app.py

import gradio as gr
from langchain.document_loaders import PyPDFLoader
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import FAISS
from langchain.chat_models import ChatOpenAI
from langchain.llms import OpenAI

def process_pdfs(files):
    """Process uploaded PDFs and return extracted text."""
    texts = []
    for file in files:
        loader = PyPDFLoader(file.name)
        docs = loader.load()
        texts.append("\n".join([doc.page_content for doc in docs]))
    return "\n\n".join(texts)

def create_gradio_interface():
    """Create and launch the Gradio interface."""
    with gr.Blocks() as demo:
        gr.Markdown("# PDF Text Extractor")

        pdf_files = gr.Files(label="Upload PDF Documents", type="file")  # Fixed multiple file issue

        output_text = gr.Textbox(label="Extracted Text", lines=10)

        extract_button = gr.Button("Extract Text")

        extract_button.click(process_pdfs, inputs=[pdf_files], outputs=[output_text])

    return demo

if __name__ == "__main__":
    demo = create_gradio_interface()
    demo.launch()