File size: 761 Bytes
642d32b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
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