DocProcessor.py

from pypdf import PdfReader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.embeddings import HuggingFaceEmbeddings 
from langchain_community.vectorstores import FAISS   


def get_pdf_text(pdf_docs):
    """Extracts text from a list of uploaded PDF files."""
    text = ""
    for pdf in pdf_docs:
        pdf_reader = PdfReader(pdf)
        for page in pdf_reader.pages:

            text += page.extract_text() + " "
    return text

def get_text_chunks(text):
    """Splits a long text into smaller, manageable chunks."""
    text_splitter = RecursiveCharacterTextSplitter(
        chunk_size=1000,
        chunk_overlap=200,
        length_function=len
    )
    chunks = text_splitter.split_text(text)
    return chunks

def get_vectorstore(text_chunks):
    """Creates a FAISS vector store from text chunks."""
    embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
    return vectorstore