app.py

import gradio as gr
from transformers import pipeline, AutoTokenizer
from sentence_transformers import SentenceTransformer, util
import nltk
from nltk.tokenize import sent_tokenize

# Download NLTK data
nltk.download('punkt')

# Translation models
translation_models = {
    'Vietnamese': "Helsinki-NLP/opus-mt-en-vi",
    'Japanese': "Helsinki-NLP/opus-mt-en-jap",
    'Thai': "Helsinki-NLP/opus-mt-en-tha",
    'Spanish': "Helsinki-NLP/opus-mt-en-es"
}

# Initialize summarization pipeline with a specified model
model_name = "sshleifer/distilbart-cnn-12-6"
summarizer = pipeline("summarization", model=model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Initialize translation pipeline
def get_translator(language):
    model_name = translation_models.get(language)
    if model_name:
        return pipeline("translation", model=model_name)
    return None

# Helper function to split text into chunks
def split_text(text, max_tokens=1024):
    inputs = tokenizer(text, return_tensors='pt', truncation=False)
    input_ids = inputs['input_ids'][0]
    total_tokens = len(input_ids)
    
    chunks = []
    start = 0
    while start < total_tokens:
        end = min(start + max_tokens, total_tokens)
        chunk_ids = input_ids[start:end]
        chunk_text = tokenizer.decode(chunk_ids, skip_special_tokens=True)
        chunks.append(chunk_text)
        start = end
    
    return chunks

# Helper function to summarize text
def summarize_text(text):
    chunks = split_text(text)
    summaries = []
    for chunk in chunks:
        try:
            summary = summarizer(chunk, max_length=150, min_length=40, do_sample=False)[0]['summary_text']
            summaries.append(summary)
        except Exception as e:
            print(f"Error summarizing chunk: {chunk}\nError: {e}")
    return " ".join(summaries)

# Helper function to translate text
def translate_text(text, language):
    translator = get_translator(language)
    if translator:
        try:
            translated_text = translator(text)[0]['translation_text']
            return translated_text
        except Exception as e:
            print(f"Error translating text: {text}\nError: {e}")
            return text
    return text

def process_text(input_text, language):
    print(f"Input text: {input_text[:500]}...")  # Show only the first 500 characters for brevity
    summary = summarize_text(input_text)
    print(f"Summary: {summary[:500]}...")  # Show only the first 500 characters for brevity
    bullet_points = generate_bullet_points(summary)
    print(f"Bullet Points: {bullet_points}")
    translated_text = translate_text(bullet_points, language)
    print(f"Translated Text: {translated_text}")
    return bullet_points, translated_text

def generate_bullet_points(text):
    print("Original Text:", text)
    sentences = sent_tokenize(text)
    print("Sentences:", sentences)
    
    bullet_points = []
    for sentence in sentences:
        bullet_points.append(sentence.strip())
    
    result = "\n".join(f"- {point}" for point in bullet_points)
    print("Bullet Points:", result)
    
    return result

# Create Gradio interface
iface = gr.Interface(
    fn=process_text,
    inputs=[
        gr.Textbox(label="Input Text", placeholder="Paste your text here...", lines=10),
        gr.Dropdown(choices=["Vietnamese", "Japanese", "Thai", "Spanish"], label="Translate to", value="Vietnamese")
    ],
    outputs=[
        gr.Textbox(label="Bullet Points", lines=10),
        gr.Textbox(label="Translated Bullet Points", lines=10)
    ],
    title="Text to Bullet Points and Translation",
    description="Paste any text, and the program will summarize it into bullet points. Optionally, translate the bullet points into Vietnamese, Japanese, Thai, or Spanish."
)

iface.launch()