Upload 3 files

app.py

@@ -0,0 +1,136 @@
+import numpy as np
+import os
+import re
+import datetime
+import time
+import openai, tenacity
+import argparse
+import configparser
+import json
+import tiktoken
+from get_paper_from_pdf import Paper
+import gradio
+
+# 定义Response类
+class Response:
+    # 初始化方法，设置属性
+    def __init__(self, api, comment, language):
+        self.api = api
+        self.comment = comment
+        self.language = language     
+        self.max_token_num = 4096
+        self.encoding = tiktoken.get_encoding("gpt2")
+    
+    
+    @tenacity.retry(wait=tenacity.wait_exponential(multiplier=1, min=4, max=10),
+                    stop=tenacity.stop_after_attempt(5),
+                    reraise=True)
+    def chat_response(self, text):
+        openai.api_key = self.chat_api_list[self.cur_api]
+        self.cur_api += 1
+        self.cur_api = 0 if self.cur_api >= len(self.chat_api_list)-1 else self.cur_api
+        response_prompt_token = 1000        
+        text_token = len(self.encoding.encode(self.comment))
+        input_text_index = int(len(text)*(self.max_token_num-response_prompt_token)/text_token)
+        input_text = "This is the review comments:" + text[:input_text_index]
+        messages=[
+                {"role": "system", "content": """You are the author, you submitted a paper, and the reviewers gave the review comments. 
+                Please reply with what we have done, not what we will do.
+                You need to extract questions from the review comments one by one, and then respond point-to-point to the reviewers’ concerns. 
+                Please answer in {}. Follow the format of the output later: 
+                - Response to reviewers
+                #1 reviewer
+                Concern #1: xxxx
+                Author response: xxxxx
+                Concern #2: xxxx
+                Author response: xxxxx
+                ...
+                #2 reviewer
+                Concern #1: xxxx
+                Author response: xxxxx
+                Concern #2: xxxx
+                Author response: xxxxx
+                ...
+                #3 reviewer
+                Concern #1: xxxx
+                Author response: xxxxx
+                Concern #2: xxxx
+                Author response: xxxxx
+                ...
+                
+                """.format(self.language)
+ 
+                },
+                {"role": "user", "content": input_text},
+            ]
+                
+        response = openai.ChatCompletion.create(
+            model="gpt-3.5-turbo",
+            messages=messages,
+        )
+        result = ''
+        for choice in response.choices:
+            result += choice.message.content
+        print("********"*10)
+        print(result)
+        print("********"*10)
+        print("prompt_token_used:", response.usage.prompt_tokens)
+        print("completion_token_used:", response.usage.completion_tokens)
+        print("total_token_used:", response.usage.total_tokens)
+        print("response_time:", response.response_ms/1000.0, 's')                    
+        return result, response.usage.total_tokens
+                        
+                           
+
+def main(api, comment, language):  
+    start_time = time.time()
+    if not api or not comment:
+        return "请输入API-key以及审稿意见！"
+    else:
+        Response1 = Response(api, comment, language)
+        # 开始判断是路径还是文件：   
+        response, total_token_used = Response1.chat_response()
+    time_used = time.time() - start_time
+    output2 ="使用token数："+ str(total_token_used)+"\n花费时间："+ str(round(time_used, 2)) +"秒"
+    return response, output2
+        
+
+########################################################################################################    
+# 标题
+title = "🤖ChatResponse🤖"
+# 描述
+
+description = '''<div align='left'>
+<img align='right' src='http://i.imgtg.com/2023/03/22/94PLN.png' width="250">
+
+<strong>ChatResponse是一款根据审稿人的评论自动生成作者回复的AI助手。用途如下：</strong>其用途为：
+
+⭐️根据输入的审稿意见，ChatResponse会自动提取其中各个审稿人的问题和担忧，并生成点对点的回复。
+
+如果觉得很卡，可以点击右上角的Duplicate this Space，把ChatResponse复制到你自己的Space中！
+
+本项目的[Github](https://github.com/nishiwen1214/ChatResponse)，欢迎Star和Fork，也欢迎大佬赞助让本项目快速成长！💗（[获取Api Key](https://chatgpt.cn.obiscr.com/blog/posts/2023/How-to-get-api-key/)）
+</div>
+'''
+
+# 创建Gradio界面
+inp = [gradio.inputs.Textbox(label="请输入你的API-key(sk开头的字符串)",
+                          default="",
+                          type='password'),
+    gradio.inputs.Textbox(lines=5,
+        label="请输入要回复的审稿意见",
+        default=""
+    ),
+    gradio.inputs.Radio(choices=["English", "Chinese"],
+                        default="English",
+                        label="选择输��语言"),
+]
+
+chat_Response_gui = gradio.Interface(fn=main,
+                                 inputs=inp,
+                                 outputs = [gradio.Textbox(lines=20, label="回复结果"), gradio.Textbox(lines=2, label="资源统计")],
+                                 title=title,
+                                 description=description)
+
+# Start server
+chat_Response_gui .launch(quiet=True, show_api=False)

get_paper_from_pdf.py

@@ -0,0 +1,193 @@
+import fitz, io, os
+from PIL import Image
+from collections import Counter
+import json
+import re
+
+class Paper:
+    def __init__(self, path, title='', url='', abs='', authors=[]):
+        # 初始化函数，根据pdf路径初始化Paper对象                
+        self.url = url  # 文章链接
+        self.path = path  # pdf路径
+        self.section_names = []  # 段落标题
+        self.section_texts = {}  # 段落内容
+        self.abs = abs
+        self.title_page = 0
+        if title == '':
+            self.pdf = fitz.open(self.path)  # pdf文档
+            self.title = self.get_title()
+            self.parse_pdf()
+        else:
+            self.title = title
+        self.authors = authors
+        self.roman_num = ["I", "II", 'III', "IV", "V", "VI", "VII", "VIII", "IIX", "IX", "X"]
+        self.digit_num = [str(d + 1) for d in range(10)]
+        self.first_image = ''
+
+    def parse_pdf(self):
+        self.pdf = fitz.open(self.path)  # pdf文档
+        self.text_list = [page.get_text() for page in self.pdf]
+        self.all_text = ' '.join(self.text_list)
+        self.extract_section_infomation()
+        self.section_texts.update({"title": self.title})
+        self.pdf.close()
+
+    # 定义一个函数，根据字体的大小，识别每个章节名称，并返回一个列表
+    def get_chapter_names(self, ):
+        # # 打开一个pdf文件
+        doc = fitz.open(self.path)  # pdf文档
+        text_list = [page.get_text() for page in doc]
+        all_text = ''
+        for text in text_list:
+            all_text += text
+        # # 创建一个空列表，用于存储章节名称
+        chapter_names = []
+        for line in all_text.split('\n'):
+            line_list = line.split(' ')
+            if '.' in line:
+                point_split_list = line.split('.')
+                space_split_list = line.split(' ')
+                if 1 < len(space_split_list) < 5:
+                    if 1 < len(point_split_list) < 5 and (
+                            point_split_list[0] in self.roman_num or point_split_list[0] in self.digit_num):
+                        # print("line:", line)
+                        chapter_names.append(line)
+
+        return chapter_names
+
+    def get_title(self):
+        doc = self.pdf  # 打开pdf文件
+        max_font_size = 0  # 初始化最大字体大小为0
+        max_string = ""  # 初始化最大字体大小对应的字符串为空
+        max_font_sizes = [0]
+        for page_index, page in enumerate(doc):  # 遍历每一页
+            text = page.get_text("dict")  # 获取页面上的文本信息
+            blocks = text["blocks"]  # 获取文本块列表
+            for block in blocks:  # 遍历每个文本块
+                if block["type"] == 0 and len(block['lines']):  # 如果是文字类型
+                    if len(block["lines"][0]["spans"]):
+                        font_size = block["lines"][0]["spans"][0]["size"]  # 获取第一行第一段文字的字体大小
+                        max_font_sizes.append(font_size)
+                        if font_size > max_font_size:  # 如果字体大小大于当前最大值
+                            max_font_size = font_size  # 更新最大值
+                            max_string = block["lines"][0]["spans"][0]["text"]  # 更新最大值对应的字符串
+        max_font_sizes.sort()
+        # print("max_font_sizes", max_font_sizes[-10:])
+        cur_title = ''
+        for page_index, page in enumerate(doc):  # 遍历每一页
+            text = page.get_text("dict")  # 获取页面上的文本信息
+            blocks = text["blocks"]  # 获取文本块列表
+            for block in blocks:  # 遍历每个文本块
+                if block["type"] == 0 and len(block['lines']):  # 如果是文字类型
+                    if len(block["lines"][0]["spans"]):
+                        cur_string = block["lines"][0]["spans"][0]["text"]  # 更新最大值对应的字符串
+                        font_flags = block["lines"][0]["spans"][0]["flags"]  # 获取第一行第一段文字的字体特征
+                        font_size = block["lines"][0]["spans"][0]["size"]  # 获取第一行第一段文字的字体大小
+                        # print(font_size)
+                        if abs(font_size - max_font_sizes[-1]) < 0.3 or abs(font_size - max_font_sizes[-2]) < 0.3:
+                            # print("The string is bold.", max_string, "font_size:", font_size, "font_flags:", font_flags)                            
+                            if len(cur_string) > 4 and "arXiv" not in cur_string:
+                                # print("The string is bold.", max_string, "font_size:", font_size, "font_flags:", font_flags) 
+                                if cur_title == '':
+                                    cur_title += cur_string
+                                else:
+                                    cur_title += ' ' + cur_string
+                                self.title_page = page_index
+                                # break
+        title = cur_title.replace('\n', ' ')
+        return title
+
+    def extract_section_infomation(self):
+        doc = fitz.open(self.path)
+
+        # 获取文档中所有字体大小
+        font_sizes = []
+        for page in doc:
+            blocks = page.get_text("dict")["blocks"]
+            for block in blocks:
+                if 'lines' not in block:
+                    continue
+                lines = block["lines"]
+                for line in lines:
+                    for span in line["spans"]:
+                        font_sizes.append(span["size"])
+        most_common_size, _ = Counter(font_sizes).most_common(1)[0]
+
+        # 按照最频繁的字体大小确定标题字体大小的阈值
+        threshold = most_common_size * 1
+
+        section_dict = {}
+        last_heading = None
+        subheadings = []
+        heading_font = -1
+        # 遍历每一页并查找子标题
+        found_abstract = False
+        upper_heading = False
+        font_heading = False
+        for page in doc:
+            blocks = page.get_text("dict")["blocks"]
+            for block in blocks:
+                if not found_abstract:
+                    try:
+                        text = json.dumps(block)
+                    except:
+                        continue
+                    if re.search(r"\bAbstract\b", text, re.IGNORECASE):
+                        found_abstract = True
+                        last_heading = "Abstract"
+                        section_dict["Abstract"] = ""
+                if found_abstract:
+                    if 'lines' not in block:
+                        continue
+                    lines = block["lines"]
+                    for line in lines:
+                        for span in line["spans"]:
+                            # 如果当前文本是子标题
+                            if not font_heading and span["text"].isupper() and sum(1 for c in span["text"] if c.isupper() and ('A' <= c <='Z')) > 4:  # 针对一些标题大小一样,但是全大写的论文
+                                upper_heading = True
+                                heading = span["text"].strip()
+                                if "References" in heading:  # reference 以后的内容不考虑
+                                    self.section_names = subheadings
+                                    self.section_texts = section_dict
+                                    return
+                                subheadings.append(heading)
+                                if last_heading is not None:
+                                    section_dict[last_heading] = section_dict[last_heading].strip()
+                                section_dict[heading] = ""
+                                last_heading = heading
+                            if not upper_heading and span["size"] > threshold and re.match(  # 正常情况下,通过字体大小判断
+                                    r"[A-Z][a-z]+(?:\s[A-Z][a-z]+)*",
+                                    span["text"].strip()):
+                                font_heading = True
+                                if heading_font == -1:
+                                    heading_font = span["size"]
+                                elif heading_font != span["size"]:
+                                    continue
+                                heading = span["text"].strip()
+                                if "References" in heading:  # reference 以后的内容不考虑
+                                    self.section_names = subheadings
+                                    self.section_texts = section_dict
+                                    return
+                                subheadings.append(heading)
+                                if last_heading is not None:
+                                    section_dict[last_heading] = section_dict[last_heading].strip()
+                                section_dict[heading] = ""
+                                last_heading = heading
+                            # 否则将当前文本添加到上一个子标题的文本中
+                            elif last_heading is not None:
+                                section_dict[last_heading] += " " + span["text"].strip()
+        self.section_names = subheadings
+        self.section_texts = section_dict
+
+
+def main():
+    path = r'demo.pdf'
+    paper = Paper(path=path)
+    paper.parse_pdf()
+    # for key, value in paper.section_text_dict.items():
+    # print(key, value)
+    # print("*"*40)
+
+
+if __name__ == '__main__':
+    main()

requirements.txt

@@ -0,0 +1,8 @@
+PyMuPDF==1.21.1
+tiktoken==0.2.0
+tenacity==8.2.2
+pybase64==1.2.3
+Pillow==9.4.0
+openai==0.27.0
+markdown
+gradio==3.20.1