new

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/Latex输出PDF结果.py

@@ -88,6 +88,9 @@ def arxiv_download(chatbot, history, txt, allow_cache=True):
         target_file = pj(translation_dir, 'translate_zh.pdf')
         if os.path.exists(target_file):
             promote_file_to_downloadzone(target_file, rename_file=None, chatbot=chatbot)
+            target_file_compare = pj(translation_dir, 'comparison.pdf')
+            if os.path.exists(target_file_compare):
+                promote_file_to_downloadzone(target_file_compare, rename_file=None, chatbot=chatbot)
             return target_file
         return False
     def is_float(s):

crazy_functions/crazy_utils.py

@@ -1,4 +1,4 @@
-from toolbox import update_ui, get_conf, trimmed_format_exc, get_max_token
+from toolbox import update_ui, get_conf, trimmed_format_exc, get_max_token, Singleton
 import threading
 import os
 import logging
@@ -139,6 +139,8 @@ def can_multi_process(llm):
     if llm.startswith('gpt-'): return True
     if llm.startswith('api2d-'): return True
     if llm.startswith('azure-'): return True
+    if llm.startswith('spark'): return True
+    if llm.startswith('zhipuai'): return True
     return False
 
 def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
@@ -312,95 +314,6 @@ 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):
     """
@@ -631,90 +544,6 @@ def get_files_from_everything(txt, type): # type='.md'
 
 
 
-
-def Singleton(cls):
-    _instance = {}
- 
-    def _singleton(*args, **kargs):
-        if cls not in _instance:
-            _instance[cls] = cls(*args, **kargs)
-        return _instance[cls]
- 
-    return _singleton
-
-
-@Singleton
-class knowledge_archive_interface():
-    def __init__(self) -> None:
-        self.threadLock = threading.Lock()
-        self.current_id = ""
-        self.kai_path = None
-        self.qa_handle = None
-        self.text2vec_large_chinese = None
-
-    def get_chinese_text2vec(self):
-        if self.text2vec_large_chinese is None:
-            # < -------------------预热文本向量化模组--------------- >
-            from toolbox import ProxyNetworkActivate
-            print('Checking Text2vec ...')
-            from langchain.embeddings.huggingface import HuggingFaceEmbeddings
-            with ProxyNetworkActivate('Download_LLM'):    # 临时地激活代理网络
-                self.text2vec_large_chinese = HuggingFaceEmbeddings(model_name="GanymedeNil/text2vec-large-chinese")
-
-        return self.text2vec_large_chinese
-
-
-    def feed_archive(self, file_manifest, id="default"):
-        self.threadLock.acquire()
-        # import uuid
-        self.current_id = id
-        from zh_langchain import construct_vector_store
-        self.qa_handle, self.kai_path = construct_vector_store(   
-            vs_id=self.current_id, 
-            files=file_manifest, 
-            sentence_size=100,
-            history=[],
-            one_conent="",
-            one_content_segmentation="",
-            text2vec = self.get_chinese_text2vec(),
-        )
-        self.threadLock.release()
-
-    def get_current_archive_id(self):
-        return self.current_id
-    
-    def get_loaded_file(self):
-        return self.qa_handle.get_loaded_file()
-
-    def answer_with_archive_by_id(self, txt, id):
-        self.threadLock.acquire()
-        if not self.current_id == id:
-            self.current_id = id
-            from zh_langchain import construct_vector_store
-            self.qa_handle, self.kai_path = construct_vector_store(   
-                vs_id=self.current_id, 
-                files=[], 
-                sentence_size=100,
-                history=[],
-                one_conent="",
-                one_content_segmentation="",
-                text2vec = self.get_chinese_text2vec(),
-            )
-        VECTOR_SEARCH_SCORE_THRESHOLD = 0
-        VECTOR_SEARCH_TOP_K = 4
-        CHUNK_SIZE = 512
-        resp, prompt = self.qa_handle.get_knowledge_based_conent_test(
-            query = txt,
-            vs_path = self.kai_path,
-            score_threshold=VECTOR_SEARCH_SCORE_THRESHOLD,
-            vector_search_top_k=VECTOR_SEARCH_TOP_K, 
-            chunk_conent=True,
-            chunk_size=CHUNK_SIZE,
-            text2vec = self.get_chinese_text2vec(),
-        )
-        self.threadLock.release()
-        return resp, prompt
-    
 @Singleton
 class nougat_interface():
     def __init__(self):

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')):
@@ -416,8 +414,11 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
                     from .latex_toolbox import merge_pdfs
                     concat_pdf = pj(work_folder_modified, f'comparison.pdf')
                     merge_pdfs(origin_pdf, result_pdf, concat_pdf)
+                    if os.path.exists(pj(work_folder, '..', 'translation')):
+                        shutil.copyfile(concat_pdf, pj(work_folder, '..', 'translation', 'comparison.pdf'))
                     promote_file_to_downloadzone(concat_pdf, rename_file=None, chatbot=chatbot)  # promote file to web UI
                 except Exception as e:
+                    print(e)
                     pass
             return True # 成功啦
         else:

crazy_functions/latex_fns/latex_toolbox.py

@@ -493,11 +493,38 @@ def compile_latex_with_timeout(command, cwd, timeout=60):
         return False
     return True
 
+def run_in_subprocess_wrapper_func(func, args, kwargs, return_dict, exception_dict):
+    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(func):
+    import multiprocessing
+    def wrapper(*args, **kwargs):
+        return_dict = multiprocessing.Manager().dict()
+        exception_dict = multiprocessing.Manager().dict()
+        process = multiprocessing.Process(target=run_in_subprocess_wrapper_func, 
+                                            args=(func, args, kwargs, return_dict, exception_dict))
+        process.start()
+        process.join()
+        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
 
-def merge_pdfs(pdf1_path, pdf2_path, output_path):
-    import PyPDF2
+def _merge_pdfs(pdf1_path, pdf2_path, output_path):
+    import PyPDF2   # PyPDF2这个库有严重的内存泄露问题，把它放到子进程中运行，从而方便内存的释放
     Percent = 0.95
+    # raise RuntimeError('PyPDF2 has a serious memory leak problem, please use other tools to merge PDF files.')
     # Open the first PDF file
     with open(pdf1_path, 'rb') as pdf1_file:
         pdf1_reader = PyPDF2.PdfFileReader(pdf1_file)
@@ -531,3 +558,5 @@ def merge_pdfs(pdf1_path, pdf2_path, output_path):
             # Save the merged PDF file
             with open(output_path, 'wb') as output_file:
                 output_writer.write(output_file)
+
+merge_pdfs = run_in_subprocess(_merge_pdfs) # PyPDF2这个库有严重的内存泄露问题，把它放到子进程中运行，从而方便内存的释放

crazy_functions/multi_stage/multi_stage_utils.py

@@ -1,6 +1,7 @@
 from pydantic import BaseModel, Field
 from typing import List
 from toolbox import update_ui_lastest_msg, disable_auto_promotion
+from toolbox import CatchException, update_ui, get_conf, select_api_key, get_log_folder
 from request_llms.bridge_all import predict_no_ui_long_connection
 from crazy_functions.json_fns.pydantic_io import GptJsonIO, JsonStringError
 import time
@@ -21,11 +22,7 @@ class GptAcademicState():
     def reset(self):
         pass
 
-    def lock_plugin(self, chatbot):
-        chatbot._cookies['plugin_state'] = pickle.dumps(self)
-
-    def unlock_plugin(self, chatbot):
-        self.reset()
+    def dump_state(self, chatbot):
         chatbot._cookies['plugin_state'] = pickle.dumps(self)
 
     def set_state(self, chatbot, key, value):
@@ -40,6 +37,57 @@ class GptAcademicState():
         state.chatbot = chatbot
         return state
 
-class GatherMaterials():
-    def __init__(self, materials) -> None:
-        materials = ['image', 'prompt']
+
+class GptAcademicGameBaseState():
+    """
+    1. first init: __init__ -> 
+    """
+    def init_game(self, chatbot, lock_plugin):
+        self.plugin_name = None
+        self.callback_fn = None
+        self.delete_game = False
+        self.step_cnt = 0
+
+    def lock_plugin(self, chatbot):
+        if self.callback_fn is None:
+            raise ValueError("callback_fn is None")
+        chatbot._cookies['lock_plugin'] = self.callback_fn
+        self.dump_state(chatbot)
+        
+    def get_plugin_name(self):
+        if self.plugin_name is None:
+            raise ValueError("plugin_name is None")
+        return self.plugin_name
+
+    def dump_state(self, chatbot):
+        chatbot._cookies[f'plugin_state/{self.get_plugin_name()}'] = pickle.dumps(self)
+
+    def set_state(self, chatbot, key, value):
+        setattr(self, key, value)
+        chatbot._cookies[f'plugin_state/{self.get_plugin_name()}'] = pickle.dumps(self)
+
+    @staticmethod
+    def sync_state(chatbot, llm_kwargs, cls, plugin_name, callback_fn, lock_plugin=True):
+        state = chatbot._cookies.get(f'plugin_state/{plugin_name}', None)
+        if state is not None:
+            state = pickle.loads(state)
+        else: 
+            state = cls()
+            state.init_game(chatbot, lock_plugin)
+        state.plugin_name = plugin_name
+        state.llm_kwargs = llm_kwargs
+        state.chatbot = chatbot
+        state.callback_fn = callback_fn
+        return state
+    
+    def continue_game(self, prompt, chatbot, history):
+        # 游戏主体
+        yield from self.step(prompt, chatbot, history)
+        self.step_cnt += 1
+        # 保存状态，收尾
+        self.dump_state(chatbot)
+        # 如果游戏结束，清理
+        if self.delete_game:
+            chatbot._cookies['lock_plugin'] = None
+            chatbot._cookies[f'plugin_state/{self.get_plugin_name()}'] = None
+        yield from update_ui(chatbot=chatbot, history=history)

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/图片生成.py

@@ -2,7 +2,7 @@ from toolbox import CatchException, update_ui, get_conf, select_api_key, get_log
 from crazy_functions.multi_stage.multi_stage_utils import GptAcademicState
 
 
-def gen_image(llm_kwargs, prompt, resolution="1024x1024", model="dall-e-2", quality=None):
+def gen_image(llm_kwargs, prompt, resolution="1024x1024", model="dall-e-2", quality=None, style=None):
     import requests, json, time, os
     from request_llms.bridge_all import model_info
 
@@ -25,7 +25,10 @@ def gen_image(llm_kwargs, prompt, resolution="1024x1024", model="dall-e-2", qual
         'model': model,
         'response_format': 'url'
     }
-    if quality is not None: data.update({'quality': quality})
+    if quality is not None:
+        data['quality'] = quality
+    if style is not None:
+        data['style'] = style
     response = requests.post(url, headers=headers, json=data, proxies=proxies)
     print(response.content)
     try:
@@ -54,19 +57,25 @@ def edit_image(llm_kwargs, prompt, image_path, resolution="1024x1024", model="da
     img_endpoint = chat_endpoint.replace('chat/completions','images/edits')
     # # Generate the image
     url = img_endpoint
+    n = 1
     headers = {
         'Authorization': f"Bearer {api_key}",
-        'Content-Type': 'application/json'
     }
-    data = {
-        'image': open(image_path, 'rb'),
-        'prompt': prompt,
-        'n': 1,
-        'size': resolution,
-        'model': model,
-        'response_format': 'url'
-    }
-    response = requests.post(url, headers=headers, json=data, proxies=proxies)
+    make_transparent(image_path, image_path+'.tsp.png')
+    make_square_image(image_path+'.tsp.png', image_path+'.tspsq.png')
+    resize_image(image_path+'.tspsq.png', image_path+'.ready.png', max_size=1024)
+    image_path = image_path+'.ready.png'
+    with open(image_path, 'rb') as f:
+        file_content = f.read()
+        files = {
+            'image': (os.path.basename(image_path), file_content),
+            # 'mask': ('mask.png', open('mask.png', 'rb'))
+            'prompt':   (None, prompt),
+            "n":        (None, str(n)),
+            'size':     (None, resolution),
+        }
+
+    response = requests.post(url, headers=headers, files=files, proxies=proxies)
     print(response.content)
     try:
         image_url = json.loads(response.content.decode('utf8'))['data'][0]['url']
@@ -95,7 +104,11 @@ def 图片生成_DALLE2(prompt, llm_kwargs, plugin_kwargs, chatbot, history, sys
     web_port        当前软件运行的端口号
     """
     history = []    # 清空历史,以免输入溢出
-    chatbot.append(("您正在调用“图像生成”插件。", "[Local Message] 生成图像, 请先把模型切换至gpt-*或者api2d-*。如果中文Prompt效果不理想, 请尝试英文Prompt。正在处理中 ....."))
+    if prompt.strip() == "":
+        chatbot.append((prompt, "[Local Message] 图像生成提示为空白，请在“输入区”输入图像生成提示。"))
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 界面更新
+        return
+    chatbot.append(("您正在调用“图像生成”插件。", "[Local Message] 生成图像, 请先把模型切换至gpt-*。如果中文Prompt效果不理想, 请尝试英文Prompt。正在处理中 ....."))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 由于请求gpt需要一段时间,我们先及时地做一次界面更新
     if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
     resolution = plugin_kwargs.get("advanced_arg", '1024x1024')
@@ -112,16 +125,25 @@ def 图片生成_DALLE2(prompt, llm_kwargs, plugin_kwargs, chatbot, history, sys
 @CatchException
 def 图片生成_DALLE3(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
     history = []    # 清空历史,以免输入溢出
-    chatbot.append(("您正在调用“图像生成”插件。", "[Local Message] 生成图像, 请先把模型切换至gpt-*或者api2d-*。如果中文Prompt效果不理想, 请尝试英文Prompt。正在处理中 ....."))
+    if prompt.strip() == "":
+        chatbot.append((prompt, "[Local Message] 图像生成提示为空白，请在“输入区”输入图像生成提示。"))
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 界面更新
+        return
+    chatbot.append(("您正在调用“图像生成”插件。", "[Local Message] 生成图像, 请先把模型切换至gpt-*。如果中文Prompt效果不理想, 请尝试英文Prompt。正在处理中 ....."))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 由于请求gpt需要一段时间,我们先及时地做一次界面更新
     if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
-    resolution = plugin_kwargs.get("advanced_arg", '1024x1024').lower()
-    if resolution.endswith('-hd'):
-        resolution = resolution.replace('-hd', '')
-        quality = 'hd'
-    else:
-        quality = 'standard'
-    image_url, image_path = gen_image(llm_kwargs, prompt, resolution, model="dall-e-3", quality=quality)
+    resolution_arg = plugin_kwargs.get("advanced_arg", '1024x1024-standard-vivid').lower()
+    parts = resolution_arg.split('-')
+    resolution = parts[0] # 解析分辨率
+    quality = 'standard' # 质量与风格默认值
+    style = 'vivid'
+    # 遍历检查是否有额外参数
+    for part in parts[1:]:
+        if part in ['hd', 'standard']:
+            quality = part
+        elif part in ['vivid', 'natural']:
+            style = part
+    image_url, image_path = gen_image(llm_kwargs, prompt, resolution, model="dall-e-3", quality=quality, style=style)
     chatbot.append([prompt,  
         f'图像中转网址: <br/>`{image_url}`<br/>'+
         f'中转网址预览: <br/><div align="center"><img src="{image_url}"></div>'
@@ -130,6 +152,7 @@ def 图片生成_DALLE3(prompt, llm_kwargs, plugin_kwargs, chatbot, history, sys
     ])
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 界面更新
 
+
 class ImageEditState(GptAcademicState):
     # 尚未完成
     def get_image_file(self, x):
@@ -142,18 +165,27 @@ class ImageEditState(GptAcademicState):
         file = None if not confirm else file_manifest[0]
         return confirm, file
     
+    def lock_plugin(self, chatbot):
+        chatbot._cookies['lock_plugin'] = 'crazy_functions.图片生成->图片修改_DALLE2'
+        self.dump_state(chatbot)
+
+    def unlock_plugin(self, chatbot):
+        self.reset()
+        chatbot._cookies['lock_plugin'] = None
+        self.dump_state(chatbot)
+
     def get_resolution(self, x):
         return (x in ['256x256', '512x512', '1024x1024']), x
-    
+
     def get_prompt(self, x):
         confirm = (len(x)>=5) and (not self.get_resolution(x)[0]) and (not self.get_image_file(x)[0])
         return confirm, x
-    
+
     def reset(self):
         self.req = [
-            {'value':None, 'description': '请先上传图像（必须是.png格式）, 然后再次点击本插件',    'verify_fn': self.get_image_file},
-            {'value':None, 'description': '请输入分辨率,可选：256x256, 512x512 或 1024x1024',   'verify_fn': self.get_resolution},
-            {'value':None, 'description': '请输入修改需求,建议您使用英文提示词',                 'verify_fn': self.get_prompt},
+            {'value':None, 'description': '请先上传图像（必须是.png格式）, 然后再次点击本插件',                      'verify_fn': self.get_image_file},
+            {'value':None, 'description': '请输入分辨率,可选：256x256, 512x512 或 1024x1024, 然后再次点击本插件',   'verify_fn': self.get_resolution},
+            {'value':None, 'description': '请输入修改需求,建议您使用英文提示词, 然后再次点击本插件',                 'verify_fn': self.get_prompt},
         ]
         self.info = ""
 
@@ -163,7 +195,7 @@ class ImageEditState(GptAcademicState):
                 confirm, res = r['verify_fn'](prompt)
                 if confirm:
                     r['value'] = res
-                    self.set_state(chatbot, 'dummy_key', 'dummy_value')
+                    self.dump_state(chatbot)
                     break
         return self
 
@@ -182,23 +214,63 @@ def 图片修改_DALLE2(prompt, llm_kwargs, plugin_kwargs, chatbot, history, sys
     history = []    # 清空历史
     state = ImageEditState.get_state(chatbot, ImageEditState)
     state = state.feed(prompt, chatbot)
+    state.lock_plugin(chatbot)
     if not state.already_obtained_all_materials():
-        chatbot.append(["图片修改（先上传图片,再输入修改需求,最后输入分辨率）", state.next_req()])
+        chatbot.append(["图片修改\n\n1. 上传图片（图片中需要修改的位置用橡皮擦擦除为纯白色，即RGB=255,255,255）\n2. 输入分辨率 \n3. 输入修改需求", state.next_req()])
         yield from update_ui(chatbot=chatbot, history=history)
         return
 
-    image_path = state.req[0]
-    resolution = state.req[1]
-    prompt = state.req[2]
+    image_path = state.req[0]['value']
+    resolution = state.req[1]['value']
+    prompt = state.req[2]['value']
     chatbot.append(["图片修改, 执行中", f"图片:`{image_path}`<br/>分辨率:`{resolution}`<br/>修改需求:`{prompt}`"])
     yield from update_ui(chatbot=chatbot, history=history)
-
     image_url, image_path = edit_image(llm_kwargs, prompt, image_path, resolution)
-    chatbot.append([state.prompt,  
+    chatbot.append([prompt,
         f'图像中转网址: <br/>`{image_url}`<br/>'+
         f'中转网址预览: <br/><div align="center"><img src="{image_url}"></div>'
         f'本地文件地址: <br/>`{image_path}`<br/>'+
         f'本地文件预览: <br/><div align="center"><img src="file={image_path}"></div>'
     ])
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 界面更新
+    state.unlock_plugin(chatbot)
 
+def make_transparent(input_image_path, output_image_path):
+    from PIL import Image
+    image = Image.open(input_image_path)
+    image = image.convert("RGBA")
+    data = image.getdata()
+    new_data = []
+    for item in data:
+        if item[0] == 255 and item[1] == 255 and item[2] == 255:
+            new_data.append((255, 255, 255, 0))
+        else:
+            new_data.append(item)
+    image.putdata(new_data)
+    image.save(output_image_path, "PNG")
+
+def resize_image(input_path, output_path, max_size=1024):
+    from PIL import Image
+    with Image.open(input_path) as img:
+        width, height = img.size
+        if width > max_size or height > max_size:
+            if width >= height:
+                new_width = max_size
+                new_height = int((max_size / width) * height)
+            else:
+                new_height = max_size
+                new_width = int((max_size / height) * width)
+
+            resized_img = img.resize(size=(new_width, new_height))
+            resized_img.save(output_path)
+        else:
+            img.save(output_path)
+
+def make_square_image(input_path, output_path):
+    from PIL import Image
+    with Image.open(input_path) as img:
+        width, height = img.size
+        size = max(width, height)
+        new_img = Image.new("RGBA", (size, size), color="black")
+        new_img.paste(img, ((size - width) // 2, (size - height) // 2))
+        new_img.save(output_path)

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)