DEV Community

Saravanan Muniraj
Saravanan Muniraj

Posted on

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
Enter fullscreen mode Exit fullscreen mode 
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")```
Enter fullscreen mode Exit fullscreen mode

Top comments (0)