from dotenv import load_dotenv
import streamlit as st
import pickle
from PyPDF2 import PdfReader
from transformers import pipeline
from sentence_transformers import SentenceTransformer
import os
import numpy as np

# Load environment variables from .env file
load_dotenv()

# Define a function to manually chunk text
def chunk_text(text, chunk_size=1000, chunk_overlap=200):
    chunks = []
    i = 0
    while i < len(text):
        chunks.append(text[i:i + chunk_size])
        i += chunk_size - chunk_overlap
    return chunks

# Function to generate embeddings using sentence-transformers
def generate_embeddings(text_chunks, model_name='all-MiniLM-L6-v2'):
    model = SentenceTransformer(model_name)

    embeddings = model.encode(text_chunks, convert_to_tensor=False)
    return embeddings

# Function to find the most relevant chunk based on the cosine similarity
def find_best_chunk(query_embedding, text_embeddings):
    cosine_similarities = np.dot(text_embeddings, query_embedding) / (
        np.linalg.norm(text_embeddings, axis=1) * np.linalg.norm(query_embedding)
    )
    best_index = np.argmax(cosine_similarities)
    return best_index, cosine_similarities[best_index]

# Main Streamlit app function
def main():
    st.header("LLM-powered PDF Chatbot 💬")

    # Upload a PDF file
    pdf = st.file_uploader("Upload your PDF", type='pdf')

    if pdf is not None:
        pdf_reader = PdfReader(pdf)

        text = ""
        for page in pdf_reader.pages:
            text += page.extract_text()

        # Split text into chunks
        chunks = chunk_text(text)

        # Generate embeddings for the chunks
        store_name = pdf.name[:-4]
        st.write(f'{store_name}')

        if os.path.exists(f"{store_name}.pkl"):
            with open(f"{store_name}.pkl", "rb") as f:
                text_embeddings = pickle.load(f)
            st.write('Embeddings Loaded from the Disk')
        else:
            text_embeddings = generate_embeddings(chunks)
            with open(f"{store_name}.pkl", "wb") as f:
                pickle.dump(text_embeddings, f)

        # Accept user questions/query
        query = st.text_input("Ask questions about your PDF file:")

        if query:
            # Generate embeddings for the query
            query_embedding = generate_embeddings([query])[0]

            # Find the best chunk for the query
            best_index, similarity = find_best_chunk(query_embedding, text_embeddings)
            best_chunk = chunks[best_index]

            # Use Hugging Face pipeline for question answering
            qa_pipeline = pipeline("question-answering", model="distilbert-base-uncased-distilled-squad")
            result = qa_pipeline(question=query, context=best_chunk)
            st.write(result['answer'])

def set_bg_from_url(url, opacity=1):
    footer = """
    <link href="https://cdn.jsdelivr.net/npm/bootstrap@5.2.0/dist/css/bootstrap.min.css" rel="stylesheet" integrity="sha384-gH2yIJqKdNHPEq0n4Mqa/HGKIhSkIHeL5AyhkYV8i59U5AR6csBvApHHNl/vI1Bx" crossorigin="anonymous">
    <footer>
        <div style='visibility: visible;margin-top:7rem;justify-content:center;display:flex;'>
            <p style="font-size:1.1rem;">
                Made by Asmae El-ghezzaz
                &nbsp;
                <a href="https://www.linkedin.com/in/asmae-el-ghezzaz/">
                    <svg xmlns="http://www.w3.org/2000/svg" width="23" height="23" fill="white" class="bi bi-linkedin" viewBox="0 0 16 16">
                        <path d="M0 1.146C0 .513.526 0 1.175 0h13.65C15.474 0 16 .513 16 1.146v13.708c0 .633-.526 1.146-1.175 1.146H1.175C.526 16 0 15.487 0 14.854V1.146zm4.943 12.248V6.169H2.542v7.225h2.401zm-1.2-8.212c.837 0 1.358-.554 1.358-1.248-.015-.709-.52-1.248-1.342-1.248-.822 0-1.359.54-1.359 1.248 0 .694.521 1.248 1.327 1.248h.016zm4.908 8.212V9.359c0-.216.016-.432.08-.586.173-.431.568-.878 1.232-.878.869 0 1.216.662 1.216 1.634v3.865h2.401V9.25c0-2.22-1.184-3.252-2.764-3.252-1.274 0-1.845.7-2.165 1.193v.025h-.016a5.54 5.54 0 0 1 .016-.025V6.169h-2.4c.03.678 0 7.225 0 7.225h2.4z"/>
                    </svg>          
                </a>
                &nbsp;
                <a href="https://github.com/aelghezzaz">
                    <svg xmlns="http://www.w3.org/2000/svg" width="23" height="23" fill="white" class="bi bi-github" viewBox="0 0 16 16">
                        <path d="M8 0C3.58 0 0 3.58 0 8c0 3.54 2.29 6.53 5.47 7.59.4.07.55-.17.55-.38 0-.19-.01-.82-.01-1.49-2.01.37-2.53-.49-2.69-.94-.09-.23-.48-.94-.82-1.13-.28-.15-.68-.52-.01-.53.63-.01 1.08.58 1.23.82.72 1.21 1.87.87 2.33.66.07-.52.28-.87.51-1.07-1.78-.2-3.64-.89-3.64-3.95 0-.87.31-1.59.82-2.15-.08-.2-.36-1.02.08-2.12 0 0 .67-.21 2.2.82.64-.18 1.32-.27 2-.27.68 0 1.36.09 2 .27 1.53-1.04 2.2-.82 2.2-.82.44 1.1.16 1.92.08 2.12.51.56.82 1.27.82 2.15 0 3.07-1.87 3.75-3.65 3.95.29.25.54.73.54 1.48 0 1.07-.01 1.93-.01 2.2 0 .21.15.46.55.38A8.012 8.012 0 0 0 16 8c0-4.42-3.58-8-8-8z"/>
                    </svg>
                </a>
            </p>
        </div>
    </footer>
    """
    st.markdown(footer, unsafe_allow_html=True)

    # Set background image using HTML and CSS
    st.markdown(
        f"""
        <style>
            body {{
                background: url('{url}') no-repeat center center fixed;
                background-size: cover;
                opacity: {opacity};
            }}
        </style>
        """,
        unsafe_allow_html=True
    )

# Set background image from URL
set_bg_from_url("https://www.1access.com/wp-content/uploads/2019/10/GettyImages-1180389186.jpg", opacity=0.5)

if __name__ == '__main__':
    main()