import numpy as np import os import re import jieba from io import BytesIO import datetime import time import openai, tenacity import argparse import configparser import json import tiktoken import PyPDF2 import gradio def contains_chinese(text): for ch in text: if u'\u4e00' <= ch <= u'\u9fff': return True return False def insert_sentence(text, sentence, interval): lines = text.split('\n') new_lines = [] for line in lines: if contains_chinese(line): words = list(jieba.cut(line)) separator = '' else: words = line.split() separator = ' ' new_words = [] count = 0 for word in words: new_words.append(word) count += 1 if count % interval == 0: new_words.append(sentence) new_lines.append(separator.join(new_words)) return '\n'.join(new_lines) # 定义Reviewer类 class Reviewer: # 初始化方法，设置属性 def __init__(self, api, review_format, paper_pdf, language): self.api = api self.review_format = review_format self.language = language self.paper_pdf = paper_pdf self.max_token_num = 4097 self.encoding = tiktoken.get_encoding("gpt2") def review_by_chatgpt(self, paper_list): text = self.extract_chapter(self.paper_pdf) chat_review_text, total_token_used = self.chat_review(text=text) return chat_review_text, total_token_used @tenacity.retry(wait=tenacity.wait_exponential(multiplier=1, min=4, max=10), stop=tenacity.stop_after_attempt(5), reraise=True) def chat_review(self, text): openai.api_key = self.api # 读取api review_prompt_token = 1000 try: text_token = len(self.encoding.encode(text)) except: text_token = 3000 input_text_index = int(len(text)*(self.max_token_num-review_prompt_token)/(text_token+1)) input_text = "This is the paper for your review:" + text[:input_text_index] messages=[ {"role": "system", "content": "You are a professional reviewer. Now I will give you a paper. You need to give a complete review opinion according to the following requirements and format:"+ self.review_format + "Be sure to use {} answers".format(self.language)} , {"role": "user", "content": input_text + " Translate the output into {}.".format(self.language)}, ] try: response = openai.ChatCompletion.create( model="gpt-3.5-turbo", messages=messages, ) result = '' for choice in response.choices: result += choice.message.content result = insert_sentence(result, '**Generated by ChatGPT, no copying allowed!**', 50) result += "\n\n⚠伦理声明/Ethics statement：\n--禁止直接复制生成的评论用于任何论文审稿工作！\n--Direct copying of generated comments for any paper review work is prohibited!" usage = response.usage.total_tokens except Exception as e: # 处理其他的异常 result = "非常抱歉>_<，生了一个错误："+ str(e) usage = 'xxxxx' print("********"*10) print(result) print("********"*10) return result, usage def extract_chapter(self, pdf_path): file_object = BytesIO(pdf_path) pdf_reader = PyPDF2.PdfReader(file_object) # 获取PDF的总页数 num_pages = len(pdf_reader.pages) # 初始化提取状态和提取文本 extraction_started = False extracted_text = "" # 遍历PDF中的每一页 for page_number in range(num_pages): page = pdf_reader.pages[page_number] page_text = page.extract_text() # 开始提取 extraction_started = True page_number_start = page_number # 如果提取已开始，将页面文本添加到提取文本中 if extraction_started: extracted_text += page_text # 停止提取 if page_number_start + 1 < page_number: break return extracted_text def main(api, review_format, paper_pdf, language): start_time = time.time() if not api or not review_format or not paper_pdf: return "请输入完整内容！" # 判断PDF文件 else: # 创建一个Reader对象 reviewer1 = Reviewer(api, review_format, paper_pdf, language) # 开始判断是路径还是文件： comments, total_token_used = reviewer1.review_by_chatgpt(paper_list=paper_pdf) 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 comments, output2 ######################################################################################################## # 标题 title = "🤖ChatReviewer🤖" # 描述 description = '''
ChatReviewer是一款基于ChatGPT-3.5的API开发的智能论文分析与建议助手。其用途如下： ⭐️对论文的优缺点进行快速总结和分析，提高科研人员的文献阅读和理解的效率，紧跟研究前沿。 ⭐️对自己的论文进行分析，根据ChatReviewer生成的改进建议进行查漏补缺，进一步提高自己的论文质量。 如果觉得很卡，可以点击右上角的Duplicate this Space，把ChatReviewer复制到你自己的Space中！（🈲：禁止直接复制生成的评论用于任何论文审稿工作！） 本项目的[Github](https://github.com/nishiwen1214/ChatReviewer)，欢迎Star和Fork，也欢迎大佬赞助让本项目快速成长！💗⭐️右边生成框进度条拉满之后，显示Error，99%是你的ChatGPT的API免费额度用完或者过期了⭐️ **很多人留言没有ChatGPT的API-key....不会申请API的可以加我微信"Shiwen_Ni"(注：本人不卖号，真不会的可以找我，备注api)**
''' # 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="请输入特定的分析要求和格式(否则为默认格式)", default="""* Overall Review Please briefly summarize the main points and contributions of this paper. xxx * Paper Strength Please provide a list of the strengths of this paper, including but not limited to: innovative and practical methodology, insightful empirical findings or in-depth theoretical analysis, well-structured review of relevant literature, and any other factors that may make the paper valuable to readers. (Maximum length: 2,000 characters) (1) xxx (2) xxx (3) xxx * Paper Weakness Please provide a numbered list of your main concerns regarding this paper (so authors could respond to the concerns individually). These may include, but are not limited to: inadequate implementation details for reproducing the study, limited evaluation and ablation studies for the proposed method, correctness of the theoretical analysis or experimental results, lack of comparisons or discussions with widely-known baselines in the field, lack of clarity in exposition, or any other factors that may impede the reader's understanding or benefit from the paper. Please kindly refrain from providing a general assessment of the paper's novelty without providing detailed explanations. (Maximum length: 2,000 characters) (1) xxx (2) xxx (3) xxx * Questions To Authors And Suggestions For Rebuttal Please provide a numbered list of specific and clear questions that pertain to the details of the proposed method, evaluation setting, or additional results that would aid in supporting the authors' claims. The questions should be formulated in a manner that, after the authors have answered them during the rebuttal, it would enable a more thorough assessment of the paper's quality. (Maximum length: 2,000 characters) *Overall score (1-10) The paper is scored on a scale of 1-10, with 10 being the full mark, and 6 stands for borderline accept. Then give the reason for your rating. xxx""" ), gradio.inputs.File(label="请上传论文PDF(必填)",type="bytes"), gradio.inputs.Radio(choices=["English", "Chinese", "French", "German","Japenese"], default="English", label="选择输出语言"), ] chat_reviewer_gui = gradio.Interface(fn=main, inputs=inp, outputs = [gradio.Textbox(lines=25, label="分析结果"), gradio.Textbox(lines=2, label="资源统计")], title=title, description=description) # Start server chat_reviewer_gui .launch(quiet=True, show_api=False)