12.19 修复豆包模型使用的bug

flask_app/货物标/技术参数要求提取.py

@@ -362,29 +362,28 @@ def generate_prompt(judge_res, full_text=None):
     base_prompt += "\n注意事项：\n1.严格按照上述要求执行，确保输出准确性和规范性。\n"
     return base_prompt
 
-def get_technical_requirements(invalid_path,processed_filepath):
+def get_technical_requirements(invalid_path,processed_filepath,model_type=1):
+    judge_res = ""
     file_id = ""
-    model_type = 1  # 默认使用豆包
+    full_text = read_txt_to_string(processed_filepath)
-    first_query_template="""该文件是否说明了采购需求,即需要采购哪些内容（包括货物、设备、系统、功能模块等）?如果有,请回答'是',否则,回答'否'
+    if model_type:
-文件内容：
+        first_query_template = """该文件是否说明了采购需求,即需要采购哪些内容（包括货物、设备、系统、功能模块等）?如果有,请回答'是',否则,回答'否'
-{full_text}
+    {}
     """
-    judge_query = generate_full_user_query(processed_filepath, first_query_template)
+        judge_query = first_query_template.format(f"文件内容：{full_text}")
-    # print(judge_query)
         judge_res = doubao_model(judge_query)
-    if '否' in judge_res:
+    if '否' in judge_res or model_type == 0:
         model_type = 0  # 使用qianwen-long+invalid_path
         print("no!调用invalid_path")
-        if invalid_path.lower().endswith('.pdf'):           #确保上传的是docx
+        if invalid_path.lower().endswith('.pdf'):  # 确保上传的是docx  upload中一定是docx，但是get_deviation中可能上传的是pdf
             invalid_path = pdf2docx(invalid_path)
-        file_id=upload_file(invalid_path)
+        file_id = upload_file(invalid_path)
         user_query = generate_prompt(judge_res)
-        model_res=qianwen_long(file_id,user_query)
+        model_res = qianwen_long(file_id, user_query)
         print(model_res)
     else:
-        full_text = read_txt_to_string(processed_filepath)
+        user_query = generate_prompt(judge_res, full_text)
-        user_query=generate_prompt(judge_res,full_text)
+        model_res = doubao_model(user_query)
-        model_res=doubao_model(user_query)
         print(model_res)
     cleaned_res = clean_json_string(model_res)     #转字典
     processed_data=truncate_system_keys(cleaned_res['采购需求'])
@@ -467,7 +466,6 @@ def get_technical_requirements(invalid_path,processed_filepath):
         modified_key = key.replace('.', '下的')
         # 使用修改后的键填充第一个占位符，原始键填充第二个占位符
         if model_type:
-            full_text = read_txt_to_string(processed_filepath)
             new_query = user_query_template.format(modified_key, key, modified_key,f"文件内容：{full_text}")   #转豆包后取消注释
         else:
             new_query = user_query_template.format(modified_key, key, modified_key,"")
@@ -479,7 +477,6 @@ def get_technical_requirements(invalid_path,processed_filepath):
             # 将键中的 '.' 替换为 '下的'
             modified_grouped_key = grouped_key.replace('.', '下的')
             if model_type:
-                full_text = read_txt_to_string(processed_filepath)
                 new_query = user_query_template_two.format(modified_grouped_key, grouped_key_cnt, grouped_key,
                                                            modified_grouped_key, f"文件内容：{full_text}")
             else:

flask_app/货物标/提取采购需求main.py

@@ -32,7 +32,7 @@ def fetch_procurement_reqs(procurement_path, invalid_path):
             # 读取 PDF 页码数
             page_count = get_pdf_page_count(procurement_path)
 
-            if page_count > 80:  # 如果页码数大于 50
+            if page_count > 80:  # 如果页码数大于 580
                 model_type = 0
                 processed_filepath = ""
             else: