app.py

import gradio as gr
import fitz  # PyMuPDF for reading PDFs
import numpy as np
import pandas as pd
import logging
from sentence_transformers import SentenceTransformer
from sklearn.metrics.pairwise import cosine_similarity, euclidean_distances, manhattan_distances
from sklearn.metrics.pairwise import linear_kernel as dot_similarity  # For dot product
import umap
import plotly.graph_objects as go

# 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}")
    doc = fitz.open(pdf_path)
    texts = [page.get_text() for page in doc]
    logging.info("PDF processed successfully.")
    return " ".join(texts)

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

def calculate_distances(embeddings, query_embedding, metric):
    if metric == "cosine":
        distances = 1 - cosine_similarity(embeddings, [query_embedding])
    elif metric == "euclidean":
        distances = euclidean_distances(embeddings, [query_embedding])
    elif metric == "manhattan":
        distances = manhattan_distances(embeddings, [query_embedding])
    elif metric == "dot":
        distances = -dot_similarity(embeddings, [query_embedding])  # Negated for consistency with other metrics
    return distances.flatten()

def generate_plotly_figure(query, pdf_file, metric):
    logging.info("Generating plot with Plotly.")
    query_embedding = model.encode([query])[0]
    text = process_pdf(pdf_file.name)
    embeddings, sentences = create_embeddings(text)
    all_embeddings = np.vstack([embeddings, query_embedding])
    all_sentences = sentences + [query]

    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)
    
    distances = calculate_distances(embeddings, query_embedding, metric)
    closest_indices = np.argsort(distances)[:5]  # Get indices of 5 closest sentences
    
    colors = ['green' if i in closest_indices else 'blue' for i in range(len(sentences))]
    colors.append('red')  # For the query
    
    fig = go.Figure(data=go.Scatter(x=umap_embeddings[:-1, 0], y=umap_embeddings[:-1, 1], mode='markers',
                                    marker=dict(color=colors[:-1]), text=all_sentences[:-1],
                                    name='Sentences'))
    fig.add_trace(go.Scatter(x=[umap_embeddings[-1, 0]], y=[umap_embeddings[-1, 1]], mode='markers',
                             marker=dict(color='red'), text=[query], name='Query'))
    fig.update_layout(title="UMAP Projection of Sentences with Query Highlight", xaxis_title="UMAP 1", yaxis_title="UMAP 2")
    
    logging.info("Plotly figure created successfully.")
    return fig

def gradio_interface(pdf_file, query, metric):
    logging.info("Gradio interface called with metric: " + metric)
    fig = generate_plotly_figure(query, pdf_file, metric)
    logging.info("Returning Plotly figure.")
    return fig

iface = gr.Interface(
    fn=gradio_interface,
    inputs=[
        gr.File(label="Upload PDF"),
        gr.Textbox(label="Query"),
        gr.Radio(choices=["cosine", "euclidean", "manhattan", "dot"], label="Distance Metric")
    ],
    outputs=gr.Plot(),
    title="PDF Content Visualizer",
    description="""This tool allows you to upload a PDF document, input a query, and visualize the context of the document 
    as it relates to your query. It uses UMAP for dimensionality reduction and highlights the query and its closest contexts 
    within the document based on the selected distance metric. Choose from cosine, Euclidean, Manhattan, or dot product metrics 
    to explore different aspects of textual similarity."""
)

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