File size: 420 Bytes
7d9087b
 
 
 
 
 
e50c54a
 
 
1
2
3
4
5
6
7
8
9
10
from langchain_community.document_loaders import PyMuPDFLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter

def load_and_split_pdf(filepath):
    loader = PyMuPDFLoader(filepath)  # Use PyMuPDFLoader instead
    documents = loader.load()
    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
    splits = text_splitter.split_documents(documents)
    return splits