update gr

crazy_functions/Latex输出PDF结果.py

@@ -5,7 +5,7 @@ import glob, os, requests, time
 pj = os.path.join
 ARXIV_CACHE_DIR = os.path.expanduser(f"~/arxiv_cache/")
 
-# =================================== 工具函数 ===============================================
+# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- 工具函数 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
 # 专业词汇声明  = 'If the term "agent" is used in this section, it should be translated to "智能体". '
 def switch_prompt(pfg, mode, more_requirement):
     """
@@ -142,7 +142,7 @@ def arxiv_download(chatbot, history, txt, allow_cache=True):
     from toolbox import extract_archive
     extract_archive(file_path=dst, dest_dir=extract_dst)
     return extract_dst, arxiv_id
-# ========================================= 插件主程序1 =====================================================    
+# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序1 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=    
 
 
 @CatchException
@@ -218,7 +218,7 @@ def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, histo
     # <-------------- we are done ------------->
     return success
 
-# ========================================= 插件主程序2 =====================================================    
+# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序2 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=    
 
 @CatchException
 def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):

crazy_functions/agent_fns/general.py

@@ -35,7 +35,11 @@ def gpt_academic_generate_oai_reply(
 class AutoGenGeneral(PluginMultiprocessManager):
     def gpt_academic_print_override(self, user_proxy, message, sender):
         # ⭐⭐ run in subprocess
-        self.child_conn.send(PipeCom("show", sender.name + "\n\n---\n\n" + message["content"]))
+        try:
+            print_msg = sender.name + "\n\n---\n\n" + message["content"]
+        except:
+            print_msg = sender.name + "\n\n---\n\n" + message
+        self.child_conn.send(PipeCom("show", print_msg))
 
     def gpt_academic_get_human_input(self, user_proxy, message):
         # ⭐⭐ run in subprocess
@@ -62,33 +66,33 @@ class AutoGenGeneral(PluginMultiprocessManager):
     def exe_autogen(self, input):
         # ⭐⭐ run in subprocess
         input = input.content
-        with ProxyNetworkActivate("AutoGen"):
-            code_execution_config = {"work_dir": self.autogen_work_dir, "use_docker": self.use_docker}
-            agents = self.define_agents()
-            user_proxy = None
-            assistant = None
-            for agent_kwargs in agents:
-                agent_cls = agent_kwargs.pop('cls')
-                kwargs = {
-                    'llm_config':self.llm_kwargs,
-                    'code_execution_config':code_execution_config
-                }
-                kwargs.update(agent_kwargs)
-                agent_handle = agent_cls(**kwargs)
-                agent_handle._print_received_message = lambda a,b: self.gpt_academic_print_override(agent_kwargs, a, b)
-                for d in agent_handle._reply_func_list:
-                    if hasattr(d['reply_func'],'__name__') and d['reply_func'].__name__ == 'generate_oai_reply':
-                        d['reply_func'] = gpt_academic_generate_oai_reply
-                if agent_kwargs['name'] == 'user_proxy':
-                    agent_handle.get_human_input = lambda a: self.gpt_academic_get_human_input(user_proxy, a)
-                    user_proxy = agent_handle
-                if agent_kwargs['name'] == 'assistant': assistant = agent_handle
-            try:
-                if user_proxy is None or assistant is None: raise Exception("用户代理或助理代理未定义")
+        code_execution_config = {"work_dir": self.autogen_work_dir, "use_docker": self.use_docker}
+        agents = self.define_agents()
+        user_proxy = None
+        assistant = None
+        for agent_kwargs in agents:
+            agent_cls = agent_kwargs.pop('cls')
+            kwargs = {
+                'llm_config':self.llm_kwargs,
+                'code_execution_config':code_execution_config
+            }
+            kwargs.update(agent_kwargs)
+            agent_handle = agent_cls(**kwargs)
+            agent_handle._print_received_message = lambda a,b: self.gpt_academic_print_override(agent_kwargs, a, b)
+            for d in agent_handle._reply_func_list:
+                if hasattr(d['reply_func'],'__name__') and d['reply_func'].__name__ == 'generate_oai_reply':
+                    d['reply_func'] = gpt_academic_generate_oai_reply
+            if agent_kwargs['name'] == 'user_proxy':
+                agent_handle.get_human_input = lambda a: self.gpt_academic_get_human_input(user_proxy, a)
+                user_proxy = agent_handle
+            if agent_kwargs['name'] == 'assistant': assistant = agent_handle
+        try:
+            if user_proxy is None or assistant is None: raise Exception("用户代理或助理代理未定义")
+            with ProxyNetworkActivate("AutoGen"):
                 user_proxy.initiate_chat(assistant, message=input)
-            except Exception as e:
-                tb_str = '```\n' + trimmed_format_exc() + '```'
-                self.child_conn.send(PipeCom("done", "AutoGen 执行失败: \n\n" + tb_str))
+        except Exception as e:
+            tb_str = '```\n' + trimmed_format_exc() + '```'
+            self.child_conn.send(PipeCom("done", "AutoGen 执行失败: \n\n" + tb_str))
 
     def subprocess_worker(self, child_conn):
         # ⭐⭐ run in subprocess

crazy_functions/crazy_utils.py

@@ -466,6 +466,9 @@ def read_and_clean_pdf_text(fp):
                     return True
                 else:
                     return False
+            # 对于某些PDF会有第一个段落就以小写字母开头,为了避免索引错误将其更改为大写
+            if starts_with_lowercase_word(meta_txt[0]):
+                meta_txt[0] = meta_txt[0].capitalize()
             for _ in range(100):
                 for index, block_txt in enumerate(meta_txt):
                     if starts_with_lowercase_word(block_txt):

crazy_functions/latex_fns/latex_toolbox.py

@@ -1,15 +1,18 @@
 import os, shutil
 import re
 import numpy as np
+
 PRESERVE = 0
 TRANSFORM = 1
 
 pj = os.path.join
 
-class LinkedListNode():
+
+class LinkedListNode:
     """
     Linked List Node
     """
+
     def __init__(self, string, preserve=True) -> None:
         self.string = string
         self.preserve = preserve
@@ -18,41 +21,47 @@ class LinkedListNode():
         # self.begin_line = 0
         # self.begin_char = 0
 
+
 def convert_to_linklist(text, mask):
     root = LinkedListNode("", preserve=True)
     current_node = root
     for c, m, i in zip(text, mask, range(len(text))):
-        if (m==PRESERVE and current_node.preserve) \
-            or (m==TRANSFORM and not current_node.preserve):
+        if (m == PRESERVE and current_node.preserve) or (
+            m == TRANSFORM and not current_node.preserve
+        ):
             # add
             current_node.string += c
         else:
-            current_node.next = LinkedListNode(c, preserve=(m==PRESERVE))
+            current_node.next = LinkedListNode(c, preserve=(m == PRESERVE))
             current_node = current_node.next
     return root
 
+
 def post_process(root):
     # 修复括号
     node = root
     while True:
         string = node.string
-        if node.preserve: 
+        if node.preserve:
             node = node.next
-            if node is None: break
+            if node is None:
+                break
             continue
+
         def break_check(string):
-            str_stack = [""] # (lv, index)
+            str_stack = [""]  # (lv, index)
             for i, c in enumerate(string):
-                if c == '{':
-                    str_stack.append('{')
-                elif c == '}':
+                if c == "{":
+                    str_stack.append("{")
+                elif c == "}":
                     if len(str_stack) == 1:
-                        print('stack fix')
+                        print("stack fix")
                         return i
                     str_stack.pop(-1)
                 else:
                     str_stack[-1] += c
             return -1
+
         bp = break_check(string)
 
         if bp == -1:
@@ -69,51 +78,66 @@ def post_process(root):
             node.next = q
 
         node = node.next
-        if node is None: break
+        if node is None:
+            break
 
     # 屏蔽空行和太短的句子
     node = root
     while True:
-        if len(node.string.strip('\n').strip(''))==0: node.preserve = True
-        if len(node.string.strip('\n').strip(''))<42: node.preserve = True
+        if len(node.string.strip("\n").strip("")) == 0:
+            node.preserve = True
+        if len(node.string.strip("\n").strip("")) < 42:
+            node.preserve = True
         node = node.next
-        if node is None: break
+        if node is None:
+            break
     node = root
     while True:
         if node.next and node.preserve and node.next.preserve:
             node.string += node.next.string
             node.next = node.next.next
         node = node.next
-        if node is None: break
+        if node is None:
+            break
 
     # 将前后断行符脱离
     node = root
     prev_node = None
     while True:
         if not node.preserve:
-            lstriped_ = node.string.lstrip().lstrip('\n')
-            if (prev_node is not None) and (prev_node.preserve) and (len(lstriped_)!=len(node.string)):
-                prev_node.string += node.string[:-len(lstriped_)]
+            lstriped_ = node.string.lstrip().lstrip("\n")
+            if (
+                (prev_node is not None)
+                and (prev_node.preserve)
+                and (len(lstriped_) != len(node.string))
+            ):
+                prev_node.string += node.string[: -len(lstriped_)]
                 node.string = lstriped_
-            rstriped_ = node.string.rstrip().rstrip('\n')
-            if (node.next is not None) and (node.next.preserve) and (len(rstriped_)!=len(node.string)):
-                node.next.string = node.string[len(rstriped_):] + node.next.string
+            rstriped_ = node.string.rstrip().rstrip("\n")
+            if (
+                (node.next is not None)
+                and (node.next.preserve)
+                and (len(rstriped_) != len(node.string))
+            ):
+                node.next.string = node.string[len(rstriped_) :] + node.next.string
                 node.string = rstriped_
-        # =====
+        # =-=-=
         prev_node = node
         node = node.next
-        if node is None: break
+        if node is None:
+            break
 
     # 标注节点的行数范围
     node = root
     n_line = 0
     expansion = 2
     while True:
-        n_l = node.string.count('\n')
-        node.range = [n_line-expansion, n_line+n_l+expansion]   # 失败时，扭转的范围
-        n_line = n_line+n_l
+        n_l = node.string.count("\n")
+        node.range = [n_line - expansion, n_line + n_l + expansion]  # 失败时，扭转的范围
+        n_line = n_line + n_l
         node = node.next
-        if node is None: break
+        if node is None:
+            break
     return root
 
 
@@ -128,97 +152,125 @@ def set_forbidden_text(text, mask, pattern, flags=0):
     """
     Add a preserve text area in this paper
     e.g. with pattern = r"\\begin\{algorithm\}(.*?)\\end\{algorithm\}"
-    you can mask out (mask = PRESERVE so that text become untouchable for GPT) 
+    you can mask out (mask = PRESERVE so that text become untouchable for GPT)
     everything between "\begin{equation}" and "\end{equation}"
     """
-    if isinstance(pattern, list): pattern = '|'.join(pattern)
+    if isinstance(pattern, list):
+        pattern = "|".join(pattern)
     pattern_compile = re.compile(pattern, flags)
     for res in pattern_compile.finditer(text):
-        mask[res.span()[0]:res.span()[1]] = PRESERVE
+        mask[res.span()[0] : res.span()[1]] = PRESERVE
     return text, mask
 
+
 def reverse_forbidden_text(text, mask, pattern, flags=0, forbid_wrapper=True):
     """
     Move area out of preserve area (make text editable for GPT)
-    count the number of the braces so as to catch compelete text area. 
+    count the number of the braces so as to catch compelete text area.
     e.g.
-    \begin{abstract} blablablablablabla. \end{abstract} 
+    \begin{abstract} blablablablablabla. \end{abstract}
     """
-    if isinstance(pattern, list): pattern = '|'.join(pattern)
+    if isinstance(pattern, list):
+        pattern = "|".join(pattern)
     pattern_compile = re.compile(pattern, flags)
     for res in pattern_compile.finditer(text):
         if not forbid_wrapper:
-            mask[res.span()[0]:res.span()[1]] = TRANSFORM
+            mask[res.span()[0] : res.span()[1]] = TRANSFORM
         else:
-            mask[res.regs[0][0]: res.regs[1][0]] = PRESERVE   # '\\begin{abstract}'
-            mask[res.regs[1][0]: res.regs[1][1]] = TRANSFORM   # abstract
-            mask[res.regs[1][1]: res.regs[0][1]] = PRESERVE   # abstract
+            mask[res.regs[0][0] : res.regs[1][0]] = PRESERVE  # '\\begin{abstract}'
+            mask[res.regs[1][0] : res.regs[1][1]] = TRANSFORM  # abstract
+            mask[res.regs[1][1] : res.regs[0][1]] = PRESERVE  # abstract
     return text, mask
 
+
 def set_forbidden_text_careful_brace(text, mask, pattern, flags=0):
     """
     Add a preserve text area in this paper (text become untouchable for GPT).
-    count the number of the braces so as to catch compelete text area. 
+    count the number of the braces so as to catch compelete text area.
     e.g.
-    \caption{blablablablabla\texbf{blablabla}blablabla.} 
+    \caption{blablablablabla\texbf{blablabla}blablabla.}
     """
     pattern_compile = re.compile(pattern, flags)
     for res in pattern_compile.finditer(text):
         brace_level = -1
         p = begin = end = res.regs[0][0]
-        for _ in range(1024*16):
-            if text[p] == '}' and brace_level == 0: break
-            elif text[p] == '}':  brace_level -= 1
-            elif text[p] == '{':  brace_level += 1
+        for _ in range(1024 * 16):
+            if text[p] == "}" and brace_level == 0:
+                break
+            elif text[p] == "}":
+                brace_level -= 1
+            elif text[p] == "{":
+                brace_level += 1
             p += 1
-        end = p+1
+        end = p + 1
         mask[begin:end] = PRESERVE
     return text, mask
 
-def reverse_forbidden_text_careful_brace(text, mask, pattern, flags=0, forbid_wrapper=True):
+
+def reverse_forbidden_text_careful_brace(
+    text, mask, pattern, flags=0, forbid_wrapper=True
+):
     """
     Move area out of preserve area (make text editable for GPT)
-    count the number of the braces so as to catch compelete text area. 
+    count the number of the braces so as to catch compelete text area.
     e.g.
-    \caption{blablablablabla\texbf{blablabla}blablabla.} 
+    \caption{blablablablabla\texbf{blablabla}blablabla.}
     """
     pattern_compile = re.compile(pattern, flags)
     for res in pattern_compile.finditer(text):
         brace_level = 0
         p = begin = end = res.regs[1][0]
-        for _ in range(1024*16):
-            if text[p] == '}' and brace_level == 0: break
-            elif text[p] == '}':  brace_level -= 1
-            elif text[p] == '{':  brace_level += 1
+        for _ in range(1024 * 16):
+            if text[p] == "}" and brace_level == 0:
+                break
+            elif text[p] == "}":
+                brace_level -= 1
+            elif text[p] == "{":
+                brace_level += 1
             p += 1
         end = p
         mask[begin:end] = TRANSFORM
         if forbid_wrapper:
-            mask[res.regs[0][0]:begin] = PRESERVE
-            mask[end:res.regs[0][1]] = PRESERVE
+            mask[res.regs[0][0] : begin] = PRESERVE
+            mask[end : res.regs[0][1]] = PRESERVE
     return text, mask
 
+
 def set_forbidden_text_begin_end(text, mask, pattern, flags=0, limit_n_lines=42):
     """
     Find all \begin{} ... \end{} text block that with less than limit_n_lines lines.
     Add it to preserve area
     """
     pattern_compile = re.compile(pattern, flags)
+
     def search_with_line_limit(text, mask):
         for res in pattern_compile.finditer(text):
             cmd = res.group(1)  # begin{what}
-            this = res.group(2) # content between begin and end
-            this_mask = mask[res.regs[2][0]:res.regs[2][1]]
-            white_list = ['document', 'abstract', 'lemma', 'definition', 'sproof', 
-                          'em', 'emph', 'textit', 'textbf', 'itemize', 'enumerate']
-            if (cmd in white_list) or this.count('\n') >= limit_n_lines: # use a magical number 42
+            this = res.group(2)  # content between begin and end
+            this_mask = mask[res.regs[2][0] : res.regs[2][1]]
+            white_list = [
+                "document",
+                "abstract",
+                "lemma",
+                "definition",
+                "sproof",
+                "em",
+                "emph",
+                "textit",
+                "textbf",
+                "itemize",
+                "enumerate",
+            ]
+            if (cmd in white_list) or this.count(
+                "\n"
+            ) >= limit_n_lines:  # use a magical number 42
                 this, this_mask = search_with_line_limit(this, this_mask)
-                mask[res.regs[2][0]:res.regs[2][1]] = this_mask
+                mask[res.regs[2][0] : res.regs[2][1]] = this_mask
             else:
-                mask[res.regs[0][0]:res.regs[0][1]] = PRESERVE
+                mask[res.regs[0][0] : res.regs[0][1]] = PRESERVE
         return text, mask
-    return search_with_line_limit(text, mask) 
 
+    return search_with_line_limit(text, mask)
 
 
 """
@@ -227,6 +279,7 @@ Latex Merge File
 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
 """
 
+
 def find_main_tex_file(file_manifest, mode):
     """
     在多Tex文档中，寻找主文件，必须包含documentclass，返回找到的第一个。
@@ -234,27 +287,36 @@ def find_main_tex_file(file_manifest, mode):
     """
     canidates = []
     for texf in file_manifest:
-        if os.path.basename(texf).startswith('merge'):
+        if os.path.basename(texf).startswith("merge"):
             continue
-        with open(texf, 'r', encoding='utf8', errors='ignore') as f:
+        with open(texf, "r", encoding="utf8", errors="ignore") as f:
             file_content = f.read()
-        if r'\documentclass' in file_content:
+        if r"\documentclass" in file_content:
             canidates.append(texf)
         else:
             continue
 
     if len(canidates) == 0:
-        raise RuntimeError('无法找到一个主Tex文件（包含documentclass关键字）')
+        raise RuntimeError("无法找到一个主Tex文件（包含documentclass关键字）")
     elif len(canidates) == 1:
         return canidates[0]
-    else: # if len(canidates) >= 2 通过一些Latex模板中常见（但通常不会出现在正文）的单词，对不同latex源文件扣分，取评分最高者返回
+    else:  # if len(canidates) >= 2 通过一些Latex模板中常见（但通常不会出现在正文）的单词，对不同latex源文件扣分，取评分最高者返回
         canidates_score = []
         # 给出一些判定模板文档的词作为扣分项
-        unexpected_words = ['\LaTeX', 'manuscript', 'Guidelines', 'font', 'citations', 'rejected', 'blind review', 'reviewers']
-        expected_words = ['\input', '\ref', '\cite']
+        unexpected_words = [
+            "\\LaTeX",
+            "manuscript",
+            "Guidelines",
+            "font",
+            "citations",
+            "rejected",
+            "blind review",
+            "reviewers",
+        ]
+        expected_words = ["\\input", "\\ref", "\\cite"]
         for texf in canidates:
             canidates_score.append(0)
-            with open(texf, 'r', encoding='utf8', errors='ignore') as f:
+            with open(texf, "r", encoding="utf8", errors="ignore") as f:
                 file_content = f.read()
                 file_content = rm_comments(file_content)
             for uw in unexpected_words:
@@ -263,9 +325,10 @@ def find_main_tex_file(file_manifest, mode):
             for uw in expected_words:
                 if uw in file_content:
                     canidates_score[-1] += 1
-        select = np.argmax(canidates_score) # 取评分最高者返回
+        select = np.argmax(canidates_score)  # 取评分最高者返回
         return canidates[select]
-    
+
+
 def rm_comments(main_file):
     new_file_remove_comment_lines = []
     for l in main_file.splitlines():
@@ -274,30 +337,39 @@ def rm_comments(main_file):
             pass
         else:
             new_file_remove_comment_lines.append(l)
-    main_file = '\n'.join(new_file_remove_comment_lines)
+    main_file = "\n".join(new_file_remove_comment_lines)
     # main_file = re.sub(r"\\include{(.*?)}", r"\\input{\1}", main_file)  # 将 \include 命令转换为 \input 命令
-    main_file = re.sub(r'(?<!\\)%.*', '', main_file)  # 使用正则表达式查找半行注释, 并替换为空字符串
+    main_file = re.sub(r"(?<!\\)%.*", "", main_file)  # 使用正则表达式查找半行注释, 并替换为空字符串
     return main_file
 
+
 def find_tex_file_ignore_case(fp):
     dir_name = os.path.dirname(fp)
     base_name = os.path.basename(fp)
     # 如果输入的文件路径是正确的
-    if os.path.isfile(pj(dir_name, base_name)): return pj(dir_name, base_name)
+    if os.path.isfile(pj(dir_name, base_name)):
+        return pj(dir_name, base_name)
     # 如果不正确，试着加上.tex后缀试试
-    if not base_name.endswith('.tex'): base_name+='.tex'
-    if os.path.isfile(pj(dir_name, base_name)): return pj(dir_name, base_name)
+    if not base_name.endswith(".tex"):
+        base_name += ".tex"
+    if os.path.isfile(pj(dir_name, base_name)):
+        return pj(dir_name, base_name)
     # 如果还找不到，解除大小写限制，再试一次
     import glob
-    for f in glob.glob(dir_name+'/*.tex'):
+
+    for f in glob.glob(dir_name + "/*.tex"):
         base_name_s = os.path.basename(fp)
         base_name_f = os.path.basename(f)
-        if base_name_s.lower() == base_name_f.lower(): return f
+        if base_name_s.lower() == base_name_f.lower():
+            return f
         # 试着加上.tex后缀试试
-        if not base_name_s.endswith('.tex'): base_name_s+='.tex'
-        if base_name_s.lower() == base_name_f.lower(): return f
+        if not base_name_s.endswith(".tex"):
+            base_name_s += ".tex"
+        if base_name_s.lower() == base_name_f.lower():
+            return f
     return None
 
+
 def merge_tex_files_(project_foler, main_file, mode):
     """
     Merge Tex project recrusively
@@ -309,18 +381,18 @@ def merge_tex_files_(project_foler, main_file, mode):
         fp_ = find_tex_file_ignore_case(fp)
         if fp_:
             try:
-                with open(fp_, 'r', encoding='utf-8', errors='replace') as fx: c = fx.read()
+                with open(fp_, "r", encoding="utf-8", errors="replace") as fx:
+                    c = fx.read()
             except:
                 c = f"\n\nWarning from GPT-Academic: LaTex source file is missing!\n\n"
         else:
-            raise RuntimeError(f'找不到{fp}，Tex源文件缺失！')
+            raise RuntimeError(f"找不到{fp}，Tex源文件缺失！")
         c = merge_tex_files_(project_foler, c, mode)
-        main_file = main_file[:s.span()[0]] + c + main_file[s.span()[1]:]
+        main_file = main_file[: s.span()[0]] + c + main_file[s.span()[1] :]
     return main_file
 
 
 def find_title_and_abs(main_file):
-
     def extract_abstract_1(text):
         pattern = r"\\abstract\{(.*?)\}"
         match = re.search(pattern, text, re.DOTALL)
@@ -362,21 +434,30 @@ def merge_tex_files(project_foler, main_file, mode):
     main_file = merge_tex_files_(project_foler, main_file, mode)
     main_file = rm_comments(main_file)
 
-    if mode == 'translate_zh':
+    if mode == "translate_zh":
         # find paper documentclass
-        pattern = re.compile(r'\\documentclass.*\n')
+        pattern = re.compile(r"\\documentclass.*\n")
         match = pattern.search(main_file)
         assert match is not None, "Cannot find documentclass statement!"
         position = match.end()
-        add_ctex = '\\usepackage{ctex}\n'
-        add_url = '\\usepackage{url}\n' if '{url}' not in main_file else ''
+        add_ctex = "\\usepackage{ctex}\n"
+        add_url = "\\usepackage{url}\n" if "{url}" not in main_file else ""
         main_file = main_file[:position] + add_ctex + add_url + main_file[position:]
         # fontset=windows
         import platform
-        main_file = re.sub(r"\\documentclass\[(.*?)\]{(.*?)}", r"\\documentclass[\1,fontset=windows,UTF8]{\2}",main_file)
-        main_file = re.sub(r"\\documentclass{(.*?)}", r"\\documentclass[fontset=windows,UTF8]{\1}",main_file)
+
+        main_file = re.sub(
+            r"\\documentclass\[(.*?)\]{(.*?)}",
+            r"\\documentclass[\1,fontset=windows,UTF8]{\2}",
+            main_file,
+        )
+        main_file = re.sub(
+            r"\\documentclass{(.*?)}",
+            r"\\documentclass[fontset=windows,UTF8]{\1}",
+            main_file,
+        )
         # find paper abstract
-        pattern_opt1 = re.compile(r'\\begin\{abstract\}.*\n')
+        pattern_opt1 = re.compile(r"\\begin\{abstract\}.*\n")
         pattern_opt2 = re.compile(r"\\abstract\{(.*?)\}", flags=re.DOTALL)
         match_opt1 = pattern_opt1.search(main_file)
         match_opt2 = pattern_opt2.search(main_file)
@@ -385,7 +466,9 @@ def merge_tex_files(project_foler, main_file, mode):
             main_file = insert_abstract(main_file)
         match_opt1 = pattern_opt1.search(main_file)
         match_opt2 = pattern_opt2.search(main_file)
-        assert (match_opt1 is not None) or (match_opt2 is not None), "Cannot find paper abstract section!"
+        assert (match_opt1 is not None) or (
+            match_opt2 is not None
+        ), "Cannot find paper abstract section!"
     return main_file
 
 
@@ -395,6 +478,7 @@ The GPT-Academic program cannot find abstract section in this paper.
 \end{abstract}
 """
 
+
 def insert_abstract(tex_content):
     if "\\maketitle" in tex_content:
         # find the position of "\maketitle"
@@ -402,7 +486,13 @@ def insert_abstract(tex_content):
         # find the nearest ending line
         end_line_index = tex_content.find("\n", find_index)
         # insert "abs_str" on the next line
-        modified_tex = tex_content[:end_line_index+1] + '\n\n' + insert_missing_abs_str + '\n\n' + tex_content[end_line_index+1:]
+        modified_tex = (
+            tex_content[: end_line_index + 1]
+            + "\n\n"
+            + insert_missing_abs_str
+            + "\n\n"
+            + tex_content[end_line_index + 1 :]
+        )
         return modified_tex
     elif r"\begin{document}" in tex_content:
         # find the position of "\maketitle"
@@ -410,29 +500,39 @@ def insert_abstract(tex_content):
         # find the nearest ending line
         end_line_index = tex_content.find("\n", find_index)
         # insert "abs_str" on the next line
-        modified_tex = tex_content[:end_line_index+1] + '\n\n' + insert_missing_abs_str + '\n\n' + tex_content[end_line_index+1:]
+        modified_tex = (
+            tex_content[: end_line_index + 1]
+            + "\n\n"
+            + insert_missing_abs_str
+            + "\n\n"
+            + tex_content[end_line_index + 1 :]
+        )
         return modified_tex
     else:
         return tex_content
 
+
 """
 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
 Post process
 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
 """
+
+
 def mod_inbraket(match):
     """
-    为啥chatgpt会把cite里面的逗号换成中文逗号呀 
+    为啥chatgpt会把cite里面的逗号换成中文逗号呀
     """
     # get the matched string
     cmd = match.group(1)
     str_to_modify = match.group(2)
     # modify the matched string
-    str_to_modify = str_to_modify.replace('：', ':')    # 前面是中文冒号，后面是英文冒号
-    str_to_modify = str_to_modify.replace('，', ',')    # 前面是中文逗号，后面是英文逗号
+    str_to_modify = str_to_modify.replace("：", ":")  # 前面是中文冒号，后面是英文冒号
+    str_to_modify = str_to_modify.replace("，", ",")  # 前面是中文逗号，后面是英文逗号
     # str_to_modify = 'BOOM'
     return "\\" + cmd + "{" + str_to_modify + "}"
 
+
 def fix_content(final_tex, node_string):
     """
     Fix common GPT errors to increase success rate
@@ -443,10 +543,10 @@ def fix_content(final_tex, node_string):
     final_tex = re.sub(r"\\([a-z]{2,10})\{([^\}]*?)\}", mod_inbraket, string=final_tex)
 
     if "Traceback" in final_tex and "[Local Message]" in final_tex:
-        final_tex = node_string # 出问题了，还原原文
-    if node_string.count('\\begin') != final_tex.count('\\begin'):
-        final_tex = node_string # 出问题了，还原原文
-    if node_string.count('\_') > 0 and node_string.count('\_') > final_tex.count('\_'):
+        final_tex = node_string  # 出问题了，还原原文
+    if node_string.count("\\begin") != final_tex.count("\\begin"):
+        final_tex = node_string  # 出问题了，还原原文
+    if node_string.count("\_") > 0 and node_string.count("\_") > final_tex.count("\_"):
         # walk and replace any _ without \
         final_tex = re.sub(r"(?<!\\)_", "\\_", final_tex)
 
@@ -454,24 +554,32 @@ def fix_content(final_tex, node_string):
         # this function count the number of { and }
         brace_level = 0
         for c in string:
-            if c == "{": brace_level += 1
-            elif c == "}": brace_level -= 1
+            if c == "{":
+                brace_level += 1
+            elif c == "}":
+                brace_level -= 1
         return brace_level
+
     def join_most(tex_t, tex_o):
         # this function join translated string and original string when something goes wrong
         p_t = 0
         p_o = 0
+
         def find_next(string, chars, begin):
             p = begin
             while p < len(string):
-                if string[p] in chars: return p, string[p]
+                if string[p] in chars:
+                    return p, string[p]
                 p += 1
             return None, None
+
         while True:
-            res1, char = find_next(tex_o, ['{','}'], p_o)
-            if res1 is None: break
+            res1, char = find_next(tex_o, ["{", "}"], p_o)
+            if res1 is None:
+                break
             res2, char = find_next(tex_t, [char], p_t)
-            if res2 is None: break
+            if res2 is None:
+                break
             p_o = res1 + 1
             p_t = res2 + 1
         return tex_t[:p_t] + tex_o[p_o:]
@@ -480,10 +588,14 @@ def fix_content(final_tex, node_string):
         # 出问题了，还原部分原文，保证括号正确
         final_tex = join_most(final_tex, node_string)
     return final_tex
-    
+
+
 def compile_latex_with_timeout(command, cwd, timeout=60):
     import subprocess
-    process = subprocess.Popen(command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE, cwd=cwd)
+
+    process = subprocess.Popen(
+        command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE, cwd=cwd
+    )
     try:
         stdout, stderr = process.communicate(timeout=timeout)
     except subprocess.TimeoutExpired:
@@ -493,43 +605,52 @@ 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
+        return_dict["result"] = result
     except Exception as e:
         exc_info = sys.exc_info()
-        exception_dict['exception'] = 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 = 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:
+        if "exception" in exception_dict:
             # ooops, the subprocess ran into an exception
-            exc_info = exception_dict['exception']
+            exc_info = exception_dict["exception"]
             raise exc_info[1].with_traceback(exc_info[2])
-        if 'result' in return_dict.keys():
+        if "result" in return_dict.keys():
             # If the subprocess ran successfully, return the result
-            return return_dict['result']
+            return return_dict["result"]
+
     return wrapper
 
+
 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
+    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:
+    with open(pdf1_path, "rb") as pdf1_file:
         pdf1_reader = PyPDF2.PdfFileReader(pdf1_file)
         # Open the second PDF file
-        with open(pdf2_path, 'rb') as pdf2_file:
+        with open(pdf2_path, "rb") as pdf2_file:
             pdf2_reader = PyPDF2.PdfFileReader(pdf2_file)
             # Create a new PDF file to store the merged pages
             output_writer = PyPDF2.PdfFileWriter()
@@ -549,14 +670,25 @@ def _merge_pdfs(pdf1_path, pdf2_path, output_path):
                     page2 = PyPDF2.PageObject.createBlankPage(pdf1_reader)
                 # Create a new empty page with double width
                 new_page = PyPDF2.PageObject.createBlankPage(
-                    width = int(int(page1.mediaBox.getWidth()) + int(page2.mediaBox.getWidth()) * Percent),
-                    height = max(page1.mediaBox.getHeight(), page2.mediaBox.getHeight())
+                    width=int(
+                        int(page1.mediaBox.getWidth())
+                        + int(page2.mediaBox.getWidth()) * Percent
+                    ),
+                    height=max(page1.mediaBox.getHeight(), page2.mediaBox.getHeight()),
                 )
                 new_page.mergeTranslatedPage(page1, 0, 0)
-                new_page.mergeTranslatedPage(page2, int(int(page1.mediaBox.getWidth())-int(page2.mediaBox.getWidth())* (1-Percent)), 0)
+                new_page.mergeTranslatedPage(
+                    page2,
+                    int(
+                        int(page1.mediaBox.getWidth())
+                        - int(page2.mediaBox.getWidth()) * (1 - Percent)
+                    ),
+                    0,
+                )
                 output_writer.addPage(new_page)
             # Save the merged PDF file
-            with open(output_path, 'wb') as output_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
+
+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/pdf_fns/breakdown_txt.py

@@ -65,10 +65,10 @@ def cut(limit, get_token_fn, txt_tocut, must_break_at_empty_line, break_anyway=F
                 # 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)
+                    prev, post = force_breakdown(remain_txt_to_cut, 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}")
+                    raise RuntimeError(f"存在一行极长的文本！{remain_txt_to_cut}")
 
             # 追加列表
             res.append(prev); fin_len+=len(prev)

crazy_functions/多智能体.py

@@ -50,14 +50,7 @@ def 多智能体终端(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
         return
     if model_info[llm_kwargs['llm_model']]["endpoint"] is not None: # 如果不是本地模型，加载API_KEY
         llm_kwargs['api_key'] = select_api_key(llm_kwargs['api_key'], llm_kwargs['llm_model'])
-    
-    # 检查当前的模型是否符合要求
-    API_URL_REDIRECT = get_conf('API_URL_REDIRECT')
-    if len(API_URL_REDIRECT) > 0:
-        chatbot.append([f"处理任务: {txt}", f"暂不支持中转."])
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return
-    
+
     # 尝试导入依赖，如果缺少依赖，则给出安装建议
     try:
         import autogen

crazy_functions/数学动画生成manim.py

@@ -1,6 +1,7 @@
-from toolbox import CatchException, update_ui, gen_time_str
-from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
-from .crazy_utils import input_clipping
+import os
+from toolbox import CatchException, update_ui, gen_time_str, promote_file_to_downloadzone
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+from crazy_functions.crazy_utils import input_clipping
 
 def inspect_dependency(chatbot, history):
     # 尝试导入依赖，如果缺少依赖，则给出安装建议
@@ -27,9 +28,10 @@ def eval_manim(code):
     class_name = get_class_name(code)
 
     try: 
+        time_str = gen_time_str()
         subprocess.check_output([sys.executable, '-c', f"from gpt_log.MyAnimation import {class_name}; {class_name}().render()"])
-        shutil.move('media/videos/1080p60/{class_name}.mp4', f'gpt_log/{class_name}-{gen_time_str()}.mp4')
-        return f'gpt_log/{gen_time_str()}.mp4'
+        shutil.move(f'media/videos/1080p60/{class_name}.mp4', f'gpt_log/{class_name}-{time_str}.mp4')
+        return f'gpt_log/{time_str}.mp4'
     except subprocess.CalledProcessError as e:
         output = e.output.decode()
         print(f"Command returned non-zero exit status {e.returncode}: {output}.")
@@ -94,6 +96,8 @@ def 动画生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
     res = eval_manim(code)
 
     chatbot.append(("生成的视频文件路径", res))
+    if os.path.exists(res):
+        promote_file_to_downloadzone(res, chatbot=chatbot)
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
 
 # 在这里放一些网上搜集的demo，辅助gpt生成代码

crazy_functions/高级功能函数模板.py

@@ -26,4 +26,46 @@ def 高阶功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
         )
         chatbot[-1] = (i_say, gpt_say)
         history.append(i_say);history.append(gpt_say)
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
+
+
+
+
+PROMPT = """
+请你给出围绕“{subject}”的逻辑关系图，使用mermaid语法，mermaid语法举例：
+```mermaid
+graph TD
+    P(编程) --> L1(Python)
+    P(编程) --> L2(C)
+    P(编程) --> L3(C++)
+    P(编程) --> L4(Javascipt)
+    P(编程) --> L5(PHP)
+```
+"""
+@CatchException
+def 测试图表渲染(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+    """
+    txt             输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径
+    llm_kwargs      gpt模型参数，如温度和top_p等，一般原样传递下去就行
+    plugin_kwargs   插件模型的参数，用于灵活调整复杂功能的各种参数
+    chatbot         聊天显示框的句柄，用于显示给用户
+    history         聊天历史，前情提要
+    system_prompt   给gpt的静默提醒
+    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(("这是什么功能？", "一个测试mermaid绘制图表的功能，您可以在输入框中输入一些关键词，然后使用mermaid+llm绘制图表。"))
+    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 txt == "": txt = "空白的输入栏" # 调皮一下
+    
+    i_say_show_user = f'请绘制有关“{txt}”的逻辑关系图。'
+    i_say = PROMPT.format(subject=txt)
+    gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
+        inputs=i_say,
+        inputs_show_user=i_say_show_user,
+        llm_kwargs=llm_kwargs, chatbot=chatbot, history=[], 
+        sys_prompt=""
+    )
+    history.append(i_say); history.append(gpt_say)
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新