DocChatAI / services /pdf_processing.py
Deepak Yadav
updated new version deepseek-r1
e50c54a
raw
history blame
420 Bytes
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