Chat-PDF / core /pdf_processing.py
Salahin's picture
Initial commit
642d32b
Raw History Blame Contribute Delete
761 Bytes
from PyPDF2 import PdfReader
import streamlit as st
from langchain_text_splitters import RecursiveCharacterTextSplitter
def get_pdf_text(pdf_docs):
try:
text = ""
for pdf in pdf_docs:
pdf_reader = PdfReader(pdf)
for page in pdf_reader.pages:
text += page.extract_text()
return text
except Exception as e:
st.error(f"Error extracting text from PDF: {e}")
return None
def get_text_chunks(text):
try:
text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=1000)
chunks = text_splitter.split_text(text)
return chunks
except Exception as e:
st.error(f"Error splitting text into chunks: {e}")
return None