upgrade to version 3.64

* feat: 拖动以上传文件

* 上传文件过程中转圈圈

* fix: 解决仅在第一次上传时才有上传动画的问题

---------

Co-authored-by: 505030475 <qingxu.fu@outlook.com>

.github/workflows/build-with-all-capacity-beta.yml

@@ -0,0 +1,44 @@
+# https://docs.github.com/en/actions/publishing-packages/publishing-docker-images#publishing-images-to-github-packages
+name: build-with-all-capacity-beta
+
+on:
+  push:
+    branches:
+      - 'master'
+
+env:
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }}_with_all_capacity_beta
+
+jobs:
+  build-and-push-image:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+
+      - name: Log in to the Container registry
+        uses: docker/login-action@v2
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@v4
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+
+      - name: Build and push Docker image
+        uses: docker/build-push-action@v4
+        with:
+          context: .
+          push: true
+          file: docs/GithubAction+AllCapacityBeta
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}

crazy_functional.py

@@ -590,19 +590,19 @@ def get_crazy_functions():
         print(trimmed_format_exc())
         print('Load function plugin failed')
 
-    # try:
-    #     from crazy_functions.互动小游戏 import 随机小游戏
-    #     function_plugins.update({
-    #         "随机小游戏": {
-    #             "Group": "智能体",
-    #             "Color": "stop",
-    #             "AsButton": True,
-    #             "Function": HotReload(随机小游戏)
-    #         }
-    #     })
-    # except:
-    #     print(trimmed_format_exc())
-    #     print('Load function plugin failed')
+    try:
+        from crazy_functions.互动小游戏 import 随机小游戏
+        function_plugins.update({
+            "随机互动小游戏（仅供测试）": {
+                "Group": "智能体",
+                "Color": "stop",
+                "AsButton": False,
+                "Function": HotReload(随机小游戏)
+            }
+        })
+    except:
+        print(trimmed_format_exc())
+        print('Load function plugin failed')
 
     # try:
     #     from crazy_functions.chatglm微调工具 import 微调数据集生成

crazy_functions/Latex全文润色.py

@@ -26,8 +26,8 @@ class PaperFileGroup():
                 self.sp_file_index.append(index)
                 self.sp_file_tag.append(self.file_paths[index])
             else:
-                from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
-                segments = breakdown_txt_to_satisfy_token_limit_for_pdf(file_content, self.get_token_num, max_token_limit)
+                from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
+                segments = breakdown_text_to_satisfy_token_limit(file_content, max_token_limit)
                 for j, segment in enumerate(segments):
                     self.sp_file_contents.append(segment)
                     self.sp_file_index.append(index)

crazy_functions/Latex全文翻译.py

@@ -26,8 +26,8 @@ class PaperFileGroup():
                 self.sp_file_index.append(index)
                 self.sp_file_tag.append(self.file_paths[index])
             else:
-                from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
-                segments = breakdown_txt_to_satisfy_token_limit_for_pdf(file_content, self.get_token_num, max_token_limit)
+                from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
+                segments = breakdown_text_to_satisfy_token_limit(file_content, max_token_limit)
                 for j, segment in enumerate(segments):
                     self.sp_file_contents.append(segment)
                     self.sp_file_index.append(index)

crazy_functions/crazy_utils.py

@@ -312,95 +312,6 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
     return gpt_response_collection
 
 
-def breakdown_txt_to_satisfy_token_limit(txt, get_token_fn, limit):
-    def cut(txt_tocut, must_break_at_empty_line):  # 递归
-        if get_token_fn(txt_tocut) <= limit:
-            return [txt_tocut]
-        else:
-            lines = txt_tocut.split('\n')
-            estimated_line_cut = limit / get_token_fn(txt_tocut) * len(lines)
-            estimated_line_cut = int(estimated_line_cut)
-            for cnt in reversed(range(estimated_line_cut)):
-                if must_break_at_empty_line:
-                    if lines[cnt] != "":
-                        continue
-                print(cnt)
-                prev = "\n".join(lines[:cnt])
-                post = "\n".join(lines[cnt:])
-                if get_token_fn(prev) < limit:
-                    break
-            if cnt == 0:
-                raise RuntimeError("存在一行极长的文本！")
-            # print(len(post))
-            # 列表递归接龙
-            result = [prev]
-            result.extend(cut(post, must_break_at_empty_line))
-            return result
-    try:
-        return cut(txt, must_break_at_empty_line=True)
-    except RuntimeError:
-        return cut(txt, must_break_at_empty_line=False)
-
-
-def force_breakdown(txt, limit, get_token_fn):
-    """
-    当无法用标点、空行分割时，我们用最暴力的方法切割
-    """
-    for i in reversed(range(len(txt))):
-        if get_token_fn(txt[:i]) < limit:
-            return txt[:i], txt[i:]
-    return "Tiktoken未知错误", "Tiktoken未知错误"
-
-def breakdown_txt_to_satisfy_token_limit_for_pdf(txt, get_token_fn, limit):
-    # 递归
-    def cut(txt_tocut, must_break_at_empty_line, break_anyway=False):  
-        if get_token_fn(txt_tocut) <= limit:
-            return [txt_tocut]
-        else:
-            lines = txt_tocut.split('\n')
-            estimated_line_cut = limit / get_token_fn(txt_tocut) * len(lines)
-            estimated_line_cut = int(estimated_line_cut)
-            cnt = 0
-            for cnt in reversed(range(estimated_line_cut)):
-                if must_break_at_empty_line:
-                    if lines[cnt] != "":
-                        continue
-                prev = "\n".join(lines[:cnt])
-                post = "\n".join(lines[cnt:])
-                if get_token_fn(prev) < limit:
-                    break
-            if cnt == 0:
-                if break_anyway:
-                    prev, post = force_breakdown(txt_tocut, limit, get_token_fn)
-                else:
-                    raise RuntimeError(f"存在一行极长的文本！{txt_tocut}")
-            # print(len(post))
-            # 列表递归接龙
-            result = [prev]
-            result.extend(cut(post, must_break_at_empty_line, break_anyway=break_anyway))
-            return result
-    try:
-        # 第1次尝试，将双空行（\n\n）作为切分点
-        return cut(txt, must_break_at_empty_line=True)
-    except RuntimeError:
-        try:
-            # 第2次尝试，将单空行（\n）作为切分点
-            return cut(txt, must_break_at_empty_line=False)
-        except RuntimeError:
-            try:
-                # 第3次尝试，将英文句号（.）作为切分点
-                res = cut(txt.replace('.', '。\n'), must_break_at_empty_line=False) # 这个中文的句号是故意的，作为一个标识而存在
-                return [r.replace('。\n', '.') for r in res]
-            except RuntimeError as e:
-                try:
-                    # 第4次尝试，将中文句号（。）作为切分点
-                    res = cut(txt.replace('。', '。。\n'), must_break_at_empty_line=False)
-                    return [r.replace('。。\n', '。') for r in res]
-                except RuntimeError as e:
-                    # 第5次尝试，没办法了，随便切一下敷衍吧
-                    return cut(txt, must_break_at_empty_line=False, break_anyway=True)
-
-
 
 def read_and_clean_pdf_text(fp):
     """
@@ -631,7 +542,6 @@ def get_files_from_everything(txt, type): # type='.md'
 
 
 
-    
 @Singleton
 class nougat_interface():
     def __init__(self):

crazy_functions/game_fns/game_ascii_art.py

@@ -0,0 +1,42 @@
+from toolbox import CatchException, update_ui, update_ui_lastest_msg
+from crazy_functions.multi_stage.multi_stage_utils import GptAcademicGameBaseState
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+from request_llms.bridge_all import predict_no_ui_long_connection
+from crazy_functions.game_fns.game_utils import get_code_block, is_same_thing
+import random
+
+
+class MiniGame_ASCII_Art(GptAcademicGameBaseState):
+    def step(self, prompt, chatbot, history):
+        if self.step_cnt == 0:  
+            chatbot.append(["我画你猜（动物）", "请稍等..."])
+        else:
+            if prompt.strip() == 'exit':
+                self.delete_game = True
+                yield from update_ui_lastest_msg(lastmsg=f"谜底是{self.obj}，游戏结束。", chatbot=chatbot, history=history, delay=0.)
+                return
+            chatbot.append([prompt, ""])
+        yield from update_ui(chatbot=chatbot, history=history)
+
+        if self.step_cnt == 0:
+            self.lock_plugin(chatbot)
+            self.cur_task = 'draw'
+
+        if self.cur_task == 'draw':
+            avail_obj = ["狗","猫","鸟","鱼","老鼠","蛇"]
+            self.obj = random.choice(avail_obj)
+            inputs = "I want to play a game called Guess the ASCII art. You can draw the ASCII art and I will try to guess it. " + \
+                f"This time you draw a {self.obj}. Note that you must not indicate what you have draw in the text, and you should only produce the ASCII art wrapped by ```. "
+            raw_res = predict_no_ui_long_connection(inputs=inputs, llm_kwargs=self.llm_kwargs, history=[], sys_prompt="")
+            self.cur_task = 'identify user guess'
+            res = get_code_block(raw_res)
+            history += ['', f'the answer is {self.obj}', inputs, res]
+            yield from update_ui_lastest_msg(lastmsg=res, chatbot=chatbot, history=history, delay=0.)
+
+        elif self.cur_task == 'identify user guess':
+            if is_same_thing(self.obj, prompt, self.llm_kwargs):
+                self.delete_game = True
+                yield from update_ui_lastest_msg(lastmsg="你猜对了！", chatbot=chatbot, history=history, delay=0.)
+            else:
+                self.cur_task = 'identify user guess'
+                yield from update_ui_lastest_msg(lastmsg="猜错了，再试试，输入“exit”获取答案。", chatbot=chatbot, history=history, delay=0.)

crazy_functions/game_fns/game_interactive_story.py

@@ -0,0 +1,212 @@
+prompts_hs = """ 请以“{headstart}”为开头，编写一个小说的第一幕。
+
+- 尽量短，不要包含太多情节，因为你接下来将会与用户互动续写下面的情节，要留出足够的互动空间。
+- 出现人物时，给出人物的名字。
+- 积极地运用环境描写、人物描写等手法，让读者能够感受到你的故事世界。
+- 积极地运用修辞手法，比如比喻、拟人、排比、对偶、夸张等等。
+- 字数要求：第一幕的字数少于300字，且少于2个段落。
+"""
+
+prompts_interact = """ 小说的前文回顾：
+「
+{previously_on_story}
+」
+
+你是一个作家，根据以上的情节，给出4种不同的后续剧情发展方向，每个发展方向都精明扼要地用一句话说明。稍后，我将在这4个选择中，挑选一种剧情发展。
+
+输出格式例如：
+1. 后续剧情发展1
+2. 后续剧情发展2
+3. 后续剧情发展3
+4. 后续剧情发展4
+"""
+
+
+prompts_resume = """小说的前文回顾：
+「
+{previously_on_story}
+」
+
+你是一个作家，我们正在互相讨论，确定后续剧情的发展。
+在以下的剧情发展中，
+「
+{choice}
+」
+我认为更合理的是：{user_choice}。
+请在前文的基础上（不要重复前文），围绕我选定的剧情情节，编写小说的下一幕。
+
+- 禁止杜撰不符合我选择的剧情。
+- 尽量短，不要包含太多情节，因为你接下来将会与用户互动续写下面的情节，要留出足够的互动空间。
+- 不要重复前文。
+- 出现人物时，给出人物的名字。
+- 积极地运用环境描写、人物描写等手法，让读者能够感受到你的故事世界。
+- 积极地运用修辞手法，比如比喻、拟人、排比、对偶、夸张等等。
+- 小说的下一幕字数少于300字，且少于2个段落。
+"""
+
+
+prompts_terminate = """小说的前文回顾：
+「
+{previously_on_story}
+」
+
+你是一个作家，我们正在互相讨论，确定后续剧情的发展。
+现在，故事该结束了，我认为最合理的故事结局是：{user_choice}。
+
+请在前文的基础上（不要重复前文），编写小说的最后一幕。
+
+- 不要重复前文。
+- 出现人物时，给出人物的名字。
+- 积极地运用环境描写、人物描写等手法，让读者能够感受到你的故事世界。
+- 积极地运用修辞手法，比如比喻、拟人、排比、对偶、夸张等等。
+- 字数要求：最后一幕的字数少于1000字。
+"""
+
+
+from toolbox import CatchException, update_ui, update_ui_lastest_msg
+from crazy_functions.multi_stage.multi_stage_utils import GptAcademicGameBaseState
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+from request_llms.bridge_all import predict_no_ui_long_connection
+from crazy_functions.game_fns.game_utils import get_code_block, is_same_thing
+import random
+
+
+class MiniGame_ResumeStory(GptAcademicGameBaseState):
+    story_headstart = [
+        '先行者知道，他现在是全宇宙中唯一的一个人了。',
+        '深夜，一个年轻人穿过天安门广场向纪念堂走去。在二十二世纪编年史中，计算机把他的代号定为M102。',
+        '他知道，这最后一课要提前讲了。又一阵剧痛从肝部袭来，几乎使他晕厥过去。',
+        '在距地球五万光年的远方，在银河系的中心，一场延续了两万年的星际战争已接近尾声。那里的太空中渐渐隐现出一个方形区域，仿佛灿烂的群星的背景被剪出一个方口。',
+        '伊依一行三人乘坐一艘游艇在南太平洋上做吟诗航行，他们的目的地是南极，如果几天后能顺利到达那里，他们将钻出地壳去看诗云。',
+        '很多人生来就会莫名其妙地迷上一样东西，仿佛他的出生就是要和这东西约会似的，正是这样，圆圆迷上了肥皂泡。'
+    ]
+
+
+    def begin_game_step_0(self, prompt, chatbot, history):
+        # init game at step 0
+        self.headstart = random.choice(self.story_headstart)
+        self.story = []
+        chatbot.append(["互动写故事", f"这次的故事开头是：{self.headstart}"])
+        self.sys_prompt_ = '你是一个想象力丰富的杰出作家。正在与你的朋友互动，一起写故事，因此你每次写的故事段落应少于300字（结局除外）。'
+        
+        
+    def generate_story_image(self, story_paragraph):
+        try:
+            from crazy_functions.图片生成 import gen_image
+            prompt_ = predict_no_ui_long_connection(inputs=story_paragraph, llm_kwargs=self.llm_kwargs, history=[], sys_prompt='你需要根据用户给出的小说段落，进行简短的环境描写。要求：80字以内。')
+            image_url, image_path = gen_image(self.llm_kwargs, prompt_, '512x512', model="dall-e-2", quality='standard', style='natural')
+            return f'<br/><div align="center"><img src="file={image_path}"></div>'
+        except:
+            return ''
+        
+    def step(self, prompt, chatbot, history):
+        
+        """
+        首先，处理游戏初始化等特殊情况
+        """
+        if self.step_cnt == 0:  
+            self.begin_game_step_0(prompt, chatbot, history)
+            self.lock_plugin(chatbot)
+            self.cur_task = 'head_start'
+        else:
+            if prompt.strip() == 'exit' or prompt.strip() == '结束剧情':
+                # should we terminate game here?
+                self.delete_game = True
+                yield from update_ui_lastest_msg(lastmsg=f"游戏结束。", chatbot=chatbot, history=history, delay=0.)
+                return
+            if '剧情收尾' in prompt:
+                self.cur_task = 'story_terminate'
+            # # well, game resumes
+            # chatbot.append([prompt, ""])
+        # update ui, don't keep the user waiting
+        yield from update_ui(chatbot=chatbot, history=history)
+
+
+        """
+        处理游戏的主体逻辑
+        """
+        if self.cur_task == 'head_start':
+            """
+            这是游戏的第一步
+            """
+            inputs_ = prompts_hs.format(headstart=self.headstart)
+            history_ = []
+            story_paragraph = yield from request_gpt_model_in_new_thread_with_ui_alive(
+                inputs_, '故事开头', self.llm_kwargs, 
+                chatbot, history_, self.sys_prompt_
+            )
+            self.story.append(story_paragraph)
+            # # 配图
+            yield from update_ui_lastest_msg(lastmsg=story_paragraph + '<br/>正在生成插图中 ...', chatbot=chatbot, history=history, delay=0.)
+            yield from update_ui_lastest_msg(lastmsg=story_paragraph + '<br/>'+ self.generate_story_image(story_paragraph), chatbot=chatbot, history=history, delay=0.)
+
+            # # 构建后续剧情引导
+            previously_on_story = ""
+            for s in self.story:
+                previously_on_story += s + '\n'
+            inputs_ = prompts_interact.format(previously_on_story=previously_on_story)
+            history_ = []
+            self.next_choices = yield from request_gpt_model_in_new_thread_with_ui_alive(
+                inputs_, '请在以下几种故事走向中，选择一种（当然，您也可以选择给出其他故事走向）：', self.llm_kwargs, 
+                chatbot,
+                history_,
+                self.sys_prompt_
+            )
+            self.cur_task = 'user_choice'
+
+
+        elif self.cur_task == 'user_choice':
+            """
+            根据用户的提示，确定故事的下一步
+            """
+            if '请在以下几种故事走向中，选择一种' in chatbot[-1][0]: chatbot.pop(-1)
+            previously_on_story = ""
+            for s in self.story:
+                previously_on_story += s + '\n'
+            inputs_ = prompts_resume.format(previously_on_story=previously_on_story, choice=self.next_choices, user_choice=prompt)
+            history_ = []
+            story_paragraph = yield from request_gpt_model_in_new_thread_with_ui_alive(
+                inputs_, f'下一段故事（您的选择是：{prompt}）。', self.llm_kwargs, 
+                chatbot, history_, self.sys_prompt_
+            )
+            self.story.append(story_paragraph)
+            # # 配图
+            yield from update_ui_lastest_msg(lastmsg=story_paragraph + '<br/>正在生成插图中 ...', chatbot=chatbot, history=history, delay=0.)
+            yield from update_ui_lastest_msg(lastmsg=story_paragraph + '<br/>'+ self.generate_story_image(story_paragraph), chatbot=chatbot, history=history, delay=0.)
+
+            # # 构建后续剧情引导
+            previously_on_story = ""
+            for s in self.story:
+                previously_on_story += s + '\n'
+            inputs_ = prompts_interact.format(previously_on_story=previously_on_story)
+            history_ = []
+            self.next_choices = yield from request_gpt_model_in_new_thread_with_ui_alive(
+                inputs_, 
+                '请在以下几种故事走向中，选择一种。当然，您也可以给出您心中的其他故事走向。另外，如果您希望剧情立即收尾，请输入剧情走向，并以“剧情收尾”四个字提示程序。', self.llm_kwargs, 
+                chatbot, 
+                history_, 
+                self.sys_prompt_
+            )
+            self.cur_task = 'user_choice'
+
+
+        elif self.cur_task == 'story_terminate':
+            """
+            根据用户的提示，确定故事的结局
+            """
+            previously_on_story = ""
+            for s in self.story:
+                previously_on_story += s + '\n'
+            inputs_ = prompts_terminate.format(previously_on_story=previously_on_story, user_choice=prompt)
+            history_ = []
+            story_paragraph = yield from request_gpt_model_in_new_thread_with_ui_alive(
+                inputs_, f'故事收尾（您的选择是：{prompt}）。', self.llm_kwargs, 
+                chatbot, history_, self.sys_prompt_
+            )
+            # # 配图
+            yield from update_ui_lastest_msg(lastmsg=story_paragraph + '<br/>正在生成插图中 ...', chatbot=chatbot, history=history, delay=0.)
+            yield from update_ui_lastest_msg(lastmsg=story_paragraph + '<br/>'+ self.generate_story_image(story_paragraph), chatbot=chatbot, history=history, delay=0.)
+
+            # terminate game
+            self.delete_game = True
+            return

crazy_functions/ipc_fns/mp.py

@@ -0,0 +1,37 @@
+import platform 
+import pickle
+import multiprocessing
+
+def run_in_subprocess_wrapper_func(v_args):
+    func, args, kwargs, return_dict, exception_dict = pickle.loads(v_args)
+    import sys
+    try:
+        result = func(*args, **kwargs)
+        return_dict['result'] = result
+    except Exception as e:
+        exc_info = sys.exc_info()
+        exception_dict['exception'] = exc_info
+
+def run_in_subprocess_with_timeout(func, timeout=60):
+    if platform.system() == 'Linux':
+        def wrapper(*args, **kwargs):
+            return_dict = multiprocessing.Manager().dict()
+            exception_dict = multiprocessing.Manager().dict()
+            v_args = pickle.dumps((func, args, kwargs, return_dict, exception_dict))
+            process = multiprocessing.Process(target=run_in_subprocess_wrapper_func, args=(v_args,))
+            process.start()
+            process.join(timeout)
+            if process.is_alive():
+                process.terminate()
+                raise TimeoutError(f'功能单元{str(func)}未能在规定时间内完成任务')
+            process.close()
+            if 'exception' in exception_dict:
+                # ooops, the subprocess ran into an exception
+                exc_info = exception_dict['exception']
+                raise exc_info[1].with_traceback(exc_info[2])
+            if 'result' in return_dict.keys():
+                # If the subprocess ran successfully, return the result
+                return return_dict['result']
+        return wrapper
+    else:
+        return func

crazy_functions/latex_fns/latex_actions.py

@@ -175,7 +175,6 @@ class LatexPaperFileGroup():
         self.sp_file_contents = []
         self.sp_file_index = []
         self.sp_file_tag = []
-
         # count_token
         from request_llms.bridge_all import model_info
         enc = model_info["gpt-3.5-turbo"]['tokenizer']
@@ -192,13 +191,12 @@ class LatexPaperFileGroup():
                 self.sp_file_index.append(index)
                 self.sp_file_tag.append(self.file_paths[index])
             else:
-                from ..crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
-                segments = breakdown_txt_to_satisfy_token_limit_for_pdf(file_content, self.get_token_num, max_token_limit)
+                from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
+                segments = breakdown_text_to_satisfy_token_limit(file_content, max_token_limit)
                 for j, segment in enumerate(segments):
                     self.sp_file_contents.append(segment)
                     self.sp_file_index.append(index)
                     self.sp_file_tag.append(self.file_paths[index] + f".part-{j}.tex")
-        print('Segmentation: done')
 
     def merge_result(self):
         self.file_result = ["" for _ in range(len(self.file_paths))]
@@ -404,7 +402,7 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
             result_pdf = pj(work_folder_modified, f'merge_diff.pdf')    # get pdf path
             promote_file_to_downloadzone(result_pdf, rename_file=None, chatbot=chatbot)  # promote file to web UI
         if modified_pdf_success:
-            yield from update_ui_lastest_msg(f'转化PDF编译已经成功, 即将退出 ...', chatbot, history)    # 刷新Gradio前端界面
+            yield from update_ui_lastest_msg(f'转化PDF编译已经成功, 正在尝试生成对比PDF, 请稍候 ...', chatbot, history)    # 刷新Gradio前端界面
             result_pdf = pj(work_folder_modified, f'{main_file_modified}.pdf') # get pdf path
             origin_pdf = pj(work_folder_original, f'{main_file_original}.pdf') # get pdf path
             if os.path.exists(pj(work_folder, '..', 'translation')):

crazy_functions/pdf_fns/breakdown_txt.py

@@ -0,0 +1,125 @@
+from crazy_functions.ipc_fns.mp import run_in_subprocess_with_timeout
+
+def force_breakdown(txt, limit, get_token_fn):
+    """ 当无法用标点、空行分割时，我们用最暴力的方法切割
+    """
+    for i in reversed(range(len(txt))):
+        if get_token_fn(txt[:i]) < limit:
+            return txt[:i], txt[i:]
+    return "Tiktoken未知错误", "Tiktoken未知错误"
+
+
+def maintain_storage(remain_txt_to_cut, remain_txt_to_cut_storage):
+    """ 为了加速计算，我们采样一个特殊的手段。当 remain_txt_to_cut > `_max` 时， 我们把 _max 后的文字转存至 remain_txt_to_cut_storage
+    当 remain_txt_to_cut < `_min` 时，我们再把 remain_txt_to_cut_storage 中的部分文字取出
+    """
+    _min = int(5e4)
+    _max = int(1e5)
+    # print(len(remain_txt_to_cut), len(remain_txt_to_cut_storage))
+    if len(remain_txt_to_cut) < _min and len(remain_txt_to_cut_storage) > 0:
+        remain_txt_to_cut = remain_txt_to_cut + remain_txt_to_cut_storage
+        remain_txt_to_cut_storage = ""
+    if len(remain_txt_to_cut) > _max:
+        remain_txt_to_cut_storage = remain_txt_to_cut[_max:] + remain_txt_to_cut_storage
+        remain_txt_to_cut = remain_txt_to_cut[:_max]
+    return remain_txt_to_cut, remain_txt_to_cut_storage
+
+
+def cut(limit, get_token_fn, txt_tocut, must_break_at_empty_line, break_anyway=False):
+    """ 文本切分
+    """
+    res = []
+    total_len = len(txt_tocut)
+    fin_len = 0
+    remain_txt_to_cut = txt_tocut
+    remain_txt_to_cut_storage = ""
+    # 为了加速计算，我们采样一个特殊的手段。当 remain_txt_to_cut > `_max` 时， 我们把 _max 后的文字转存至 remain_txt_to_cut_storage
+    remain_txt_to_cut, remain_txt_to_cut_storage = maintain_storage(remain_txt_to_cut, remain_txt_to_cut_storage)
+    
+    while True:
+        if get_token_fn(remain_txt_to_cut) <= limit:
+            # 如果剩余文本的token数小于限制，那么就不用切了
+            res.append(remain_txt_to_cut); fin_len+=len(remain_txt_to_cut)
+            break
+        else:
+            # 如果剩余文本的token数大于限制，那么就切
+            lines = remain_txt_to_cut.split('\n')
+
+            # 估计一个切分点
+            estimated_line_cut = limit / get_token_fn(remain_txt_to_cut) * len(lines)
+            estimated_line_cut = int(estimated_line_cut)
+
+            # 开始查找合适切分点的偏移（cnt）
+            cnt = 0
+            for cnt in reversed(range(estimated_line_cut)):
+                if must_break_at_empty_line:
+                    # 首先尝试用双空行（\n\n）作为切分点
+                    if lines[cnt] != "":
+                        continue
+                prev = "\n".join(lines[:cnt])
+                post = "\n".join(lines[cnt:])
+                if get_token_fn(prev) < limit:
+                    break
+
+            if cnt == 0:
+                # 如果没有找到合适的切分点
+                if break_anyway:
+                    # 是否允许暴力切分
+                    prev, post = force_breakdown(txt_tocut, limit, get_token_fn)
+                else:
+                    # 不允许直接报错
+                    raise RuntimeError(f"存在一行极长的文本！{txt_tocut}")
+
+            # 追加列表
+            res.append(prev); fin_len+=len(prev)
+            # 准备下一次迭代
+            remain_txt_to_cut = post
+            remain_txt_to_cut, remain_txt_to_cut_storage = maintain_storage(remain_txt_to_cut, remain_txt_to_cut_storage)
+            process = fin_len/total_len
+            print(f'正在文本切分 {int(process*100)}%')
+            if len(remain_txt_to_cut.strip()) == 0:
+                break
+    return res
+
+
+def breakdown_text_to_satisfy_token_limit_(txt, limit, llm_model="gpt-3.5-turbo"):
+    """ 使用多种方式尝试切分文本，以满足 token 限制
+    """
+    from request_llms.bridge_all import model_info
+    enc = model_info[llm_model]['tokenizer']
+    def get_token_fn(txt): return len(enc.encode(txt, disallowed_special=()))
+    try:
+        # 第1次尝试，将双空行（\n\n）作为切分点
+        return cut(limit, get_token_fn, txt, must_break_at_empty_line=True)
+    except RuntimeError:
+        try:
+            # 第2次尝试，将单空行（\n）作为切分点
+            return cut(limit, get_token_fn, txt, must_break_at_empty_line=False)
+        except RuntimeError:
+            try:
+                # 第3次尝试，将英文句号（.）作为切分点
+                res = cut(limit, get_token_fn, txt.replace('.', '。\n'), must_break_at_empty_line=False) # 这个中文的句号是故意的，作为一个标识而存在
+                return [r.replace('。\n', '.') for r in res]
+            except RuntimeError as e:
+                try:
+                    # 第4次尝试，将中文句号（。）作为切分点
+                    res = cut(limit, get_token_fn, txt.replace('。', '。。\n'), must_break_at_empty_line=False)
+                    return [r.replace('。。\n', '。') for r in res]
+                except RuntimeError as e:
+                    # 第5次尝试，没办法了，随便切一下吧
+                    return cut(limit, get_token_fn, txt, must_break_at_empty_line=False, break_anyway=True)
+
+breakdown_text_to_satisfy_token_limit = run_in_subprocess_with_timeout(breakdown_text_to_satisfy_token_limit_, timeout=60)
+
+if __name__ == '__main__':
+    from crazy_functions.crazy_utils import read_and_clean_pdf_text
+    file_content, page_one = read_and_clean_pdf_text("build/assets/at.pdf")
+
+    from request_llms.bridge_all import model_info
+    for i in range(5):
+        file_content += file_content
+
+    print(len(file_content))
+    TOKEN_LIMIT_PER_FRAGMENT = 2500
+    res = breakdown_text_to_satisfy_token_limit(file_content, TOKEN_LIMIT_PER_FRAGMENT)
+

crazy_functions/pdf_fns/parse_pdf.py

@@ -74,7 +74,7 @@ def produce_report_markdown(gpt_response_collection, meta, paper_meta_info, chat
 
 def translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_files, TOKEN_LIMIT_PER_FRAGMENT, DST_LANG):
     from crazy_functions.pdf_fns.report_gen_html import construct_html
-    from crazy_functions.crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
+    from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
     from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
     from crazy_functions.crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
 
@@ -116,7 +116,7 @@ def translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_fi
             # find a smooth token limit to achieve even seperation
             count = int(math.ceil(raw_token_num / TOKEN_LIMIT_PER_FRAGMENT))
             token_limit_smooth = raw_token_num // count + count
-            return breakdown_txt_to_satisfy_token_limit_for_pdf(txt, get_token_fn=get_token_num, limit=token_limit_smooth)
+            return breakdown_text_to_satisfy_token_limit(txt, limit=token_limit_smooth, llm_model=llm_kwargs['llm_model'])
 
     for section in article_dict.get('sections'):
         if len(section['text']) == 0: continue

crazy_functions/互动小游戏.py

@@ -3,47 +3,28 @@ from crazy_functions.multi_stage.multi_stage_utils import GptAcademicGameBaseSta
 from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 from request_llms.bridge_all import predict_no_ui_long_connection
 from crazy_functions.game_fns.game_utils import get_code_block, is_same_thing
-import random
-
-
-class MiniGame_ASCII_Art(GptAcademicGameBaseState):
-    
-    def step(self, prompt, chatbot, history):
-        if self.step_cnt == 0:  
-            chatbot.append(["我画你猜（动物）", "请稍等..."])
-        else:
-            if prompt.strip() == 'exit':
-                self.delete_game = True
-                yield from update_ui_lastest_msg(lastmsg=f"谜底是{self.obj}，游戏结束。", chatbot=chatbot, history=history, delay=0.)
-                return
-            chatbot.append([prompt, ""])
-        yield from update_ui(chatbot=chatbot, history=history)
-
-        if self.step_cnt == 0:
-            self.lock_plugin(chatbot)
-            self.cur_task = 'draw'
-
-        if self.cur_task == 'draw':
-            avail_obj = ["狗","猫","鸟","鱼","老鼠","蛇"]
-            self.obj = random.choice(avail_obj)
-            inputs = "I want to play a game called Guess the ASCII art. You can draw the ASCII art and I will try to guess it. " + f"This time you draw a {self.obj}. Note that you must not indicate what you have draw in the text, and you should only produce the ASCII art wrapped by ```. "
-            raw_res = predict_no_ui_long_connection(inputs=inputs, llm_kwargs=self.llm_kwargs, history=[], sys_prompt="")
-            self.cur_task = 'identify user guess'
-            res = get_code_block(raw_res)
-            history += ['', f'the answer is {self.obj}', inputs, res]
-            yield from update_ui_lastest_msg(lastmsg=res, chatbot=chatbot, history=history, delay=0.)
-
-        elif self.cur_task == 'identify user guess':
-            if is_same_thing(self.obj, prompt, self.llm_kwargs):
-                self.delete_game = True
-                yield from update_ui_lastest_msg(lastmsg="你猜对了！", chatbot=chatbot, history=history, delay=0.)
-            else:
-                self.cur_task = 'identify user guess'
-                yield from update_ui_lastest_msg(lastmsg="猜错了，再试试，输入“exit”获取答案。", chatbot=chatbot, history=history, delay=0.)
-            
 
 @CatchException
 def 随机小游戏(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+    from crazy_functions.game_fns.game_interactive_story import MiniGame_ResumeStory
+    # 清空历史
+    history = []
+    # 选择游戏
+    cls = MiniGame_ResumeStory
+    # 如果之前已经初始化了游戏实例，则继续该实例；否则重新初始化
+    state = cls.sync_state(chatbot, 
+                           llm_kwargs, 
+                           cls, 
+                           plugin_name='MiniGame_ResumeStory',
+                           callback_fn='crazy_functions.互动小游戏->随机小游戏',
+                           lock_plugin=True
+                           )
+    yield from state.continue_game(prompt, chatbot, history)
+
+
+@CatchException
+def 随机小游戏1(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+    from crazy_functions.game_fns.game_ascii_art import MiniGame_ASCII_Art
     # 清空历史
     history = []
     # 选择游戏
@@ -53,7 +34,7 @@ def 随机小游戏(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system_
                            llm_kwargs, 
                            cls, 
                            plugin_name='MiniGame_ASCII_Art',
-                           callback_fn='crazy_functions.互动小游戏->随机小游戏',
+                           callback_fn='crazy_functions.互动小游戏->随机小游戏1',
                            lock_plugin=True
                            )
     yield from state.continue_game(prompt, chatbot, history)

crazy_functions/总结word文档.py

@@ -29,17 +29,12 @@ def 解析docx(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot
             except:
                 raise RuntimeError('请先将.doc文档转换为.docx文档。')
 
-        print(file_content)
         # private_upload里面的文件名在解压zip后容易出现乱码（rar和7z格式正常），故可以只分析文章内容，不输入文件名
-        from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
+        from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
         from request_llms.bridge_all import model_info
         max_token = model_info[llm_kwargs['llm_model']]['max_token']
         TOKEN_LIMIT_PER_FRAGMENT = max_token * 3 // 4
-        paper_fragments = breakdown_txt_to_satisfy_token_limit_for_pdf(
-            txt=file_content,  
-            get_token_fn=model_info[llm_kwargs['llm_model']]['token_cnt'], 
-            limit=TOKEN_LIMIT_PER_FRAGMENT
-        )
+        paper_fragments = breakdown_text_to_satisfy_token_limit(txt=file_content, limit=TOKEN_LIMIT_PER_FRAGMENT, llm_model=llm_kwargs['llm_model'])
         this_paper_history = []
         for i, paper_frag in enumerate(paper_fragments):
             i_say = f'请对下面的文章片段用中文做概述，文件名是{os.path.relpath(fp, project_folder)}，文章内容是 ```{paper_frag}```'

crazy_functions/批量Markdown翻译.py

@@ -28,8 +28,8 @@ class PaperFileGroup():
                 self.sp_file_index.append(index)
                 self.sp_file_tag.append(self.file_paths[index])
             else:
-                from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
-                segments = breakdown_txt_to_satisfy_token_limit_for_pdf(file_content, self.get_token_num, max_token_limit)
+                from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
+                segments = breakdown_text_to_satisfy_token_limit(file_content, max_token_limit)
                 for j, segment in enumerate(segments):
                     self.sp_file_contents.append(segment)
                     self.sp_file_index.append(index)

crazy_functions/批量总结PDF文档.py

@@ -20,14 +20,9 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
         
         TOKEN_LIMIT_PER_FRAGMENT = 2500
 
-        from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
-        from request_llms.bridge_all import model_info
-        enc = model_info["gpt-3.5-turbo"]['tokenizer']
-        def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
-        paper_fragments = breakdown_txt_to_satisfy_token_limit_for_pdf(
-            txt=file_content,  get_token_fn=get_token_num, limit=TOKEN_LIMIT_PER_FRAGMENT)
-        page_one_fragments = breakdown_txt_to_satisfy_token_limit_for_pdf(
-            txt=str(page_one), get_token_fn=get_token_num, limit=TOKEN_LIMIT_PER_FRAGMENT//4)
+        from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
+        paper_fragments = breakdown_text_to_satisfy_token_limit(txt=file_content,  limit=TOKEN_LIMIT_PER_FRAGMENT, llm_model=llm_kwargs['llm_model'])
+        page_one_fragments = breakdown_text_to_satisfy_token_limit(txt=str(page_one), limit=TOKEN_LIMIT_PER_FRAGMENT//4, llm_model=llm_kwargs['llm_model'])
         # 为了更好的效果，我们剥离Introduction之后的部分（如果有）
         paper_meta = page_one_fragments[0].split('introduction')[0].split('Introduction')[0].split('INTRODUCTION')[0]
         

crazy_functions/批量翻译PDF文档_多线程.py

@@ -91,14 +91,9 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
         page_one = str(page_one).encode('utf-8', 'ignore').decode()      # avoid reading non-utf8 chars
 
         # 递归地切割PDF文件
-        from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
-        from request_llms.bridge_all import model_info
-        enc = model_info["gpt-3.5-turbo"]['tokenizer']
-        def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
-        paper_fragments = breakdown_txt_to_satisfy_token_limit_for_pdf(
-            txt=file_content,  get_token_fn=get_token_num, limit=TOKEN_LIMIT_PER_FRAGMENT)
-        page_one_fragments = breakdown_txt_to_satisfy_token_limit_for_pdf(
-            txt=page_one, get_token_fn=get_token_num, limit=TOKEN_LIMIT_PER_FRAGMENT//4)
+        from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
+        paper_fragments = breakdown_text_to_satisfy_token_limit(txt=file_content, limit=TOKEN_LIMIT_PER_FRAGMENT, llm_model=llm_kwargs['llm_model'])
+        page_one_fragments = breakdown_text_to_satisfy_token_limit(txt=page_one, limit=TOKEN_LIMIT_PER_FRAGMENT//4, llm_model=llm_kwargs['llm_model'])
 
         # 为了更好的效果，我们剥离Introduction之后的部分（如果有）
         paper_meta = page_one_fragments[0].split('introduction')[0].split('Introduction')[0].split('INTRODUCTION')[0]

crazy_functions/理解PDF文档内容.py

@@ -18,14 +18,9 @@ def 解析PDF(file_name, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
     
     TOKEN_LIMIT_PER_FRAGMENT = 2500
 
-    from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
-    from request_llms.bridge_all import model_info
-    enc = model_info["gpt-3.5-turbo"]['tokenizer']
-    def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
-    paper_fragments = breakdown_txt_to_satisfy_token_limit_for_pdf(
-        txt=file_content,  get_token_fn=get_token_num, limit=TOKEN_LIMIT_PER_FRAGMENT)
-    page_one_fragments = breakdown_txt_to_satisfy_token_limit_for_pdf(
-        txt=str(page_one), get_token_fn=get_token_num, limit=TOKEN_LIMIT_PER_FRAGMENT//4)
+    from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
+    paper_fragments = breakdown_text_to_satisfy_token_limit(txt=file_content, limit=TOKEN_LIMIT_PER_FRAGMENT, llm_model=llm_kwargs['llm_model'])
+    page_one_fragments = breakdown_text_to_satisfy_token_limit(txt=str(page_one), limit=TOKEN_LIMIT_PER_FRAGMENT//4, llm_model=llm_kwargs['llm_model'])
     # 为了更好的效果，我们剥离Introduction之后的部分（如果有）
     paper_meta = page_one_fragments[0].split('introduction')[0].split('Introduction')[0].split('INTRODUCTION')[0]
     
@@ -45,7 +40,7 @@ def 解析PDF(file_name, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
     for i in range(n_fragment):
         NUM_OF_WORD = MAX_WORD_TOTAL // n_fragment
         i_say = f"Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words: {paper_fragments[i]}"
-        i_say_show_user = f"[{i+1}/{n_fragment}] Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words: {paper_fragments[i][:200]}"
+        i_say_show_user = f"[{i+1}/{n_fragment}] Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words: {paper_fragments[i][:200]} ...."
         gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(i_say, i_say_show_user,  # i_say=真正给chatgpt的提问， i_say_show_user=给用户看的提问
                                                                            llm_kwargs, chatbot, 
                                                                            history=["The main idea of the previous section is?", last_iteration_result], # 迭代上一次的结果

crazy_functions/解析JupyterNotebook.py

@@ -12,13 +12,6 @@ class PaperFileGroup():
         self.sp_file_index = []
         self.sp_file_tag = []
 
-        # count_token
-        from request_llms.bridge_all import model_info
-        enc = model_info["gpt-3.5-turbo"]['tokenizer']
-        def get_token_num(txt): return len(
-            enc.encode(txt, disallowed_special=()))
-        self.get_token_num = get_token_num
-
     def run_file_split(self, max_token_limit=1900):
         """
         将长文本分离开来
@@ -29,9 +22,8 @@ class PaperFileGroup():
                 self.sp_file_index.append(index)
                 self.sp_file_tag.append(self.file_paths[index])
             else:
-                from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
-                segments = breakdown_txt_to_satisfy_token_limit_for_pdf(
-                    file_content, self.get_token_num, max_token_limit)
+                from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
+                segments = breakdown_text_to_satisfy_token_limit(file_content, max_token_limit)
                 for j, segment in enumerate(segments):
                     self.sp_file_contents.append(segment)
                     self.sp_file_index.append(index)

docs/GithubAction+AllCapacityBeta

@@ -0,0 +1,53 @@
+# docker build -t gpt-academic-all-capacity -f docs/GithubAction+AllCapacity  --network=host --build-arg http_proxy=http://localhost:10881 --build-arg https_proxy=http://localhost:10881 .
+# docker build -t gpt-academic-all-capacity -f docs/GithubAction+AllCapacityBeta  --network=host .
+# docker run -it --net=host gpt-academic-all-capacity  bash
+
+# 从NVIDIA源，从而支持显卡（检查宿主的nvidia-smi中的cuda版本必须>=11.3）
+FROM fuqingxu/11.3.1-runtime-ubuntu20.04-with-texlive:latest
+
+# use python3 as the system default python
+WORKDIR /gpt
+RUN curl -sS https://bootstrap.pypa.io/get-pip.py | python3.8
+
+# # 非必要步骤，更换pip源 （以下三行，可以删除）
+# RUN echo '[global]' > /etc/pip.conf && \
+#     echo 'index-url = https://mirrors.aliyun.com/pypi/simple/' >> /etc/pip.conf && \
+#     echo 'trusted-host = mirrors.aliyun.com' >> /etc/pip.conf
+
+# 下载pytorch
+RUN python3 -m pip install torch torchvision --extra-index-url https://download.pytorch.org/whl/cu113
+# 准备pip依赖
+RUN python3 -m pip install openai numpy arxiv rich
+RUN python3 -m pip install colorama Markdown pygments pymupdf
+RUN python3 -m pip install python-docx moviepy pdfminer
+RUN python3 -m pip install zh_langchain==0.2.1 pypinyin
+RUN python3 -m pip install rarfile py7zr
+RUN python3 -m pip install aliyun-python-sdk-core==2.13.3 pyOpenSSL webrtcvad scipy git+https://github.com/aliyun/alibabacloud-nls-python-sdk.git
+# 下载分支
+WORKDIR /gpt
+RUN git clone --depth=1 https://github.com/binary-husky/gpt_academic.git
+WORKDIR /gpt/gpt_academic
+RUN git clone --depth=1 https://github.com/OpenLMLab/MOSS.git request_llms/moss
+
+RUN python3 -m pip install -r requirements.txt
+RUN python3 -m pip install -r request_llms/requirements_moss.txt
+RUN python3 -m pip install -r request_llms/requirements_qwen.txt
+RUN python3 -m pip install -r request_llms/requirements_chatglm.txt
+RUN python3 -m pip install -r request_llms/requirements_newbing.txt
+RUN python3 -m pip install nougat-ocr
+
+# 预热Tiktoken模块
+RUN python3  -c 'from check_proxy import warm_up_modules; warm_up_modules()'
+
+# 安装知识库插件的额外依赖
+RUN apt-get update && apt-get install libgl1 -y
+RUN pip3 install transformers protobuf langchain sentence-transformers  faiss-cpu nltk beautifulsoup4 bitsandbytes tabulate icetk --upgrade
+RUN pip3 install unstructured[all-docs] --upgrade
+RUN python3  -c 'from check_proxy import warm_up_vectordb; warm_up_vectordb()'
+RUN rm -rf /usr/local/lib/python3.8/dist-packages/tests
+
+
+# COPY .cache /root/.cache
+# COPY config_private.py config_private.py
+# 启动
+CMD ["python3", "-u", "main.py"]

docs/GithubAction+NoLocal+Vectordb

@@ -17,10 +17,10 @@ RUN apt-get update && apt-get install libgl1 -y
 RUN pip3 install torch torchvision --index-url https://download.pytorch.org/whl/cpu
 RUN pip3 install transformers protobuf langchain sentence-transformers  faiss-cpu nltk beautifulsoup4 bitsandbytes tabulate icetk --upgrade
 RUN pip3 install unstructured[all-docs] --upgrade
+RUN python3  -c 'from check_proxy import warm_up_vectordb; warm_up_vectordb()'
 
 # 可选步骤，用于预热模块
 RUN python3  -c 'from check_proxy import warm_up_modules; warm_up_modules()'
-RUN python3  -c 'from check_proxy import warm_up_vectordb; warm_up_vectordb()'
 
 # 启动
 CMD ["python3", "-u", "main.py"]

docs/translate_english.json

@@ -2863,7 +2863,7 @@
     "加载API_KEY": "Loading API_KEY",
     "协助您编写代码": "Assist you in writing code",
     "我可以为您提供以下服务": "I can provide you with the following services",
-    "排队中请稍后 ...": "Please wait in line ...",
+    "排队中请稍候 ...": "Please wait in line ...",
     "建议您使用英文提示词": "It is recommended to use English prompts",
     "不能支撑AutoGen运行": "Cannot support AutoGen operation",
     "帮助您解决编程问题": "Help you solve programming problems",

main.py

@@ -1,6 +1,17 @@
 import os; os.environ['no_proxy'] = '*' # 避免代理网络产生意外污染
-import pickle
-import base64
+
+help_menu_description = \
+"""Github源代码开源和更新[地址🚀](https://github.com/binary-husky/gpt_academic), 
+感谢热情的[开发者们❤️](https://github.com/binary-husky/gpt_academic/graphs/contributors).
+</br></br>常见问题请查阅[项目Wiki](https://github.com/binary-husky/gpt_academic/wiki), 
+如遇到Bug请前往[Bug反馈](https://github.com/binary-husky/gpt_academic/issues).
+</br></br>普通对话使用说明: 1. 输入问题; 2. 点击提交
+</br></br>基础功能区使用说明: 1. 输入文本; 2. 点击任意基础功能区按钮
+</br></br>函数插件区使用说明: 1. 输入路径/问题, 或者上传文件; 2. 点击任意函数插件区按钮
+</br></br>虚空终端使用说明: 点击虚空终端, 然后根据提示输入指令, 再次点击虚空终端
+</br></br>如何保存对话: 点击保存当前的对话按钮
+</br></br>如何语音对话: 请阅读Wiki
+</br></br>如何临时更换API_KEY: 在输入区输入临时API_KEY后提交（网页刷新后失效）"""
 
 def main():
     import gradio as gr
@@ -8,7 +19,7 @@ def main():
         raise ModuleNotFoundError("使用项目内置Gradio获取最优体验! 请运行 `pip install -r requirements.txt` 指令安装内置Gradio及其他依赖, 详情信息见requirements.txt.")
     from request_llms.bridge_all import predict
     from toolbox import format_io, find_free_port, on_file_uploaded, on_report_generated, get_conf, ArgsGeneralWrapper, load_chat_cookies, DummyWith
-    # 建议您复制一个config_private.py放自己的秘密, 如API和代理网址, 避免不小心传github被别人看到
+    # 建议您复制一个config_private.py放自己的秘密, 如API和代理网址
     proxies, WEB_PORT, LLM_MODEL, CONCURRENT_COUNT, AUTHENTICATION = get_conf('proxies', 'WEB_PORT', 'LLM_MODEL', 'CONCURRENT_COUNT', 'AUTHENTICATION')
     CHATBOT_HEIGHT, LAYOUT, AVAIL_LLM_MODELS, AUTO_CLEAR_TXT = get_conf('CHATBOT_HEIGHT', 'LAYOUT', 'AVAIL_LLM_MODELS', 'AUTO_CLEAR_TXT')
     ENABLE_AUDIO, AUTO_CLEAR_TXT, PATH_LOGGING, AVAIL_THEMES, THEME = get_conf('ENABLE_AUDIO', 'AUTO_CLEAR_TXT', 'PATH_LOGGING', 'AVAIL_THEMES', 'THEME')
@@ -18,21 +29,11 @@ def main():
     # 如果WEB_PORT是-1, 则随机选取WEB端口
     PORT = find_free_port() if WEB_PORT <= 0 else WEB_PORT
     from check_proxy import get_current_version
-    from themes.theme import adjust_theme, advanced_css, theme_declaration, load_dynamic_theme
-
+    from themes.theme import adjust_theme, advanced_css, theme_declaration
+    from themes.theme import js_code_for_css_changing, js_code_for_darkmode_init, js_code_for_toggle_darkmode, js_code_for_persistent_cookie_init
+    from themes.theme import load_dynamic_theme, to_cookie_str, from_cookie_str, init_cookie
     title_html = f"<h1 align=\"center\">GPT 学术优化 {get_current_version()}</h1>{theme_declaration}"
-    description =  "Github源代码开源和更新[地址🚀](https://github.com/binary-husky/gpt_academic), "
-    description += "感谢热情的[开发者们❤️](https://github.com/binary-husky/gpt_academic/graphs/contributors)."
-    description += "</br></br>常见问题请查阅[项目Wiki](https://github.com/binary-husky/gpt_academic/wiki), "
-    description += "如遇到Bug请前往[Bug反馈](https://github.com/binary-husky/gpt_academic/issues)."
-    description += "</br></br>普通对话使用说明: 1. 输入问题; 2. 点击提交"
-    description += "</br></br>基础功能区使用说明: 1. 输入文本; 2. 点击任意基础功能区按钮"
-    description += "</br></br>函数插件区使用说明: 1. 输入路径/问题, 或者上传文件; 2. 点击任意函数插件区按钮"
-    description += "</br></br>虚空终端使用说明: 点击虚空终端, 然后根据提示输入指令, 再次点击虚空终端"
-    description += "</br></br>如何保存对话: 点击保存当前的对话按钮"
-    description += "</br></br>如何语音对话: 请阅读Wiki"
-    description += "</br></br>如何临时更换API_KEY: 在输入区输入临时API_KEY后提交（网页刷新后失效）"
-
+    
     # 问询记录, python 版本建议3.9+（越新越好）
     import logging, uuid
     os.makedirs(PATH_LOGGING, exist_ok=True)
@@ -162,16 +163,10 @@ def main():
                     checkboxes_2 = gr.CheckboxGroup(["自定义菜单"], 
                                                   value=[], label="显示/隐藏自定义菜单", elem_id='cbs').style(container=False)
                     dark_mode_btn = gr.Button("切换界面明暗 ☀", variant="secondary").style(size="sm")
-                    dark_mode_btn.click(None, None, None, _js="""() => {
-                            if (document.querySelectorAll('.dark').length) {
-                                document.querySelectorAll('.dark').forEach(el => el.classList.remove('dark'));
-                            } else {
-                                document.querySelector('body').classList.add('dark');
-                            }
-                        }""",
+                    dark_mode_btn.click(None, None, None, _js=js_code_for_toggle_darkmode,
                     )
                 with gr.Tab("帮助", elem_id="interact-panel"):
-                    gr.Markdown(description)
+                    gr.Markdown(help_menu_description)
 
         with gr.Floating(init_x="20%", init_y="50%", visible=False, width="40%", drag="top") as area_input_secondary:
             with gr.Accordion("浮动输入区", open=True, elem_id="input-panel2"):
@@ -186,16 +181,6 @@ def main():
                         stopBtn2 = gr.Button("停止", variant="secondary"); stopBtn2.style(size="sm")
                         clearBtn2 = gr.Button("清除", variant="secondary", visible=False); clearBtn2.style(size="sm")
 
-        def to_cookie_str(d):
-            # Pickle the dictionary and encode it as a string
-            pickled_dict = pickle.dumps(d)
-            cookie_value = base64.b64encode(pickled_dict).decode('utf-8')
-            return cookie_value
-        
-        def from_cookie_str(c):
-            # Decode the base64-encoded string and unpickle it into a dictionary
-            pickled_dict = base64.b64decode(c.encode('utf-8'))
-            return pickle.loads(pickled_dict)
 
         with gr.Floating(init_x="20%", init_y="50%", visible=False, width="40%", drag="top") as area_customize:
             with gr.Accordion("自定义菜单", open=True, elem_id="edit-panel"):
@@ -227,11 +212,11 @@ def main():
                             else:
                                 ret.update({predefined_btns[basic_btn_dropdown_]: gr.update(visible=True, value=basic_fn_title)})
                             ret.update({cookies: cookies_})
-                            try: persistent_cookie_ = from_cookie_str(persistent_cookie_)    # persistent cookie to dict
+                            try: persistent_cookie_ = from_cookie_str(persistent_cookie_)   # persistent cookie to dict
                             except: persistent_cookie_ = {}
-                            persistent_cookie_["custom_bnt"] = customize_fn_overwrite_   # dict update new value
-                            persistent_cookie_ = to_cookie_str(persistent_cookie_)         # persistent cookie to dict
-                            ret.update({persistent_cookie: persistent_cookie_})                             # write persistent cookie
+                            persistent_cookie_["custom_bnt"] = customize_fn_overwrite_      # dict update new value
+                            persistent_cookie_ = to_cookie_str(persistent_cookie_)          # persistent cookie to dict
+                            ret.update({persistent_cookie: persistent_cookie_})             # write persistent cookie
                             return ret
                         
                         def reflesh_btn(persistent_cookie_, cookies_):
@@ -252,10 +237,11 @@ def main():
                                 else: ret.update({predefined_btns[k]: gr.update(visible=True, value=v['Title'])})
                             return ret
                         
-                        basic_fn_load.click(reflesh_btn, [persistent_cookie, cookies],[cookies, *customize_btns.values(), *predefined_btns.values()])
+                        basic_fn_load.click(reflesh_btn, [persistent_cookie, cookies], [cookies, *customize_btns.values(), *predefined_btns.values()])
                         h = basic_fn_confirm.click(assign_btn, [persistent_cookie, cookies, basic_btn_dropdown, basic_fn_title, basic_fn_prefix, basic_fn_suffix], 
                                                    [persistent_cookie, cookies, *customize_btns.values(), *predefined_btns.values()])
-                        h.then(None, [persistent_cookie], None, _js="""(persistent_cookie)=>{setCookie("persistent_cookie", persistent_cookie, 5);}""") # save persistent cookie
+                        # save persistent cookie
+                        h.then(None, [persistent_cookie], None, _js="""(persistent_cookie)=>{setCookie("persistent_cookie", persistent_cookie, 5);}""")
 
         # 功能区显示开关与功能区的互动
         def fn_area_visibility(a):
@@ -305,8 +291,8 @@ def main():
             click_handle = btn.click(fn=ArgsGeneralWrapper(predict), inputs=[*input_combo, gr.State(True), gr.State(btn.value)], outputs=output_combo)
             cancel_handles.append(click_handle)
         # 文件上传区，接收文件后与chatbot的互动
-        file_upload.upload(on_file_uploaded, [file_upload, chatbot, txt, txt2, checkboxes, cookies], [chatbot, txt, txt2, cookies])
-        file_upload_2.upload(on_file_uploaded, [file_upload_2, chatbot, txt, txt2, checkboxes, cookies], [chatbot, txt, txt2, cookies])
+        file_upload.upload(on_file_uploaded, [file_upload, chatbot, txt, txt2, checkboxes, cookies], [chatbot, txt, txt2, cookies]).then(None, None, None,   _js=r"()=>{toast_push('上传完毕 ...'); cancel_loading_status();}")
+        file_upload_2.upload(on_file_uploaded, [file_upload_2, chatbot, txt, txt2, checkboxes, cookies], [chatbot, txt, txt2, cookies]).then(None, None, None, _js=r"()=>{toast_push('上传完毕 ...'); cancel_loading_status();}")
         # 函数插件-固定按钮区
         for k in plugins:
             if not plugins[k].get("AsButton", True): continue
@@ -342,18 +328,7 @@ def main():
             None,
             [secret_css],
             None,
-            _js="""(css) => {
-                var existingStyles = document.querySelectorAll("style[data-loaded-css]");
-                for (var i = 0; i < existingStyles.length; i++) {
-                    var style = existingStyles[i];
-                    style.parentNode.removeChild(style);
-                }
-                var styleElement = document.createElement('style');
-                styleElement.setAttribute('data-loaded-css', css);
-                styleElement.innerHTML = css;
-                document.head.appendChild(styleElement);
-            }
-            """
+            _js=js_code_for_css_changing
         )
         # 随变按钮的回调函数注册
         def route(request: gr.Request, k, *args, **kwargs):
@@ -385,27 +360,10 @@ def main():
                 rad.feed(cookies['uuid'].hex, audio)
             audio_mic.stream(deal_audio, inputs=[audio_mic, cookies])
 
-        def init_cookie(cookies, chatbot):
-            # 为每一位访问的用户赋予一个独一无二的uuid编码
-            cookies.update({'uuid': uuid.uuid4()})
-            return cookies
+
         demo.load(init_cookie, inputs=[cookies, chatbot], outputs=[cookies])
-        darkmode_js = """(dark) => {
-            dark = dark == "True";
-            if (document.querySelectorAll('.dark').length) {
-                if (!dark){
-                    document.querySelectorAll('.dark').forEach(el => el.classList.remove('dark'));
-                }
-            } else {
-                if (dark){
-                    document.querySelector('body').classList.add('dark');
-                }
-            }
-        }"""
-        load_cookie_js = """(persistent_cookie) => {
-            return getCookie("persistent_cookie");
-        }"""
-        demo.load(None, inputs=None, outputs=[persistent_cookie], _js=load_cookie_js)
+        darkmode_js = js_code_for_darkmode_init
+        demo.load(None, inputs=None, outputs=[persistent_cookie], _js=js_code_for_persistent_cookie_init)
         demo.load(None, inputs=[dark_mode], outputs=None, _js=darkmode_js)    # 配置暗色主题或亮色主题
         demo.load(None, inputs=[gr.Textbox(LAYOUT, visible=False)], outputs=None, _js='(LAYOUT)=>{GptAcademicJavaScriptInit(LAYOUT);}')
         
@@ -418,7 +376,7 @@ def main():
 
         def auto_updates(): time.sleep(0); auto_update()
         def open_browser(): time.sleep(2); webbrowser.open_new_tab(f"http://localhost:{PORT}")
-        def warm_up_mods(): time.sleep(4); warm_up_modules()
+        def warm_up_mods(): time.sleep(6); warm_up_modules()
         
         threading.Thread(target=auto_updates, name="self-upgrade", daemon=True).start() # 查看自动更新
         threading.Thread(target=open_browser, name="open-browser", daemon=True).start() # 打开浏览器页面

request_llms/bridge_chatgpt.py

@@ -51,7 +51,8 @@ def decode_chunk(chunk):
         chunkjson = json.loads(chunk_decoded[6:])
         has_choices = 'choices' in chunkjson
         if has_choices: choice_valid = (len(chunkjson['choices']) > 0)
-        if has_choices and choice_valid: has_content = "content" in chunkjson['choices'][0]["delta"]
+        if has_choices and choice_valid: has_content = ("content" in chunkjson['choices'][0]["delta"])
+        if has_content: has_content = (chunkjson['choices'][0]["delta"]["content"] is not None)
         if has_choices and choice_valid: has_role = "role" in chunkjson['choices'][0]["delta"]
     except: 
         pass

request_llms/local_llm_class.py

@@ -183,11 +183,11 @@ class LocalLLMHandle(Process):
     def stream_chat(self, **kwargs):
         # ⭐run in main process
         if self.get_state() == "`准备就绪`":
-            yield "`正在等待线程锁，排队中请稍后 ...`"
+            yield "`正在等待线程锁，排队中请稍候 ...`"
 
         with self.threadLock:
             if self.parent.poll():
-                yield "`排队中请稍后 ...`"
+                yield "`排队中请稍候 ...`"
                 self.clear_pending_messages()
             self.parent.send(kwargs)
             std_out = ""

request_llms/requirements_chatglm_onnx.txt

@@ -6,5 +6,3 @@ sentencepiece
 numpy
 onnxruntime
 sentencepiece
-streamlit
-streamlit-chat

request_llms/requirements_moss.txt

@@ -5,5 +5,4 @@ accelerate
 matplotlib
 huggingface_hub
 triton
-streamlit
 

requirements.txt

@@ -3,6 +3,7 @@ pypdf2==2.12.1
 tiktoken>=0.3.3
 requests[socks]
 pydantic==1.10.11
+protobuf==3.18
 transformers>=4.27.1
 scipdf_parser>=0.52
 python-markdown-math

themes/common.js

@@ -1,9 +1,13 @@
+// -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
+//  第 1 部分: 工具函数
+// -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
+
 function gradioApp() {
     // https://github.com/GaiZhenbiao/ChuanhuChatGPT/tree/main/web_assets/javascript
     const elems = document.getElementsByTagName('gradio-app');
     const elem = elems.length == 0 ? document : elems[0];
     if (elem !== document) {
-        elem.getElementById = function(id) {
+        elem.getElementById = function (id) {
             return document.getElementById(id);
         };
     }
@@ -12,31 +16,76 @@ function gradioApp() {
 
 function setCookie(name, value, days) {
     var expires = "";
-  
+
     if (days) {
-      var date = new Date();
-      date.setTime(date.getTime() + (days * 24 * 60 * 60 * 1000));
-      expires = "; expires=" + date.toUTCString();
+        var date = new Date();
+        date.setTime(date.getTime() + (days * 24 * 60 * 60 * 1000));
+        expires = "; expires=" + date.toUTCString();
     }
-  
+
     document.cookie = name + "=" + value + expires + "; path=/";
 }
 
 function getCookie(name) {
     var decodedCookie = decodeURIComponent(document.cookie);
     var cookies = decodedCookie.split(';');
-  
+
     for (var i = 0; i < cookies.length; i++) {
-      var cookie = cookies[i].trim();
-  
-      if (cookie.indexOf(name + "=") === 0) {
-        return cookie.substring(name.length + 1, cookie.length);
-      }
+        var cookie = cookies[i].trim();
+
+        if (cookie.indexOf(name + "=") === 0) {
+            return cookie.substring(name.length + 1, cookie.length);
+        }
     }
-  
+
     return null;
-  }
-  
+}
+
+let toastCount = 0;
+function toast_push(msg, duration) {
+    duration = isNaN(duration) ? 3000 : duration;
+    const existingToasts = document.querySelectorAll('.toast');
+    existingToasts.forEach(toast => {
+        toast.style.top = `${parseInt(toast.style.top, 10) - 70}px`;
+    });
+    const m = document.createElement('div');
+    m.innerHTML = msg;
+    m.classList.add('toast');
+    m.style.cssText = `font-size: var(--text-md) !important; color: rgb(255, 255, 255); background-color: rgba(0, 0, 0, 0.6); padding: 10px 15px; border-radius: 4px; position: fixed; top: ${50 + toastCount * 70}%; left: 50%; transform: translateX(-50%); width: auto; text-align: center; transition: top 0.3s;`;
+    document.body.appendChild(m);
+    setTimeout(function () {
+        m.style.opacity = '0';
+        setTimeout(function () {
+            document.body.removeChild(m);
+            toastCount--;
+        }, 500);
+    }, duration);
+    toastCount++;
+}
+
+function toast_up(msg) {
+    var m = document.getElementById('toast_up');
+    if (m) {
+        document.body.removeChild(m); // remove the loader from the body
+    }
+    m = document.createElement('div');
+    m.id = 'toast_up';
+    m.innerHTML = msg;
+    m.style.cssText = "font-size: var(--text-md) !important; color: rgb(255, 255, 255); background-color: rgba(0, 0, 100, 0.6); padding: 10px 15px; margin: 0 0 0 -60px; border-radius: 4px; position: fixed; top: 50%; left: 50%; width: auto; text-align: center;";
+    document.body.appendChild(m);
+}
+function toast_down() {
+    var m = document.getElementById('toast_up');
+    if (m) {
+        document.body.removeChild(m); // remove the loader from the body
+    }
+}
+
+
+// -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
+//  第 2 部分: 复制按钮
+// -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
+
 function addCopyButton(botElement) {
     // https://github.com/GaiZhenbiao/ChuanhuChatGPT/tree/main/web_assets/javascript
     // Copy bot button
@@ -49,7 +98,7 @@ function addCopyButton(botElement) {
         // messageBtnColumnElement.remove();
         return;
     }
-    
+
     var copyButton = document.createElement('button');
     copyButton.classList.add('copy-bot-btn');
     copyButton.setAttribute('aria-label', 'Copy');
@@ -98,47 +147,42 @@ function chatbotContentChanged(attempt = 1, force = false) {
     }
 }
 
-function chatbotAutoHeight(){
+
+
+// -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
+//  第 3 部分: chatbot动态高度调整
+// -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
+
+function chatbotAutoHeight() {
     // 自动调整高度
-    function update_height(){
+    function update_height() {
         var { panel_height_target, chatbot_height, chatbot } = get_elements(true);
-        if (panel_height_target!=chatbot_height)
-        {
+        if (panel_height_target != chatbot_height) {
             var pixelString = panel_height_target.toString() + 'px';
-            chatbot.style.maxHeight = pixelString; chatbot.style.height = pixelString; 
+            chatbot.style.maxHeight = pixelString; chatbot.style.height = pixelString;
         }
     }
 
-    function update_height_slow(){
+    function update_height_slow() {
         var { panel_height_target, chatbot_height, chatbot } = get_elements();
-        if (panel_height_target!=chatbot_height)
-        {
-            new_panel_height = (panel_height_target - chatbot_height)*0.5 + chatbot_height;
-            if (Math.abs(new_panel_height - panel_height_target) < 10){
+        if (panel_height_target != chatbot_height) {
+            new_panel_height = (panel_height_target - chatbot_height) * 0.5 + chatbot_height;
+            if (Math.abs(new_panel_height - panel_height_target) < 10) {
                 new_panel_height = panel_height_target;
             }
             // console.log(chatbot_height, panel_height_target, new_panel_height);
             var pixelString = new_panel_height.toString() + 'px';
-            chatbot.style.maxHeight = pixelString; chatbot.style.height = pixelString; 
+            chatbot.style.maxHeight = pixelString; chatbot.style.height = pixelString;
         }
     }
     monitoring_input_box()
     update_height();
-    setInterval(function() {
+    setInterval(function () {
         update_height_slow()
     }, 50); // 每100毫秒执行一次
 }
 
-function GptAcademicJavaScriptInit(LAYOUT = "LEFT-RIGHT") {
-    chatbotIndicator = gradioApp().querySelector('#gpt-chatbot > div.wrap');
-    var chatbotObserver = new MutationObserver(() => {
-        chatbotContentChanged(1);
-    });
-    chatbotObserver.observe(chatbotIndicator, { attributes: true, childList: true, subtree: true });
-    if (LAYOUT === "LEFT-RIGHT") {chatbotAutoHeight();}
-}
-
-function get_elements(consider_state_panel=false) {
+function get_elements(consider_state_panel = false) {
     var chatbot = document.querySelector('#gpt-chatbot > div.wrap.svelte-18telvq');
     if (!chatbot) {
         chatbot = document.querySelector('#gpt-chatbot');
@@ -149,13 +193,13 @@ function get_elements(consider_state_panel=false) {
     // const panel4 = document.querySelector('#interact-panel').getBoundingClientRect();
     const panel5 = document.querySelector('#input-panel2').getBoundingClientRect();
     const panel_active = document.querySelector('#state-panel').getBoundingClientRect();
-    if (consider_state_panel || panel_active.height < 25){
+    if (consider_state_panel || panel_active.height < 25) {
         document.state_panel_height = panel_active.height;
     }
     // 25 是chatbot的label高度, 16 是右侧的gap
-    var panel_height_target = panel1.height + panel2.height + panel3.height + 0 + 0 - 25 + 16*2;
+    var panel_height_target = panel1.height + panel2.height + panel3.height + 0 + 0 - 25 + 16 * 2;
     // 禁止动态的state-panel高度影响
-    panel_height_target = panel_height_target + (document.state_panel_height-panel_active.height)
+    panel_height_target = panel_height_target + (document.state_panel_height - panel_active.height)
     var panel_height_target = parseInt(panel_height_target);
     var chatbot_height = chatbot.style.height;
     var chatbot_height = parseInt(chatbot_height);
@@ -163,6 +207,18 @@ function get_elements(consider_state_panel=false) {
 }
 
 
+
+// -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
+//  第 4 部分: 粘贴、拖拽文件上传
+// -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
+
+var elem_upload = null;
+var elem_upload_float = null;
+var elem_input_main = null;
+var elem_input_float = null;
+var elem_chatbot = null;
+var exist_file_msg = '⚠️请先删除上传区（左上方）中的历史文件，再尝试上传。'
+
 function add_func_paste(input) {
     let paste_files = [];
     if (input) {
@@ -180,7 +236,7 @@ function add_func_paste(input) {
                 }
                 if (paste_files.length > 0) {
                     // 按照文件列表执行批量上传逻辑
-                    await paste_upload_files(paste_files);
+                    await upload_files(paste_files);
                     paste_files = []
 
                 }
@@ -189,8 +245,43 @@ function add_func_paste(input) {
     }
 }
 
+function add_func_drag(elem) {
+    if (elem) {
+        const dragEvents = ["dragover"];
+        const leaveEvents = ["dragleave", "dragend", "drop"];
 
-async function paste_upload_files(files) {
+        const onDrag = function (e) {
+            e.preventDefault();
+            e.stopPropagation();
+            if (elem_upload_float.querySelector("input[type=file]")) {
+                toast_up('⚠️释放以上传文件')
+            } else {
+                toast_up(exist_file_msg)
+            }
+        };
+
+        const onLeave = function (e) {
+            toast_down();
+            e.preventDefault();
+            e.stopPropagation();
+        };
+
+        dragEvents.forEach(event => {
+            elem.addEventListener(event, onDrag);
+        });
+
+        leaveEvents.forEach(event => {
+            elem.addEventListener(event, onLeave);
+        });
+
+        elem.addEventListener("drop", async function (e) {
+            const files = e.dataTransfer.files;
+            await upload_files(files);
+        });
+    }
+}
+
+async function upload_files(files) {
     const uploadInputElement = elem_upload_float.querySelector("input[type=file]");
     let totalSizeMb = 0
     if (files && files.length > 0) {
@@ -202,59 +293,101 @@ async function paste_upload_files(files) {
             }
             // 检查文件总大小是否超过20MB
             if (totalSizeMb > 20) {
-                toast_push('⚠️文件夹大于20MB 🚀上传文件中', 2000)
+                toast_push('⚠️文件夹大于 20MB 🚀上传文件中', 3000)
                 // return;  // 如果超过了指定大小, 可以不进行后续上传操作
             }
-             // 监听change事件， 原生Gradio可以实现
+            // 监听change事件， 原生Gradio可以实现
             // uploadInputElement.addEventListener('change', function(){replace_input_string()});
             let event = new Event("change");
-            Object.defineProperty(event, "target", {value: uploadInputElement, enumerable: true});
-            Object.defineProperty(event, "currentTarget", {value: uploadInputElement, enumerable: true});
-            Object.defineProperty(uploadInputElement, "files", {value: files, enumerable: true});
+            Object.defineProperty(event, "target", { value: uploadInputElement, enumerable: true });
+            Object.defineProperty(event, "currentTarget", { value: uploadInputElement, enumerable: true });
+            Object.defineProperty(uploadInputElement, "files", { value: files, enumerable: true });
             uploadInputElement.dispatchEvent(event);
-            // toast_push('🎉上传文件成功', 2000)
         } else {
-            toast_push('⚠️请先删除上传区中的历史文件，再尝试粘贴。', 2000)
+            toast_push(exist_file_msg, 3000)
         }
     }
 }
-//提示信息 封装
-function toast_push(msg, duration) {
-    duration = isNaN(duration) ? 3000 : duration;
-    const m = document.createElement('div');
-    m.innerHTML = msg;
-    m.style.cssText = "font-size:  var(--text-md) !important; color: rgb(255, 255, 255);background-color: rgba(0, 0, 0, 0.6);padding: 10px 15px;margin: 0 0 0 -60px;border-radius: 4px;position: fixed;    top: 50%;left: 50%;width: auto; text-align: center;";
-    document.body.appendChild(m);
-    setTimeout(function () {
-        var d = 0.5;
-        m.style.opacity = '0';
-        setTimeout(function () {
-            document.body.removeChild(m)
-        }, d * 1000);
-    }, duration);
+
+function begin_loading_status() {
+    // Create the loader div and add styling
+    var loader = document.createElement('div');
+    loader.id = 'Js_File_Loading';
+    loader.style.position = "absolute";
+    loader.style.top = "50%";
+    loader.style.left = "50%";
+    loader.style.width = "60px";
+    loader.style.height = "60px";
+    loader.style.border = "16px solid #f3f3f3";
+    loader.style.borderTop = "16px solid #3498db";
+    loader.style.borderRadius = "50%";
+    loader.style.animation = "spin 2s linear infinite";
+    loader.style.transform = "translate(-50%, -50%)";
+    document.body.appendChild(loader); // Add the loader to the body
+    // Set the CSS animation keyframes
+    var styleSheet = document.createElement('style');
+    // styleSheet.type = 'text/css';
+    styleSheet.id = 'Js_File_Loading_Style'
+    styleSheet.innerText = `
+    @keyframes spin {
+        0% { transform: rotate(0deg); }
+        100% { transform: rotate(360deg); }
+    }`;
+    document.head.appendChild(styleSheet);
 }
 
-var elem_upload = null;
-var elem_upload_float = null;
-var elem_input_main = null;
-var elem_input_float = null;
+function cancel_loading_status() {
+    var loadingElement = document.getElementById('Js_File_Loading');
+    if (loadingElement) {
+        document.body.removeChild(loadingElement); // remove the loader from the body
+    }
+    var loadingStyle = document.getElementById('Js_File_Loading_Style');
+    if (loadingStyle) {
+        document.head.removeChild(loadingStyle);
+    }
+    let clearButton = document.querySelectorAll('div[id*="elem_upload"] button[aria-label="Clear"]');
+    for (let button of clearButton) {
+        button.addEventListener('click', function () {
+            setTimeout(function () {
+                register_upload_event();
+            }, 50);
+        });
+    }
+}
 
+function register_upload_event() {
+    elem_upload_float = document.getElementById('elem_upload_float')
+    const upload_component = elem_upload_float.querySelector("input[type=file]");
+    if (upload_component) {
+        upload_component.addEventListener('change', function (event) {
+            toast_push('正在上传中，请稍等。', 2000);
+            begin_loading_status();
+        });
+    }
+}
 
 function monitoring_input_box() {
+    register_upload_event();
+
     elem_upload = document.getElementById('elem_upload')
     elem_upload_float = document.getElementById('elem_upload_float')
     elem_input_main = document.getElementById('user_input_main')
     elem_input_float = document.getElementById('user_input_float')
+    elem_chatbot = document.getElementById('gpt-chatbot')
+
     if (elem_input_main) {
         if (elem_input_main.querySelector("textarea")) {
             add_func_paste(elem_input_main.querySelector("textarea"))
         }
     }
     if (elem_input_float) {
-        if (elem_input_float.querySelector("textarea")){
+        if (elem_input_float.querySelector("textarea")) {
             add_func_paste(elem_input_float.querySelector("textarea"))
         }
     }
+    if (elem_chatbot) {
+        add_func_drag(elem_chatbot)
+    }
 }
 
 
@@ -263,3 +396,64 @@ window.addEventListener("DOMContentLoaded", function () {
     // const ga = document.getElementsByTagName("gradio-app");
     gradioApp().addEventListener("render", monitoring_input_box);
 });
+
+
+
+
+
+// -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
+//  第 5 部分: 音频按钮样式变化
+// -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
+
+function audio_fn_init() {
+    let audio_component = document.getElementById('elem_audio');
+    if (audio_component) {
+        let buttonElement = audio_component.querySelector('button');
+        let specificElement = audio_component.querySelector('.hide.sr-only');
+        specificElement.remove();
+
+        buttonElement.childNodes[1].nodeValue = '启动麦克风';
+        buttonElement.addEventListener('click', function (event) {
+            event.stopPropagation();
+            toast_push('您启动了麦克风!下一步请点击“实时语音对话”启动语音对话。');
+        });
+
+        // 查找语音插件按钮
+        let buttons = document.querySelectorAll('button');
+        let audio_button = null;
+        for (let button of buttons) {
+            if (button.textContent.includes('语音')) {
+                audio_button = button;
+                break;
+            }
+        }
+        if (audio_button) {
+            audio_button.addEventListener('click', function () {
+                toast_push('您点击了“实时语音对话”启动语音对话。');
+            });
+            let parent_element = audio_component.parentElement; // 将buttonElement移动到audio_button的内部
+            audio_button.appendChild(audio_component);
+            buttonElement.style.cssText = 'border-color: #00ffe0;border-width: 2px; height: 25px;'
+            parent_element.remove();
+            audio_component.style.cssText = 'width: 250px;right: 0px;display: inline-flex;flex-flow: row-reverse wrap;place-content: stretch space-between;align-items: center;background-color: #ffffff00;';
+        }
+
+    }
+}
+
+
+
+
+// -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
+//  第 6 部分: JS初始化函数
+// -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
+
+function GptAcademicJavaScriptInit(LAYOUT = "LEFT-RIGHT") {
+    audio_fn_init();
+    chatbotIndicator = gradioApp().querySelector('#gpt-chatbot > div.wrap');
+    var chatbotObserver = new MutationObserver(() => {
+        chatbotContentChanged(1);
+    });
+    chatbotObserver.observe(chatbotIndicator, { attributes: true, childList: true, subtree: true });
+    if (LAYOUT === "LEFT-RIGHT") { chatbotAutoHeight(); }
+}

themes/theme.py

@@ -1,6 +1,14 @@
-import gradio as gr
+import pickle
+import base64
+import uuid
 from toolbox import get_conf
-THEME = get_conf('THEME')
+
+"""
+-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
+第 1 部分
+加载主题相关的工具函数
+-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
+"""
 
 def load_dynamic_theme(THEME):
     adjust_dynamic_theme = None
@@ -20,4 +28,91 @@ def load_dynamic_theme(THEME):
         theme_declaration = ""
     return adjust_theme, advanced_css, theme_declaration, adjust_dynamic_theme
 
-adjust_theme, advanced_css, theme_declaration, _ = load_dynamic_theme(THEME)
+adjust_theme, advanced_css, theme_declaration, _ = load_dynamic_theme(get_conf('THEME'))
+
+
+
+
+
+
+"""
+-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
+第 2 部分
+cookie相关工具函数
+-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
+"""
+
+def init_cookie(cookies, chatbot):
+    # 为每一位访问的用户赋予一个独一无二的uuid编码
+    cookies.update({'uuid': uuid.uuid4()})
+    return cookies
+
+def to_cookie_str(d):
+    # Pickle the dictionary and encode it as a string
+    pickled_dict = pickle.dumps(d)
+    cookie_value = base64.b64encode(pickled_dict).decode('utf-8')
+    return cookie_value
+
+def from_cookie_str(c):
+    # Decode the base64-encoded string and unpickle it into a dictionary
+    pickled_dict = base64.b64decode(c.encode('utf-8'))
+    return pickle.loads(pickled_dict)
+
+
+
+
+
+"""
+-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
+第 3 部分
+内嵌的javascript代码
+-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
+"""
+
+js_code_for_css_changing = """(css) => {
+    var existingStyles = document.querySelectorAll("body > gradio-app > div > style")
+    for (var i = 0; i < existingStyles.length; i++) {
+        var style = existingStyles[i];
+        style.parentNode.removeChild(style);
+    }
+    var existingStyles = document.querySelectorAll("style[data-loaded-css]");
+    for (var i = 0; i < existingStyles.length; i++) {
+        var style = existingStyles[i];
+        style.parentNode.removeChild(style);
+    }
+    var styleElement = document.createElement('style');
+    styleElement.setAttribute('data-loaded-css', 'placeholder');
+    styleElement.innerHTML = css;
+    document.body.appendChild(styleElement);
+}
+"""
+
+js_code_for_darkmode_init = """(dark) => {
+    dark = dark == "True";
+    if (document.querySelectorAll('.dark').length) {
+        if (!dark){
+            document.querySelectorAll('.dark').forEach(el => el.classList.remove('dark'));
+        }
+    } else {
+        if (dark){
+            document.querySelector('body').classList.add('dark');
+        }
+    }
+}
+"""
+
+js_code_for_toggle_darkmode = """() => {
+    if (document.querySelectorAll('.dark').length) {
+        document.querySelectorAll('.dark').forEach(el => el.classList.remove('dark'));
+    } else {
+        document.querySelector('body').classList.add('dark');
+    }
+}"""
+
+
+js_code_for_persistent_cookie_init = """(persistent_cookie) => {
+    return getCookie("persistent_cookie");
+}
+"""
+
+

toolbox.py

@@ -583,7 +583,8 @@ def promote_file_to_downloadzone(file, rename_file=None, chatbot=None):
     if chatbot is not None:
         if 'files_to_promote' in chatbot._cookies: current = chatbot._cookies['files_to_promote']
         else: current = []
-        chatbot._cookies.update({'files_to_promote': [new_path] + current})
+        if new_path not in current: # 避免把同一个文件添加多次
+            chatbot._cookies.update({'files_to_promote': [new_path] + current})
     return new_path
 
 
@@ -1007,14 +1008,19 @@ def clip_history(inputs, history, tokenizer, max_token_limit):
     def get_token_num(txt): 
         return len(tokenizer.encode(txt, disallowed_special=()))
     input_token_num = get_token_num(inputs)
+
+    if max_token_limit < 5000:   output_token_expect = 256  # 4k & 2k models
+    elif max_token_limit < 9000: output_token_expect = 512  # 8k models
+    else: output_token_expect = 1024                        # 16k & 32k models
+
     if input_token_num < max_token_limit * 3 / 4:
         # 当输入部分的token占比小于限制的3/4时，裁剪时
         # 1. 把input的余量留出来
         max_token_limit = max_token_limit - input_token_num
         # 2. 把输出用的余量留出来
-        max_token_limit = max_token_limit - 128
+        max_token_limit = max_token_limit - output_token_expect
         # 3. 如果余量太小了，直接清除历史
-        if max_token_limit < 128:
+        if max_token_limit < output_token_expect:
             history = []
             return history
     else:

version

@@ -1,5 +1,5 @@
 {
-  "version": 3.62,
+  "version": 3.64,
   "show_feature": true,
-  "new_feature": "修复若干隐蔽的内存BUG <-> 修复多用户冲突问题 <-> 接入Deepseek Coder <-> AutoGen多智能体插件测试版 <-> 修复本地模型在Windows下的加载BUG <-> 支持文心一言v4和星火v3 <-> 支持GLM3和智谱的API <-> 解决本地模型并发BUG <-> 支持动态追加基础功能按钮"
+  "new_feature": "支持直接拖拽文件到上传区 <-> 支持将图片粘贴到输入区 <-> 修复若干隐蔽的内存BUG <-> 修复多用户冲突问题 <-> 接入Deepseek Coder <-> AutoGen多智能体插件测试版"
 }