate_limit
+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
 if __name__ == "__main__":
     # Example file path - replace with your actual file path
 

flask_app/old_version/不得存在及禁止投标情形.py

@@ -4,7 +4,7 @@ import re
 
 from PyPDF2 import PdfWriter, PdfReader
 
-from flask_app.general.通义千问long import upload_file, qianwen_long, qianwen_long_text
+from flask_app.general.通义千问long import upload_file, qianwen_long
 from flask_app.general.通用功能函数 import process_string_list
 
 
@@ -144,7 +144,7 @@ def find_forbidden(qualification=""):
                 "该招标文件规定的投标人不得存在的其他情形有哪些，请以列表给我提供信息，形如[xx,xx,...],"
                 "请你不要回答有关\"信誉要求\"的内容,若原文未提及，返回[]。"
             )
-            qianwen_forbidden_str = qianwen_long_text(file_id, user_query_forbidden)
+            qianwen_forbidden_str = qianwen_long(file_id, user_query_forbidden)
         else:
             qianwen_forbidden_str = "[]"
 

flask_app/old_version/无效标和废标和禁止投标整合.py

@@ -5,7 +5,7 @@ import time
 import re
 
 from flask_app.general.format_change import pdf2docx
-from flask_app.general.通义千问long import upload_file, qianwen_long_text
+from flask_app.general.通义千问long import upload_file, qianwen_long
 from concurrent.futures import ThreadPoolExecutor
 
 from flask_app.general.table_content_extraction import extract_tables_main
@@ -345,7 +345,7 @@ def handle_query(file_path, user_query, output_file, result_key, keywords, trunc
 
             file_id = upload_file(output_file)
             # qianwen_ans = qianwen_long(file_id, user_query)
-            qianwen_ans = qianwen_long_text(file_id, user_query)
+            qianwen_ans = qianwen_long(file_id, user_query)
             num_list = process_string_list(qianwen_ans)
             print(result_key + "选中的序号:" + str(num_list))
 

flask_app/货物标/评分标准提取main.py

@@ -3,7 +3,7 @@ import json
 import re
 import time
 from collections import defaultdict
-from flask_app.general.通义千问long import upload_file, qianwen_long, qianwen_long_text
+from flask_app.general.通义千问long import upload_file, qianwen_long
 
 
 def combine_technical_and_business(data, target_values):
@@ -211,7 +211,7 @@ def combine_evaluation_standards(truncate_file):
         )  # 应对竞争性谈判这种无评分要求的情况
 
         # 执行查询
-        judge_res = qianwen_long_text(file_id, user_query1)
+        judge_res = qianwen_long(file_id, user_query1)
         # 默认 judge 为 True
         judge = True
 
@@ -268,7 +268,7 @@ def combine_evaluation_standards(truncate_file):
                 """
             )
             # 执行第二个查询
-            evaluation_res = qianwen_long_text(file_id, user_query)    #有些重复的键名，只有qianwen_long_text能保留
+            evaluation_res = qianwen_long(file_id, user_query)    #有些重复的键名，只有qianwen_long_text能保留
             # print(evaluation_res)
             # 清理和处理响应
             cleaned_evaluation_res = parse_json_with_duplicates(evaluation_res)   #处理重复键名的情况

requirements.txt

@@ -14,4 +14,5 @@ dashscope==1.19.2
 PyMuPDF==1.24.1
 openai==1.33.0
 pathlib==1.0.1
-alibabacloud_bailian20231229==1.7.0
+alibabacloud_bailian20231229==1.7.0
+ratelimit==2.2.1