app.py

import gradio as gr
from transformers import T5ForConditionalGeneration, T5Tokenizer
import pandas as pd

# Load the T5 model and tokenizer
model_name = "t5-small"
model = T5ForConditionalGeneration.from_pretrained(model_name)
tokenizer = T5Tokenizer.from_pretrained(model_name)

# Sample DataFrame (You need to upload your dataset to Hugging Face Spaces)
df = pd.read_csv("t_kjv.csv")  # Replace "data.csv" with the path to your uploaded CSV file in your Space

# Map book numbers to book names
book_mapping = {
    1: "Genesis",
    2: "Exodus",
    3: "Leviticus",
    4: "Numbers",
    5: "Deuteronomy",
    6: "Joshua",
    7: "Judges",
    8: "Ruth",
    9: "1 Samuel",
    10: "2 Samuel",
    11: "1 Kings",
    12: "2 Kings",
    13: "1 Chronicles",
    14: "2 Chronicles",
    15: "Ezra",
    16: "Nehemiah",
    17: "Esther",
    18: "Job",
    19: "Psalms",
    20: "Proverbs",
    21: "Ecclesiastes",
    22: "Song of Solomon",
    23: "Isaiah",
    24: "Jeremiah",
    25: "Lamentations",
    26: "Ezekiel",
    27: "Daniel",
    28: "Hosea",
    29: "Joel",
    30: "Amos",
    31: "Obadiah",
    32: "Jonah",
    33: "Micah",
    34: "Nahum",
    35: "Habakkuk",
    36: "Zephaniah",
    37: "Haggai",
    38: "Zechariah",
    39: "Malachi",
    40: "Matthew",
    41: "Mark",
    42: "Luke",
    43: "John",
    44: "Acts",
    45: "Romans",
    46: "1 Corinthians",
    47: "2 Corinthians",
    48: "Galatians",
    49: "Ephesians",
    50: "Philippians",
    51: "Colossians",
    52: "1 Thessalonians",
    53: "2 Thessalonians",
    54: "1 Timothy",
    55: "2 Timothy",
    56: "Titus",
    57: "Philemon",
    58: "Hebrews",
    59: "James",
    60: "1 Peter",
    61: "2 Peter",
    62: "1 John",
    63: "2 John",
    64: "3 John",
    65: "Jude",
    66: "Revelation"
}

# Create a reverse mapping of book names to book numbers
reverse_book_mapping = {v: k for k, v in book_mapping.items()}

def summarize_bible(book_name, chapter_number, max_summary_length=500):
    # Get the corresponding book number from reverse_book_mapping
    book_number = reverse_book_mapping.get(book_name)
    
    if book_number is None:
        return "Invalid Book Name"
    
    # Filter the DataFrame based on the selected book and chapter
    chapter_text = df[(df["b"] == book_number) & (df["c"] == int(chapter_number))]["t"].values.tolist()

    # Generate summary using the T5 model with custom max_length
    summary = model.generate(
        tokenizer.encode("summarize: " + chapter_text[0], return_tensors="pt"),
        max_length=max_summary_length,
        num_return_sequences=1,
    )

    # Decode and return the summary
    decoded_summary = tokenizer.decode(summary[0], skip_special_tokens=True)

    final_summary = f"Summary of {book_name}, Chapter {chapter_number}:\n{decoded_summary}"
    return final_summary

# Create the input and output interfaces for Gradio
input_interface = [
    gr.inputs.Dropdown(list(book_mapping.values()), label="Select Book"),
    gr.inputs.Number(label="Chapter Number")
]

output_interface = gr.outputs.Textbox(label="Chapter Summary")

# Create the Gradio app
gr.Interface(fn=summarize_bible, inputs=input_interface, outputs=output_interface, title="Bible Chapter Summarizer").launch()