import gradio as gr
import fitz  # PyMuPDF for reading PDFs
import numpy as np
from bokeh.plotting import figure, output_file, save
from bokeh.models import HoverTool, ColumnDataSource
import umap
import pandas as pd
from sklearn.metrics.pairwise import cosine_similarity, euclidean_distances
from sentence_transformers import SentenceTransformer
import tempfile
import logging

# Set up logging
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')

# Initialize the model globally
model = SentenceTransformer('all-MiniLM-L6-v2')
logging.info("Model loaded successfully.")

def process_pdf(pdf_path):
    logging.info(f"Processing PDF: {pdf_path}")
    # Open the PDF
    doc = fitz.open(pdf_path)
    texts = [page.get_text() for page in doc]
    print("PDF processed successfully.")
    return " ".join(texts)

def create_embeddings(text):
    print("Creating embeddings.")
    sentences = text.split(". ")  # A simple split; consider a more robust sentence splitter
    embeddings = model.encode(sentences)
    print("Embeddings created successfully.")
    return embeddings, sentences

def generate_plot(query, pdf_file):
    logging.info("Generating plot.")
    # Generate embeddings for the query
    query_embedding = model.encode([query])[0]
    
    # Process the PDF and create embeddings
    text = process_pdf(pdf_file.name)
    embeddings, sentences = create_embeddings(text)
    
    logging.info("Data prepared for UMAP.")
    # Prepare the data for UMAP and visualization
    all_embeddings = np.vstack([embeddings, query_embedding])
    all_sentences = sentences + [query]
    
    # UMAP transformation
    umap_transform = umap.UMAP(n_neighbors=15, min_dist=0.0, n_components=2, random_state=42)
    umap_embeddings = umap_transform.fit_transform(all_embeddings)
    
    logging.info("UMAP transformation completed.")
    # Find the closest sentences to the query
    distances = cosine_similarity([query_embedding], embeddings)[0]
    closest_indices = distances.argsort()[-5:][::-1]  # Adjust the number as needed
    
    # Prepare data for plotting
    data = {
        'x': umap_embeddings[:-1, 0],  # Exclude the query point itself
        'y': umap_embeddings[:-1, 1],  # Exclude the query point itself
        'content': all_sentences[:-1],  # Exclude the query sentence itself
        'color': ['red' if i in closest_indices else 'blue' for i in range(len(sentences))],
    }
    source = ColumnDataSource(data)
    
    # Create the Bokeh plot
    p = figure(title="UMAP Projection of Sentences", width=700, height=700)
    p.scatter('x', 'y', color='color', source=source)
    
    hover = HoverTool(tooltips=[("Content", "@content")])
    p.add_tools(hover)
    
    logging.info("Plot created successfully.")
    # Save the plot to an HTML file
    temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".html")
    output_file(temp_file.name)
    save(p)
    logging.info("Plot saved to file.")
    output_file("plot.html")
    return p.figure

def gradio_interface(pdf_file, query):
    logging.info("Gradio interface called.")
    plot_path = generate_plot(query, pdf_file)
    with open(plot_path, "r") as f:
        html_content = f.read()
    logging.info("Returning HTML content.")
    return html_content

iface = gr.Interface(
    fn=gradio_interface,
    inputs=[gr.File(label="Upload PDF"), gr.Textbox(label="Query")],
    outputs=gr.HTML(label="Visualization"),
    title="PDF Content Visualizer",
    description="Upload a PDF and enter a query to visualize the content."
)

if __name__ == "__main__":
    iface.launch()