优化搜索prompt速度

__main__.py

@@ -101,7 +101,7 @@ class ChatBot(ChatBotFrame):
         with gr.Box():
             with gr.Row():
                 with gr.Column(scale=100):
-                    self.pro_results = gr.Chatbot(label='Prompt and result').style(height=422)
+                    self.pro_results = gr.Chatbot(label='Prompt and result', elem_id='prompt_result').style()
                 with gr.Column(scale=10):
                     Tips = "用 BORF 分析法设计chat GPT prompt:\n" \
                            "1、阐述背景 B(Background): 说明背景，为chatGPT提供充足的信息\n" \

func_box.py

@@ -10,6 +10,8 @@ import os.path
 import subprocess
 import threading
 import time
+from concurrent.futures import ThreadPoolExecutor
+import Levenshtein
 import psutil
 import re
 import tempfile
@@ -284,25 +286,30 @@ def diff_list(txt='', percent=0.70, switch: list = None, lst: list = None, sp=15
     Returns:
         返回一个列表
     """
-    import difflib
     count_dict = {}
     if not lst:
         lst = SqliteHandle('ai_common').get_prompt_value(txt)
         lst.update(SqliteHandle(f"ai_private_{hosts}").get_prompt_value(txt))
     # diff 数据，根据precent系数归类数据
-    for i in lst:
+    str_ = time.time()
+
+    def tf_factor_calcul(i):
         found = False
-        for key in count_dict.keys():
-            str_tf = difflib.SequenceMatcher(None, i, key).ratio()
+        dict_copy = count_dict.copy()
+        for key in dict_copy.keys():
+            str_tf = Levenshtein.jaro_winkler(i, key)
             if str_tf >= percent:
                 if len(i) > len(key):
-                    count_dict[i] = count_dict[key] + 1
+                    count_dict[i] = count_dict.copy()[key] + 1
                     count_dict.pop(key)
                 else:
                     count_dict[key] += 1
                 found = True
                 break
         if not found: count_dict[i] = 1
+    with ThreadPoolExecutor(1000) as executor:
+        executor.map(tf_factor_calcul, lst)
+    print('计算耗时', time.time()-str_)
     sorted_dict = sorted(count_dict.items(), key=lambda x: x[1], reverse=True)
     if switch:
         sorted_dict += prompt_retrieval(is_all=switch, hosts=hosts, search=True)

requirements.txt

@@ -22,3 +22,4 @@ psutil
 distro
 python-dotenv
 rich
+Levenshtein

theme.py

@@ -139,6 +139,10 @@ textarea {
     /* overflow: auto !important; */
     z-index: 2;
 }
+#prompt_result{
+    height: 50vh !important;
+    max-height: 50vh !important;
+}
 .wrap.svelte-18telvq.svelte-18telvq {
     padding: var(--block-padding) !important;
     height: 100% !important;
@@ -153,7 +157,6 @@ textarea {
     width: 100%;
     height: 100%;
 }
-
 .markdown-body table {
     margin: 1em 0;
     border-collapse: collapse;