A Simple Guide to Loading an Entire PDF into a List of Documents Using Langchain

#ai #langchain #python

Before diving into the code, it is essential to install the necessary packages to ensure everything runs smoothly. You can do this by executing the following commands in your terminal:

pip install langchain_community
pip install pypdf

from langchain_community.document_loaders import PyPDFLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter

# Load the PDF file from the specified path.

FILE_PATH = "c:/work/Test01.pdf"

loader = PyPDFLoader(file_path=FILE_PATH)

# Load the entire PDF into a list of documents

text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)

documents = loader.load_and_split(text_splitter)

for i in range(len(documents)):
    print(documents[i].page_content + "\n")```