| import os | |
| import requests | |
| from bs4 import BeautifulSoup | |
| from pdf2image import convert_from_path | |
| import pytesseract | |
| import pickle | |
| from langchain.text_splitter import RecursiveCharacterTextSplitter | |
| from langchain.document_loaders import UnstructuredFileLoader | |
| from langchain.vectorstores.faiss import FAISS | |
| from langchain.embeddings import OpenAIEmbeddings | |
| def download_pdf(url, filename): | |
| print("Downloading pdf...") | |
| response = requests.get(url, stream=True) | |
| with open(filename, 'wb') as f: | |
| for chunk in response.iter_content(chunk_size=8192): | |
| f.write(chunk) | |
| def extract_pdf_text(filename): | |
| print("Extracting text from pdf...") | |
| pytesseract.pytesseract.tesseract_cmd = 'tesseract' | |
| images = convert_from_path(filename) | |
| text = "" | |
| for image in images: | |
| text += pytesseract.image_to_string(image) | |
| return text | |
| def get_arxiv_pdf_url(paper_link): | |
| if paper_link.endswith('.pdf'): | |
| return paper_link | |
| else: | |
| print("Getting pdf url...") | |
| response = requests.get(paper_link) | |
| soup = BeautifulSoup(response.text, 'html.parser') | |
| pdf_url = soup.find('a', {'class': 'mobile-submission-download'})['href'] | |
| pdf_url = 'https://arxiv.org' + pdf_url | |
| return pdf_url | |
| def read_paper(paper_link): | |
| print("Reading paper...") | |
| pdf_filename = 'paper.pdf' | |
| pdf_url = get_arxiv_pdf_url(paper_link) | |
| download_pdf(pdf_url, pdf_filename) | |
| text = extract_pdf_text(pdf_filename) | |
| os.remove(pdf_filename) | |
| return text | |
| def convert_to_vectorstore(arxiv_url, api_key): | |
| if not arxiv_url or not api_key: | |
| return None | |
| print("Converting to vectorstore...") | |
| txtfile = "paper.txt" | |
| with open(txtfile, 'w') as f: | |
| f.write(read_paper(arxiv_url)) | |
| loader = UnstructuredFileLoader(txtfile) | |
| raw_documents = loader.load() | |
| os.remove(txtfile) | |
| print("Loaded document") | |
| text_splitter = RecursiveCharacterTextSplitter(chunk_size=2000, chunk_overlap=200) | |
| documents = text_splitter.split_documents(raw_documents) | |
| os.environ["OPENAI_API_KEY"] = api_key | |
| embeddings = OpenAIEmbeddings() | |
| os.environ["OPENAI_API_KEY"] = "" | |
| vectorstore = FAISS.from_documents(documents, embeddings) | |
| return vectorstore |