赞
踩
阅读论文可以说是我们的日常工作之一,论文的数量太多,我们如何快速阅读归纳呢?自从ChatGPT出现以后,有很多阅读论文的服务可以使用。其实使用ChatGPT API非常简单,我们只用30行python代码就可以在本地搭建一个自己的应用。
使用 Python 和 ChatGPT API 总结论文的步骤很简单:
import PyPDF2
import openai
pdf_summary_text = ""
解析pdf
pdf_file_path = "./pdfs/paper.pdf"
pdf_file = open(pdf_file_path, 'rb')
pdf_reader = PyPDF2.PdfReader(pdf_file)
获取每一页的文本:
for page_num in range(len(pdf_reader.pages)):
page_text = pdf_reader.pages[page_num].extract_text().lower()
使用openai的api进行汇总
response = openai.ChatCompletion.create(
model="gpt-3.5-turbo",
messages=[
{"role": "system", "content": "You are a helpful research assistant."},
{"role": "user", "content": f"Summarize this: {page_text}"},
],
)
page_summary = response["choices"][0]["message"]["content"]
合并摘要
pdf_summary_text += page_summary + "\n"
pdf_summary_file = pdf_file_path.replace(os.path.splitext(pdf_file_path)[1], "_summary.txt")
with open(pdf_summary_file, "w+") as file:
file.write(pdf_summary_text)
搞定,关闭pdf文件,回收内存
pdf_file.close()
完整代码如下:
import os import PyPDF2 import re import openai # Here I assume you are on a Jupiter Notebook and download the paper directly from the URL !curl -o paper.pdf https://arxiv.org/pdf/2301.00810v3.pdf?utm_source=pocket_saves # Set the string that will contain the summary pdf_summary_text = "" # Open the PDF file pdf_file_path = "paper.pdf" # Read the PDF file using PyPDF2 pdf_file = open(pdf_file_path, 'rb') pdf_reader = PyPDF2.PdfReader(pdf_file) # Loop through all the pages in the PDF file for page_num in range(len(pdf_reader.pages)): # Extract the text from the page page_text = pdf_reader.pages[page_num].extract_text().lower() response = openai.ChatCompletion.create( model="gpt-3.5-turbo", messages=[ {"role": "system", "content": "You are a helpful research assistant."}, {"role": "user", "content": f"Summarize this: {page_text}"}, ], ) page_summary = response["choices"][0]["message"]["content"] pdf_summary_text+=page_summary + "\n" pdf_summary_file = pdf_file_path.replace(os.path.splitext(pdf_file_path)[1], "_summary.txt") with open(pdf_summary_file, "w+") as file: file.write(pdf_summary_text) pdf_file.close() with open(pdf_summary_file, "r") as file: print(file.read())
需要说明的是2个事情:
1、openai的API免费调用额度是有限的,这个方法一篇论文大概在0.2-0.5美元左右,根据论文长度会有变化
2、gpt4的API我没测试,因为我还没有申请到,并且看价格那个太贵了(贵20倍)我觉得不值,但是可以试试把论文的图表一同传过去,是不是会有更好效果(不确定)
https://avoid.overfit.cn/post/914a2ba7497f467798bed72208778ad8
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。