new version

crazy_functions/Langchain知识库.py

@@ -53,14 +53,14 @@ def 知识库问答(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
     print('Checking Text2vec ...')
     from langchain.embeddings.huggingface import HuggingFaceEmbeddings
-    with ProxyNetworkActivate():    # 临时地激活代理网络
+    with ProxyNetworkActivate('Download_LLM'):    # 临时地激活代理网络
         HuggingFaceEmbeddings(model_name="GanymedeNil/text2vec-large-chinese")
 
     # < -------------------构建知识库--------------- >
     chatbot.append(['<br/>'.join(file_manifest), "正在构建知识库..."])
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
     print('Establishing knowledge archive ...')
-    with ProxyNetworkActivate():    # 临时地激活代理网络
+    with ProxyNetworkActivate('Download_LLM'):    # 临时地激活代理网络
         kai = knowledge_archive_interface()
         kai.feed_archive(file_manifest=file_manifest, id=kai_id)
     kai_files = kai.get_loaded_file()

crazy_functions/Latex输出PDF结果.py

@@ -79,7 +79,7 @@ def move_project(project_folder, arxiv_id=None):
     shutil.copytree(src=project_folder, dst=new_workfolder)
     return new_workfolder
 
-def arxiv_download(chatbot, history, txt):
+def arxiv_download(chatbot, history, txt, allow_cache=True):
     def check_cached_translation_pdf(arxiv_id):
         translation_dir = pj(ARXIV_CACHE_DIR, arxiv_id, 'translation')
         if not os.path.exists(translation_dir):
@@ -116,7 +116,7 @@ def arxiv_download(chatbot, history, txt):
     arxiv_id = url_.split('/abs/')[-1]
     if 'v' in arxiv_id: arxiv_id = arxiv_id[:10]
     cached_translation_pdf = check_cached_translation_pdf(arxiv_id)
-    if cached_translation_pdf: return cached_translation_pdf, arxiv_id
+    if cached_translation_pdf and allow_cache: return cached_translation_pdf, arxiv_id
 
     url_tar = url_.replace('/abs/', '/e-print/')
     translation_dir = pj(ARXIV_CACHE_DIR, arxiv_id, 'e-print')
@@ -228,6 +228,9 @@ def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot,
     # <-------------- more requirements ------------->
     if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
     more_req = plugin_kwargs.get("advanced_arg", "")
+    no_cache = more_req.startswith("--no-cache")
+    if no_cache: more_req.lstrip("--no-cache")
+    allow_cache = not no_cache
     _switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
 
     # <-------------- check deps ------------->
@@ -244,7 +247,7 @@ def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot,
 
     # <-------------- clear history and read input ------------->
     history = []
-    txt, arxiv_id = yield from arxiv_download(chatbot, history, txt)
+    txt, arxiv_id = yield from arxiv_download(chatbot, history, txt, allow_cache)
     if txt.endswith('.pdf'):
         report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"发现已经存在翻译好的PDF文档")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面

crazy_functions/crazy_utils.py

@@ -651,7 +651,7 @@ class knowledge_archive_interface():
             from toolbox import ProxyNetworkActivate
             print('Checking Text2vec ...')
             from langchain.embeddings.huggingface import HuggingFaceEmbeddings
-            with ProxyNetworkActivate():    # 临时地激活代理网络
+            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
@@ -807,3 +807,10 @@ class construct_html():
         with open(os.path.join(get_log_folder(), file_name), 'w', encoding='utf8') as f:
             f.write(self.html_string.encode('utf-8', 'ignore').decode())
         return os.path.join(get_log_folder(), file_name)
+
+
+def get_plugin_arg(plugin_kwargs, key, default):
+    # 如果参数是空的
+    if (key in plugin_kwargs) and (plugin_kwargs[key] == ""): plugin_kwargs.pop(key)
+    # 正常情况
+    return plugin_kwargs.get(key, default)

crazy_functions/gen_fns/gen_fns_shared.py

@@ -0,0 +1,70 @@
+import time
+import importlib
+from toolbox import trimmed_format_exc, gen_time_str, get_log_folder
+from toolbox import CatchException, update_ui, gen_time_str, trimmed_format_exc, is_the_upload_folder
+from toolbox import promote_file_to_downloadzone, get_log_folder, update_ui_lastest_msg
+import multiprocessing
+
+def get_class_name(class_string):
+    import re
+    # Use regex to extract the class name
+    class_name = re.search(r'class (\w+)\(', class_string).group(1)
+    return class_name
+
+def try_make_module(code, chatbot):
+    module_file = 'gpt_fn_' + gen_time_str().replace('-','_')
+    fn_path = f'{get_log_folder(plugin_name="gen_plugin_verify")}/{module_file}.py'
+    with open(fn_path, 'w', encoding='utf8') as f: f.write(code)
+    promote_file_to_downloadzone(fn_path, chatbot=chatbot)
+    class_name = get_class_name(code)
+    manager = multiprocessing.Manager()
+    return_dict = manager.dict()
+    p = multiprocessing.Process(target=is_function_successfully_generated, args=(fn_path, class_name, return_dict))
+    # only has 10 seconds to run
+    p.start(); p.join(timeout=10)
+    if p.is_alive(): p.terminate(); p.join()
+    p.close()
+    return return_dict["success"], return_dict['traceback']
+
+# check is_function_successfully_generated
+def is_function_successfully_generated(fn_path, class_name, return_dict):
+    return_dict['success'] = False
+    return_dict['traceback'] = ""
+    try:
+        # Create a spec for the module
+        module_spec = importlib.util.spec_from_file_location('example_module', fn_path)
+        # Load the module
+        example_module = importlib.util.module_from_spec(module_spec)
+        module_spec.loader.exec_module(example_module)
+        # Now you can use the module
+        some_class = getattr(example_module, class_name)
+        # Now you can create an instance of the class
+        instance = some_class()
+        return_dict['success'] = True
+        return 
+    except:
+        return_dict['traceback'] = trimmed_format_exc()
+        return
+    
+def subprocess_worker(code, file_path, return_dict):
+    return_dict['result'] = None
+    return_dict['success'] = False
+    return_dict['traceback'] = ""
+    try:
+        module_file = 'gpt_fn_' + gen_time_str().replace('-','_')
+        fn_path = f'{get_log_folder(plugin_name="gen_plugin_run")}/{module_file}.py'
+        with open(fn_path, 'w', encoding='utf8') as f: f.write(code)
+        class_name = get_class_name(code)
+        # Create a spec for the module
+        module_spec = importlib.util.spec_from_file_location('example_module', fn_path)
+        # Load the module
+        example_module = importlib.util.module_from_spec(module_spec)
+        module_spec.loader.exec_module(example_module)
+        # Now you can use the module
+        some_class = getattr(example_module, class_name)
+        # Now you can create an instance of the class
+        instance = some_class()
+        return_dict['result'] = instance.run(file_path)
+        return_dict['success'] = True
+    except:
+        return_dict['traceback'] = trimmed_format_exc()

crazy_functions/pdf_fns/parse_pdf.py

@@ -1,16 +1,26 @@
+from functools import lru_cache
+from toolbox import gen_time_str
+from toolbox import promote_file_to_downloadzone
+from toolbox import write_history_to_file, promote_file_to_downloadzone
+from toolbox import get_conf
+from toolbox import ProxyNetworkActivate
+from colorful import *
 import requests
 import random
-from functools import lru_cache
+import copy
+import os
+import math
+
 class GROBID_OFFLINE_EXCEPTION(Exception): pass
 
 def get_avail_grobid_url():
-    from toolbox import get_conf
     GROBID_URLS, = get_conf('GROBID_URLS')
     if len(GROBID_URLS) == 0: return None
     try:
         _grobid_url = random.choice(GROBID_URLS) # 随机负载均衡
         if _grobid_url.endswith('/'): _grobid_url = _grobid_url.rstrip('/')
-        res = requests.get(_grobid_url+'/api/isalive')
+        with ProxyNetworkActivate('Connect_Grobid'):
+            res = requests.get(_grobid_url+'/api/isalive')
         if res.text=='true': return _grobid_url
         else: return None
     except:
@@ -21,10 +31,141 @@ def parse_pdf(pdf_path, grobid_url):
     import scipdf   # pip install scipdf_parser
     if grobid_url.endswith('/'): grobid_url = grobid_url.rstrip('/')
     try:
-        article_dict = scipdf.parse_pdf_to_dict(pdf_path, grobid_url=grobid_url)
+        with ProxyNetworkActivate('Connect_Grobid'):
+            article_dict = scipdf.parse_pdf_to_dict(pdf_path, grobid_url=grobid_url)
     except GROBID_OFFLINE_EXCEPTION:
         raise GROBID_OFFLINE_EXCEPTION("GROBID服务不可用，请修改config中的GROBID_URL，可修改成本地GROBID服务。")
     except:
         raise RuntimeError("解析PDF失败，请检查PDF是否损坏。")
     return article_dict
 
+
+def produce_report_markdown(gpt_response_collection, meta, paper_meta_info, chatbot, fp, generated_conclusion_files):
+    # -=-=-=-=-=-=-=-= 写出第1个文件：翻译前后混合 -=-=-=-=-=-=-=-=
+    res_path = write_history_to_file(meta +  ["# Meta Translation" , paper_meta_info] + gpt_response_collection, file_basename=f"{gen_time_str()}translated_and_original.md", file_fullname=None)
+    promote_file_to_downloadzone(res_path, rename_file=os.path.basename(res_path)+'.md', chatbot=chatbot)
+    generated_conclusion_files.append(res_path)
+
+    # -=-=-=-=-=-=-=-= 写出第2个文件：仅翻译后的文本 -=-=-=-=-=-=-=-=
+    translated_res_array = []
+    # 记录当前的大章节标题：
+    last_section_name = ""
+    for index, value in enumerate(gpt_response_collection):
+        # 先挑选偶数序列号：
+        if index % 2 != 0:
+            # 先提取当前英文标题：
+            cur_section_name = gpt_response_collection[index-1].split('\n')[0].split(" Part")[0]
+            # 如果index是1的话，则直接使用first section name：
+            if cur_section_name != last_section_name:
+                cur_value = cur_section_name + '\n'
+                last_section_name = copy.deepcopy(cur_section_name)
+            else:
+                cur_value = ""
+            # 再做一个小修改：重新修改当前part的标题，默认用英文的
+            cur_value += value
+            translated_res_array.append(cur_value)
+    res_path = write_history_to_file(meta +  ["# Meta Translation" , paper_meta_info] + translated_res_array, 
+                                     file_basename = f"{gen_time_str()}-translated_only.md", 
+                                     file_fullname = None,
+                                     auto_caption = False)
+    promote_file_to_downloadzone(res_path, rename_file=os.path.basename(res_path)+'.md', chatbot=chatbot)
+    generated_conclusion_files.append(res_path)
+    return res_path
+
+def translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_files, TOKEN_LIMIT_PER_FRAGMENT, DST_LANG):
+    from crazy_functions.crazy_utils import construct_html
+    from crazy_functions.crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
+    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
+
+    prompt = "以下是一篇学术论文的基本信息:\n"
+    # title
+    title = article_dict.get('title', '无法获取 title'); prompt += f'title:{title}\n\n'
+    # authors
+    authors = article_dict.get('authors', '无法获取 authors'); prompt += f'authors:{authors}\n\n'
+    # abstract
+    abstract = article_dict.get('abstract', '无法获取 abstract'); prompt += f'abstract:{abstract}\n\n'
+    # command
+    prompt += f"请将题目和摘要翻译为{DST_LANG}。"
+    meta = [f'# Title:\n\n', title, f'# Abstract:\n\n', abstract ]
+
+    # 单线，获取文章meta信息
+    paper_meta_info = yield from request_gpt_model_in_new_thread_with_ui_alive(
+        inputs=prompt,
+        inputs_show_user=prompt,
+        llm_kwargs=llm_kwargs,
+        chatbot=chatbot, history=[],
+        sys_prompt="You are an academic paper reader。",
+    )
+
+    # 多线，翻译
+    inputs_array = []
+    inputs_show_user_array = []
+
+    # get_token_num
+    from request_llm.bridge_all import model_info
+    enc = model_info[llm_kwargs['llm_model']]['tokenizer']
+    def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
+
+    def break_down(txt):
+        raw_token_num = get_token_num(txt)
+        if raw_token_num <= TOKEN_LIMIT_PER_FRAGMENT:
+            return [txt]
+        else:
+            # raw_token_num > TOKEN_LIMIT_PER_FRAGMENT
+            # 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)
+
+    for section in article_dict.get('sections'):
+        if len(section['text']) == 0: continue
+        section_frags = break_down(section['text'])
+        for i, fragment in enumerate(section_frags):
+            heading = section['heading']
+            if len(section_frags) > 1: heading += f' Part-{i+1}'
+            inputs_array.append(
+                f"你需要翻译{heading}章节，内容如下: \n\n{fragment}"
+            )
+            inputs_show_user_array.append(
+                f"# {heading}\n\n{fragment}"
+            )
+
+    gpt_response_collection = yield from request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
+        inputs_array=inputs_array,
+        inputs_show_user_array=inputs_show_user_array,
+        llm_kwargs=llm_kwargs,
+        chatbot=chatbot,
+        history_array=[meta for _ in inputs_array],
+        sys_prompt_array=[
+            "请你作为一个学术翻译，负责把学术论文准确翻译成中文。注意文章中的每一句话都要翻译。" for _ in inputs_array],
+    )
+    # -=-=-=-=-=-=-=-= 写出Markdown文件 -=-=-=-=-=-=-=-=
+    produce_report_markdown(gpt_response_collection, meta, paper_meta_info, chatbot, fp, generated_conclusion_files)
+
+    # -=-=-=-=-=-=-=-= 写出HTML文件 -=-=-=-=-=-=-=-=
+    ch = construct_html() 
+    orig = ""
+    trans = ""
+    gpt_response_collection_html = copy.deepcopy(gpt_response_collection)
+    for i,k in enumerate(gpt_response_collection_html): 
+        if i%2==0:
+            gpt_response_collection_html[i] = inputs_show_user_array[i//2]
+        else:
+            # 先提取当前英文标题：
+            cur_section_name = gpt_response_collection[i-1].split('\n')[0].split(" Part")[0]
+            cur_value = cur_section_name + "\n" + gpt_response_collection_html[i]
+            gpt_response_collection_html[i] = cur_value
+
+    final = ["", "", "一、论文概况",  "", "Abstract", paper_meta_info,  "二、论文翻译",  ""]
+    final.extend(gpt_response_collection_html)
+    for i, k in enumerate(final): 
+        if i%2==0:
+            orig = k
+        if i%2==1:
+            trans = k
+            ch.add_row(a=orig, b=trans)
+    create_report_file_name = f"{os.path.basename(fp)}.trans.html"
+    html_file = ch.save_file(create_report_file_name)
+    generated_conclusion_files.append(html_file)
+    promote_file_to_downloadzone(html_file, rename_file=os.path.basename(html_file), chatbot=chatbot)

crazy_functions/函数动态生成.py

@@ -0,0 +1,252 @@
+# 本源代码中, ⭐ = 关键步骤
+"""
+测试：
+    - 裁剪图像，保留下半部分
+    - 交换图像的蓝色通道和红色通道
+    - 将图像转为灰度图像
+    - 将csv文件转excel表格
+
+Testing: 
+    - Crop the image, keeping the bottom half. 
+    - Swap the blue channel and red channel of the image. 
+    - Convert the image to grayscale. 
+    - Convert the CSV file to an Excel spreadsheet.
+"""
+
+
+from toolbox import CatchException, update_ui, gen_time_str, trimmed_format_exc, is_the_upload_folder
+from toolbox import promote_file_to_downloadzone, get_log_folder, update_ui_lastest_msg
+from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, get_plugin_arg
+from .crazy_utils import input_clipping, try_install_deps
+from crazy_functions.gen_fns.gen_fns_shared import is_function_successfully_generated
+from crazy_functions.gen_fns.gen_fns_shared import get_class_name
+from crazy_functions.gen_fns.gen_fns_shared import subprocess_worker
+from crazy_functions.gen_fns.gen_fns_shared import try_make_module
+import os
+import time
+import glob
+import multiprocessing
+
+templete = """
+```python
+import ...  # Put dependencies here, e.g. import numpy as np. 
+
+class TerminalFunction(object): # Do not change the name of the class, The name of the class must be `TerminalFunction`
+
+    def run(self, path):    # The name of the function must be `run`, it takes only a positional argument.
+        # rewrite the function you have just written here 
+        ...
+        return generated_file_path
+```
+"""
+
+def inspect_dependency(chatbot, history):
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+    return True
+
+def get_code_block(reply):
+    import re
+    pattern = r"```([\s\S]*?)```" # regex pattern to match code blocks
+    matches = re.findall(pattern, reply) # find all code blocks in text
+    if len(matches) == 1: 
+        return matches[0].strip('python') #  code block
+    for match in matches:
+        if 'class TerminalFunction' in match:
+            return match.strip('python') #  code block
+    raise RuntimeError("GPT is not generating proper code.")
+
+def gpt_interact_multi_step(txt, file_type, llm_kwargs, chatbot, history):
+    # 输入
+    prompt_compose = [
+        f'Your job:\n'
+        f'1. write a single Python function, which takes a path of a `{file_type}` file as the only argument and returns a `string` containing the result of analysis or the path of generated files. \n',
+        f"2. You should write this function to perform following task: " + txt + "\n",
+        f"3. Wrap the output python function with markdown codeblock."
+    ]
+    i_say = "".join(prompt_compose)
+    demo = []
+
+    # 第一步
+    gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
+        inputs=i_say, inputs_show_user=i_say, 
+        llm_kwargs=llm_kwargs, chatbot=chatbot, history=demo, 
+        sys_prompt= r"You are a world-class programmer."
+    )
+    history.extend([i_say, gpt_say])
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
+
+    # 第二步
+    prompt_compose = [
+        "If previous stage is successful, rewrite the function you have just written to satisfy following templete: \n",
+        templete
+    ]
+    i_say = "".join(prompt_compose); inputs_show_user = "If previous stage is successful, rewrite the function you have just written to satisfy executable templete. "
+    gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
+        inputs=i_say, inputs_show_user=inputs_show_user, 
+        llm_kwargs=llm_kwargs, chatbot=chatbot, history=history, 
+        sys_prompt= r"You are a programmer. You need to replace `...` with valid packages, do not give `...` in your answer!"
+    )
+    code_to_return = gpt_say
+    history.extend([i_say, gpt_say])
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
+    
+    # # 第三步
+    # i_say = "Please list to packages to install to run the code above. Then show me how to use `try_install_deps` function to install them."
+    # i_say += 'For instance. `try_install_deps(["opencv-python", "scipy", "numpy"])`'
+    # installation_advance = yield from request_gpt_model_in_new_thread_with_ui_alive(
+    #     inputs=i_say, inputs_show_user=inputs_show_user, 
+    #     llm_kwargs=llm_kwargs, chatbot=chatbot, history=history, 
+    #     sys_prompt= r"You are a programmer."
+    # )
+
+    # # # 第三步  
+    # i_say = "Show me how to use `pip` to install packages to run the code above. "
+    # i_say += 'For instance. `pip install -r opencv-python scipy numpy`'
+    # installation_advance = yield from request_gpt_model_in_new_thread_with_ui_alive(
+    #     inputs=i_say, inputs_show_user=i_say, 
+    #     llm_kwargs=llm_kwargs, chatbot=chatbot, history=history, 
+    #     sys_prompt= r"You are a programmer."
+    # )
+    installation_advance = ""
+    
+    return code_to_return, installation_advance, txt, file_type, llm_kwargs, chatbot, history
+
+
+
+
+def for_immediate_show_off_when_possible(file_type, fp, chatbot):
+    if file_type in ['png', 'jpg']:
+        image_path = os.path.abspath(fp)
+        chatbot.append(['这是一张图片, 展示如下:',  
+            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>'
+        ])
+    return chatbot
+
+
+
+def have_any_recent_upload_files(chatbot):
+    _5min = 5 * 60
+    if not chatbot: return False    # chatbot is None
+    most_recent_uploaded = chatbot._cookies.get("most_recent_uploaded", None)
+    if not most_recent_uploaded: return False   # most_recent_uploaded is None
+    if time.time() - most_recent_uploaded["time"] < _5min: return True # most_recent_uploaded is new
+    else: return False  # most_recent_uploaded is too old
+
+def get_recent_file_prompt_support(chatbot):
+    most_recent_uploaded = chatbot._cookies.get("most_recent_uploaded", None)
+    path = most_recent_uploaded['path']
+    return path
+
+@CatchException
+def 函数动态生成(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，暂时没有用武之地
+    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
+    """
+
+    # 清空历史
+    history = []
+
+    # 基本信息：功能、贡献者
+    chatbot.append(["正在启动: 插件动态生成插件", "插件动态生成, 执行开始, 作者Binary-Husky."])
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+    # ⭐ 文件上传区是否有东西
+    # 1. 如果有文件: 作为函数参数
+    # 2. 如果没有文件：需要用GPT提取参数 （太懒了，以后再写，虚空终端已经实现了类似的代码）
+    file_list = []
+    if get_plugin_arg(plugin_kwargs, key="file_path_arg", default=False):
+        file_path = get_plugin_arg(plugin_kwargs, key="file_path_arg", default=None)
+        file_list.append(file_path)
+        yield from update_ui_lastest_msg(f"当前文件: {file_path}", chatbot, history, 1)
+    elif have_any_recent_upload_files(chatbot):
+        file_dir = get_recent_file_prompt_support(chatbot)
+        file_list = glob.glob(os.path.join(file_dir, '**/*'), recursive=True)
+        yield from update_ui_lastest_msg(f"当前文件处理列表: {file_list}", chatbot, history, 1)
+    else:
+        chatbot.append(["文件检索", "没有发现任何近期上传的文件。"])
+        yield from update_ui_lastest_msg("没有发现任何近期上传的文件。", chatbot, history, 1)
+        return  # 2. 如果没有文件
+    if len(file_list) == 0:
+        chatbot.append(["文件检索", "没有发现任何近期上传的文件。"])
+        yield from update_ui_lastest_msg("没有发现任何近期上传的文件。", chatbot, history, 1)
+        return  # 2. 如果没有文件
+    
+    # 读取文件
+    file_type = file_list[0].split('.')[-1]
+
+    # 粗心检查
+    if is_the_upload_folder(txt):
+        yield from update_ui_lastest_msg(f"请在输入框内填写需求, 然后再次点击该插件! 至于您的文件，不用担心, 文件路径 {txt} 已经被记忆. ", chatbot, history, 1)
+        return
+    
+    # 开始干正事
+    MAX_TRY = 3
+    for j in range(MAX_TRY):  # 最多重试5次
+        traceback = ""
+        try:
+            # ⭐ 开始啦 ！
+            code, installation_advance, txt, file_type, llm_kwargs, chatbot, history = \
+                yield from gpt_interact_multi_step(txt, file_type, llm_kwargs, chatbot, history)
+            chatbot.append(["代码生成阶段结束", ""])
+            yield from update_ui_lastest_msg(f"正在验证上述代码的有效性 ...", chatbot, history, 1)
+            # ⭐ 分离代码块
+            code = get_code_block(code)
+            # ⭐ 检查模块
+            ok, traceback = try_make_module(code, chatbot)
+            # 搞定代码生成
+            if ok: break
+        except Exception as e:
+            if not traceback: traceback = trimmed_format_exc()
+        # 处理异常
+        if not traceback: traceback = trimmed_format_exc()
+        yield from update_ui_lastest_msg(f"第 {j+1}/{MAX_TRY} 次代码生成尝试, 失败了~ 别担心, 我们5秒后再试一次... \n\n此次我们的错误追踪是\n```\n{traceback}\n```\n", chatbot, history, 5)
+
+    # 代码生成结束, 开始执行
+    TIME_LIMIT = 15
+    yield from update_ui_lastest_msg(f"开始创建新进程并执行代码! 时间限制 {TIME_LIMIT} 秒. 请等待任务完成... ", chatbot, history, 1)
+    manager = multiprocessing.Manager()
+    return_dict = manager.dict()
+
+    # ⭐ 到最后一步了，开始逐个文件进行处理
+    for file_path in file_list:
+        if os.path.exists(file_path):
+            chatbot.append([f"正在处理文件: {file_path}", f"请稍等..."])
+            chatbot = for_immediate_show_off_when_possible(file_type, file_path, chatbot)
+            yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
+        else:
+            continue
+
+        # ⭐⭐⭐ subprocess_worker ⭐⭐⭐
+        p = multiprocessing.Process(target=subprocess_worker, args=(code, file_path, return_dict))
+        # ⭐ 开始执行，时间限制TIME_LIMIT
+        p.start(); p.join(timeout=TIME_LIMIT)
+        if p.is_alive(): p.terminate(); p.join()
+        p.close()
+        res = return_dict['result']
+        success = return_dict['success']
+        traceback = return_dict['traceback']
+        if not success:
+            if not traceback: traceback = trimmed_format_exc()
+            chatbot.append(["执行失败了", f"错误追踪\n```\n{trimmed_format_exc()}\n```\n"])
+            # chatbot.append(["如果是缺乏依赖，请参考以下建议", installation_advance])
+            yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+            return
+        
+        # 顺利完成，收尾
+        res = str(res)
+        if os.path.exists(res):
+            chatbot.append(["执行成功了，结果是一个有效文件", "结果：" + res])
+            new_file_path = promote_file_to_downloadzone(res, chatbot=chatbot)
+            chatbot = for_immediate_show_off_when_possible(file_type, new_file_path, chatbot)
+            yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
+        else:
+            chatbot.append(["执行成功了，结果是一个字符串", "结果：" + res])
+            yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新   
+

crazy_functions/批量翻译PDF文档_NOUGAT.py

@@ -1,11 +1,12 @@
-from toolbox import CatchException, report_execption, gen_time_str
+from toolbox import CatchException, report_execption, get_log_folder, gen_time_str
 from toolbox import update_ui, promote_file_to_downloadzone, update_ui_lastest_msg, disable_auto_promotion
-from toolbox import write_history_to_file, get_log_folder
+from toolbox import write_history_to_file, promote_file_to_downloadzone
 from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
 from .crazy_utils import read_and_clean_pdf_text
-from .pdf_fns.parse_pdf import parse_pdf, get_avail_grobid_url
+from .pdf_fns.parse_pdf import parse_pdf, get_avail_grobid_url, translate_pdf
 from colorful import *
+import copy
 import os
 import math
 import logging
@@ -92,7 +93,7 @@ def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
 def 解析PDF_基于NOUGAT(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
     import copy
     import tiktoken
-    TOKEN_LIMIT_PER_FRAGMENT = 1280
+    TOKEN_LIMIT_PER_FRAGMENT = 1024
     generated_conclusion_files = []
     generated_html_files = []
     DST_LANG = "中文"
@@ -101,101 +102,12 @@ def 解析PDF_基于NOUGAT(file_manifest, project_folder, llm_kwargs, plugin_kwa
     for index, fp in enumerate(file_manifest):
         chatbot.append(["当前进度：", f"正在解析论文，请稍候。（第一次运行时，需要花费较长时间下载NOUGAT参数）"]); yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         fpp = yield from nougat_handle.NOUGAT_parse_pdf(fp, chatbot, history)
-
+        promote_file_to_downloadzone(fpp, rename_file=os.path.basename(fpp)+'.nougat.mmd', chatbot=chatbot)
         with open(fpp, 'r', encoding='utf8') as f:
             article_content = f.readlines()
         article_dict = markdown_to_dict(article_content)
         logging.info(article_dict)
-
-        prompt = "以下是一篇学术论文的基本信息:\n"
-        # title
-        title = article_dict.get('title', '无法获取 title'); prompt += f'title:{title}\n\n'
-        # authors
-        authors = article_dict.get('authors', '无法获取 authors'); prompt += f'authors:{authors}\n\n'
-        # abstract
-        abstract = article_dict.get('abstract', '无法获取 abstract'); prompt += f'abstract:{abstract}\n\n'
-        # command
-        prompt += f"请将题目和摘要翻译为{DST_LANG}。"
-        meta = [f'# Title:\n\n', title, f'# Abstract:\n\n', abstract ]
-
-        # 单线，获取文章meta信息
-        paper_meta_info = yield from request_gpt_model_in_new_thread_with_ui_alive(
-            inputs=prompt,
-            inputs_show_user=prompt,
-            llm_kwargs=llm_kwargs,
-            chatbot=chatbot, history=[],
-            sys_prompt="You are an academic paper reader。",
-        )
-
-        # 多线，翻译
-        inputs_array = []
-        inputs_show_user_array = []
-
-        # get_token_num
-        from request_llm.bridge_all import model_info
-        enc = model_info[llm_kwargs['llm_model']]['tokenizer']
-        def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
-        from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
-
-        def break_down(txt):
-            raw_token_num = get_token_num(txt)
-            if raw_token_num <= TOKEN_LIMIT_PER_FRAGMENT:
-                return [txt]
-            else:
-                # raw_token_num > TOKEN_LIMIT_PER_FRAGMENT
-                # 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)
-
-        for section in article_dict.get('sections'):
-            if len(section['text']) == 0: continue
-            section_frags = break_down(section['text'])
-            for i, fragment in enumerate(section_frags):
-                heading = section['heading']
-                if len(section_frags) > 1: heading += f' Part-{i+1}'
-                inputs_array.append(
-                    f"你需要翻译{heading}章节，内容如下: \n\n{fragment}"
-                )
-                inputs_show_user_array.append(
-                    f"# {heading}\n\n{fragment}"
-                )
-
-        gpt_response_collection = yield from request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
-            inputs_array=inputs_array,
-            inputs_show_user_array=inputs_show_user_array,
-            llm_kwargs=llm_kwargs,
-            chatbot=chatbot,
-            history_array=[meta for _ in inputs_array],
-            sys_prompt_array=[
-                "请你作为一个学术翻译，负责把学术论文准确翻译成中文。注意文章中的每一句话都要翻译。" for _ in inputs_array],
-        )
-        res_path = write_history_to_file(meta +  ["# Meta Translation" , paper_meta_info] + gpt_response_collection, file_basename=None, file_fullname=None)
-        promote_file_to_downloadzone(res_path, rename_file=os.path.basename(fp)+'.md', chatbot=chatbot)
-        generated_conclusion_files.append(res_path)
-
-        ch = construct_html() 
-        orig = ""
-        trans = ""
-        gpt_response_collection_html = copy.deepcopy(gpt_response_collection)
-        for i,k in enumerate(gpt_response_collection_html): 
-            if i%2==0:
-                gpt_response_collection_html[i] = inputs_show_user_array[i//2]
-            else:
-                gpt_response_collection_html[i] = gpt_response_collection_html[i]
-
-        final = ["", "", "一、论文概况",  "", "Abstract", paper_meta_info,  "二、论文翻译",  ""]
-        final.extend(gpt_response_collection_html)
-        for i, k in enumerate(final): 
-            if i%2==0:
-                orig = k
-            if i%2==1:
-                trans = k
-                ch.add_row(a=orig, b=trans)
-        create_report_file_name = f"{os.path.basename(fp)}.trans.html"
-        html_file = ch.save_file(create_report_file_name)
-        generated_html_files.append(html_file)
-        promote_file_to_downloadzone(html_file, rename_file=os.path.basename(html_file), chatbot=chatbot)
+        yield from translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_files, TOKEN_LIMIT_PER_FRAGMENT, DST_LANG)
 
     chatbot.append(("给出输出文件清单", str(generated_conclusion_files + generated_html_files)))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面

crazy_functions/批量翻译PDF文档_多线程.py

@@ -1,12 +1,12 @@
-from toolbox import CatchException, report_execption, get_log_folder
+from toolbox import CatchException, report_execption, get_log_folder, gen_time_str
 from toolbox import update_ui, promote_file_to_downloadzone, update_ui_lastest_msg, disable_auto_promotion
 from toolbox import write_history_to_file, promote_file_to_downloadzone
 from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
 from .crazy_utils import read_and_clean_pdf_text
-from .pdf_fns.parse_pdf import parse_pdf, get_avail_grobid_url
+from .pdf_fns.parse_pdf import parse_pdf, get_avail_grobid_url, translate_pdf
 from colorful import *
-import glob
+import copy
 import os
 import math
 
@@ -58,8 +58,8 @@ def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
 
 
 def 解析PDF_基于GROBID(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, grobid_url):
-    import copy
-    TOKEN_LIMIT_PER_FRAGMENT = 1280
+    import copy, json
+    TOKEN_LIMIT_PER_FRAGMENT = 1024
     generated_conclusion_files = []
     generated_html_files = []
     DST_LANG = "中文"
@@ -67,104 +67,23 @@ def 解析PDF_基于GROBID(file_manifest, project_folder, llm_kwargs, plugin_kwa
     for index, fp in enumerate(file_manifest):
         chatbot.append(["当前进度：", f"正在连接GROBID服务，请稍候: {grobid_url}\n如果等待时间过长，请修改config中的GROBID_URL，可修改成本地GROBID服务。"]); yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         article_dict = parse_pdf(fp, grobid_url)
+        grobid_json_res = os.path.join(get_log_folder(), gen_time_str() + "grobid.json")
+        with open(grobid_json_res, 'w+', encoding='utf8') as f:
+            f.write(json.dumps(article_dict, indent=4, ensure_ascii=False))
+        promote_file_to_downloadzone(grobid_json_res, chatbot=chatbot)
+        
         if article_dict is None: raise RuntimeError("解析PDF失败，请检查PDF是否损坏。")
-        prompt = "以下是一篇学术论文的基本信息:\n"
-        # title
-        title = article_dict.get('title', '无法获取 title'); prompt += f'title:{title}\n\n'
-        # authors
-        authors = article_dict.get('authors', '无法获取 authors'); prompt += f'authors:{authors}\n\n'
-        # abstract
-        abstract = article_dict.get('abstract', '无法获取 abstract'); prompt += f'abstract:{abstract}\n\n'
-        # command
-        prompt += f"请将题目和摘要翻译为{DST_LANG}。"
-        meta = [f'# Title:\n\n', title, f'# Abstract:\n\n', abstract ]
-
-        # 单线，获取文章meta信息
-        paper_meta_info = yield from request_gpt_model_in_new_thread_with_ui_alive(
-            inputs=prompt,
-            inputs_show_user=prompt,
-            llm_kwargs=llm_kwargs,
-            chatbot=chatbot, history=[],
-            sys_prompt="You are an academic paper reader。",
-        )
-
-        # 多线，翻译
-        inputs_array = []
-        inputs_show_user_array = []
-
-        # get_token_num
-        from request_llm.bridge_all import model_info
-        enc = model_info[llm_kwargs['llm_model']]['tokenizer']
-        def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
-        from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
-
-        def break_down(txt):
-            raw_token_num = get_token_num(txt)
-            if raw_token_num <= TOKEN_LIMIT_PER_FRAGMENT:
-                return [txt]
-            else:
-                # raw_token_num > TOKEN_LIMIT_PER_FRAGMENT
-                # 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)
-
-        for section in article_dict.get('sections'):
-            if len(section['text']) == 0: continue
-            section_frags = break_down(section['text'])
-            for i, fragment in enumerate(section_frags):
-                heading = section['heading']
-                if len(section_frags) > 1: heading += f' Part-{i+1}'
-                inputs_array.append(
-                    f"你需要翻译{heading}章节，内容如下: \n\n{fragment}"
-                )
-                inputs_show_user_array.append(
-                    f"# {heading}\n\n{fragment}"
-                )
-
-        gpt_response_collection = yield from request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
-            inputs_array=inputs_array,
-            inputs_show_user_array=inputs_show_user_array,
-            llm_kwargs=llm_kwargs,
-            chatbot=chatbot,
-            history_array=[meta for _ in inputs_array],
-            sys_prompt_array=[
-                "请你作为一个学术翻译，负责把学术论文准确翻译成中文。注意文章中的每一句话都要翻译。" for _ in inputs_array],
-        )
-        res_path = write_history_to_file(meta +  ["# Meta Translation" , paper_meta_info] + gpt_response_collection, file_basename=None, file_fullname=None)
-        promote_file_to_downloadzone(res_path, rename_file=os.path.basename(fp)+'.md', chatbot=chatbot)
-        generated_conclusion_files.append(res_path)
-
-        ch = construct_html() 
-        orig = ""
-        trans = ""
-        gpt_response_collection_html = copy.deepcopy(gpt_response_collection)
-        for i,k in enumerate(gpt_response_collection_html): 
-            if i%2==0:
-                gpt_response_collection_html[i] = inputs_show_user_array[i//2]
-            else:
-                gpt_response_collection_html[i] = gpt_response_collection_html[i]
-
-        final = ["", "", "一、论文概况",  "", "Abstract", paper_meta_info,  "二、论文翻译",  ""]
-        final.extend(gpt_response_collection_html)
-        for i, k in enumerate(final): 
-            if i%2==0:
-                orig = k
-            if i%2==1:
-                trans = k
-                ch.add_row(a=orig, b=trans)
-        create_report_file_name = f"{os.path.basename(fp)}.trans.html"
-        html_file = ch.save_file(create_report_file_name)
-        generated_html_files.append(html_file)
-        promote_file_to_downloadzone(html_file, rename_file=os.path.basename(html_file), chatbot=chatbot)
-
+        yield from translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_files, TOKEN_LIMIT_PER_FRAGMENT, DST_LANG)
     chatbot.append(("给出输出文件清单", str(generated_conclusion_files + generated_html_files)))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
 
 
 def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
+    """
+    此函数已经弃用
+    """
     import copy
-    TOKEN_LIMIT_PER_FRAGMENT = 1280
+    TOKEN_LIMIT_PER_FRAGMENT = 1024
     generated_conclusion_files = []
     generated_html_files = []
     from crazy_functions.crazy_utils import construct_html

crazy_functions/解析项目源代码.py

@@ -136,6 +136,23 @@ def 解析一个Python项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
         return
     yield from 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
 
+@CatchException
+def 解析一个Matlab项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+    history = []    # 清空历史，以免输入溢出
+    import glob, os
+    if os.path.exists(txt):
+        project_folder = txt
+    else:
+        if txt == "": txt = '空空如也的输入栏'
+        report_execption(chatbot, history, a = f"解析Matlab项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return
+    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.m', recursive=True)]
+    if len(file_manifest) == 0:
+        report_execption(chatbot, history, a = f"解析Matlab项目: {txt}", b = f"找不到任何`.m`源文件: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return
+    yield from 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
 
 @CatchException
 def 解析一个C项目的头文件(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):