introduce project self-translation

crazy_functions/全项目切换英文.py

@@ -0,0 +1,59 @@
+import threading
+from predict import predict_no_ui_long_connection
+from toolbox import CatchException, write_results_to_file
+
+
+
+@CatchException
+def 全项目切换英文(txt, top_p, temperature, chatbot, history, sys_prompt, WEB_PORT):
+    history = []    # 清空历史，以免输入溢出
+    # 集合文件
+    import time, glob, os
+    file_manifest = [f for f in glob.glob('./**/*.py', recursive=True) if ('test_project' not in f) and ('gpt_log' not in f)]
+    i_say_show_user_buffer = []
+
+    # 随便显示点什么防止卡顿
+    for index, fp in enumerate(file_manifest):
+        # if 'test_project' in fp: continue
+        with open(fp, 'r', encoding='utf-8') as f:
+            file_content = f.read()
+        i_say_show_user =f'[{index}/{len(file_manifest)}] 接下来请将以下代码中包含的所有中文转化为英文，只输出代码: {os.path.abspath(fp)}'
+        i_say_show_user_buffer.append(i_say_show_user)
+        chatbot.append((i_say_show_user, "[Local Message] 等待多线程操作，中间过程不予显示."))
+        yield chatbot, history, '正常'
+
+    # 任务函数
+    mutable_return = [None for _ in file_manifest]
+    def thread_worker(fp,index):
+        with open(fp, 'r', encoding='utf-8') as f:
+            file_content = f.read()
+        i_say = f'接下来请将以下代码中包含的所有中文转化为英文，只输出代码，文件名是{fp}，文件代码是 ```{file_content}```'
+        # ** gpt request **
+        gpt_say = predict_no_ui_long_connection(inputs=i_say, top_p=top_p, temperature=temperature, history=history, sys_prompt=sys_prompt)
+        mutable_return[index] = gpt_say
+
+    # 所有线程同时开始执行任务函数
+    handles = [threading.Thread(target=thread_worker, args=(fp,index)) for index, fp in enumerate(file_manifest)]
+    for h in handles:
+        h.daemon = True
+        h.start()
+
+    # 等待各个线程逐一完成
+    for index, h in enumerate(handles):
+        h.join()
+        fp = file_manifest[index]
+        gpt_say = mutable_return[index]
+        i_say_show_user = i_say_show_user_buffer[index]
+        os.makedirs('gpt_log/generated_english_version', exist_ok=True)
+        os.makedirs('gpt_log/generated_english_version/crazy_functions', exist_ok=True)
+        where_to_relocate = f'gpt_log/generated_english_version/{fp}'
+        with open(where_to_relocate, 'w+', encoding='utf-8') as f: f.write(gpt_say.lstrip('```').rstrip('```'))
+        chatbot.append((i_say_show_user, f'[Local Message] 已完成{os.path.abspath(fp)}的转化，\n\n存入{os.path.abspath(where_to_relocate)}'))
+        history.append(i_say_show_user); history.append(gpt_say)
+        yield chatbot, history, '正常'
+        time.sleep(2)
+
+    # 结束
+    res = write_results_to_file(history)
+    chatbot.append(("完成了吗？", res))
+    yield chatbot, history, '正常'

functional_crazy.py

@@ -7,11 +7,16 @@ def get_crazy_functionals():
     from crazy_functions.解析项目源代码 import 解析一个C项目的头文件
     from crazy_functions.解析项目源代码 import 解析一个C项目
     from crazy_functions.高级功能函数模板 import 高阶功能模板函数
+    from crazy_functions.全项目切换英文 import 全项目切换英文
 
     return {
         "[实验] 请解析并解构此项目本身": {
             "Function": 解析项目本身
         },
+        "[实验] 把此项目代码切换成全英文": {
+            "Color": "stop",    # 按钮颜色
+            "Function": 全项目切换英文
+        },
         "[实验] 解析整个py项目（配合input输入框）": {
             "Color": "stop",    # 按钮颜色
             "Function": 解析一个Python项目

predict.py

@@ -25,7 +25,7 @@ def get_full_error(chunk, stream_response):
             break
     return chunk
 
-def predict_no_ui(inputs, top_p, temperature, history=[]):
+def predict_no_ui(inputs, top_p, temperature, history=[], sys_prompt=""):
     """
         发送至chatGPT，等待回复，一次性完成，不显示中间过程。
         predict函数的简化版。
@@ -36,7 +36,7 @@ def predict_no_ui(inputs, top_p, temperature, history=[]):
         history 是之前的对话列表
         （注意无论是inputs还是history，内容太长了都会触发token数量溢出的错误，然后raise ConnectionAbortedError）
     """
-    headers, payload = generate_payload(inputs, top_p, temperature, history, system_prompt="", stream=False)
+    headers, payload = generate_payload(inputs, top_p, temperature, history, system_prompt=sys_prompt, stream=False)
 
     retry = 0
     while True:
@@ -47,8 +47,8 @@ def predict_no_ui(inputs, top_p, temperature, history=[]):
         except requests.exceptions.ReadTimeout as e:
             retry += 1
             traceback.print_exc()
-            if MAX_RETRY!=0: print(f'请求超时，正在重试 ({retry}/{MAX_RETRY}) ……')
             if retry > MAX_RETRY: raise TimeoutError
+            if MAX_RETRY!=0: print(f'请求超时，正在重试 ({retry}/{MAX_RETRY}) ……')
 
     try:
         result = json.loads(response.text)["choices"][0]["message"]["content"]
@@ -58,6 +58,40 @@ def predict_no_ui(inputs, top_p, temperature, history=[]):
         raise ConnectionAbortedError("Json解析不合常规，可能是文本过长" + response.text)
 
 
+def predict_no_ui_long_connection(inputs, top_p, temperature, history=[], sys_prompt=""):
+    """
+        发送至chatGPT，等待回复，一次性完成，不显示中间过程。但内部用stream的方法避免有人中途掐网线。
+    """
+    headers, payload = generate_payload(inputs, top_p, temperature, history, system_prompt=sys_prompt, stream=True)
+
+    retry = 0
+    while True:
+        try:
+            # make a POST request to the API endpoint, stream=False
+            response = requests.post(API_URL, headers=headers, proxies=proxies,
+                                    json=payload, stream=True, timeout=TIMEOUT_SECONDS); break
+        except requests.exceptions.ReadTimeout as e:
+            retry += 1
+            traceback.print_exc()
+            if retry > MAX_RETRY: raise TimeoutError
+            if MAX_RETRY!=0: print(f'请求超时，正在重试 ({retry}/{MAX_RETRY}) ……')
+
+    stream_response =  response.iter_lines()
+    result = ''
+    while True:
+        try: chunk = next(stream_response).decode()
+        except StopIteration: break
+        if len(chunk)==0: continue
+        if not chunk.startswith('data:'): 
+            raise ConnectionAbortedError("OpenAI返回了错误:" + chunk)
+        delta = json.loads(chunk.lstrip('data:'))['choices'][0]["delta"]
+        if len(delta) == 0: break
+        if "role" in delta: continue
+        if "content" in delta: result += delta["content"]; print(delta["content"], end='')
+        else: raise RuntimeError("意外Json结构："+delta)
+    return result
+
+
 def predict(inputs, top_p, temperature, chatbot=[], history=[], system_prompt='', 
             stream = True, additional_fn=None):
     """

toolbox.py

@@ -2,7 +2,7 @@ import markdown, mdtex2html, threading
 from show_math import convert as convert_math
 from functools import wraps
 
-def predict_no_ui_but_counting_down(i_say, i_say_show_user, chatbot, top_p, temperature, history=[]):
+def predict_no_ui_but_counting_down(i_say, i_say_show_user, chatbot, top_p, temperature, history=[], sys_prompt=''):
     """
         调用简单的predict_no_ui接口，但是依然保留了些许界面心跳功能，当对话太长时，会自动采用二分法截断
     """
@@ -17,7 +17,7 @@ def predict_no_ui_but_counting_down(i_say, i_say_show_user, chatbot, top_p, temp
     def mt(i_say, history): 
         while True:
             try:
-                mutable[0] = predict_no_ui(inputs=i_say, top_p=top_p, temperature=temperature, history=history)
+                mutable[0] = predict_no_ui(inputs=i_say, top_p=top_p, temperature=temperature, history=history, sys_prompt=sys_prompt)
                 break
             except ConnectionAbortedError as e:
                 if len(history) > 0:
@@ -27,7 +27,8 @@ def predict_no_ui_but_counting_down(i_say, i_say_show_user, chatbot, top_p, temp
                     i_say = i_say[:len(i_say)//2]
                     mutable[1] = 'Warning! Input file is too long, cut into half. '
             except TimeoutError as e:
-                mutable[0] = '[Local Message] Failed with timeout'
+                mutable[0] = '[Local Message] Failed with timeout.'
+                raise TimeoutError
     # 创建新线程发出http请求
     thread_name = threading.Thread(target=mt, args=(i_say, history)); thread_name.start()
     # 原来的线程则负责持续更新UI，实现一个超时倒计时，并等待新线程的任务完成
@@ -39,6 +40,7 @@ def predict_no_ui_but_counting_down(i_say, i_say_show_user, chatbot, top_p, temp
         time.sleep(1)
     # 把gpt的输出从mutable中取出来
     gpt_say = mutable[0]
+    if gpt_say=='[Local Message] Failed with timeout.': raise TimeoutError
     return gpt_say
 
 def write_results_to_file(history, file_name=None):