Create app.py

app.py

@@ -0,0 +1,71 @@
+import gradio as gr
+from transformers import pipeline
+import networkx as nx
+import numpy as np
+import re
+import nltk
+from nltk.tokenize import sent_tokenize
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
+
+# Download NLTK data
+nltk.download('punkt')
+
+# Load Transformer model for abstractive summarization
+summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
+
+# Extractive summarization using TextRank
+def extractive_summarization(text, num_sentences=3):
+    sentences = sent_tokenize(text)
+    if len(sentences) <= num_sentences:
+        return text  # If text is short, return as is
+    
+    vectorizer = TfidfVectorizer(stop_words="english")
+    sentence_vectors = vectorizer.fit_transform(sentences)
+    similarity_matrix = cosine_similarity(sentence_vectors)
+    graph = nx.from_numpy_array(similarity_matrix)
+    scores = nx.pagerank(graph)
+    ranked_sentences = sorted(((scores[i], s) for i, s in enumerate(sentences)), reverse=True)
+    return " ".join([s for _, s in ranked_sentences[:num_sentences]])
+
+# Abstractive summarization using BART
+def abstractive_summarization(text, length):
+    if len(text.split()) < 30:
+        return "Text is too short for summarization."
+    max_length = {"short": 50, "medium": 100, "long": 150}[length]
+    summary = summarizer(text, max_length=max_length, min_length=30, do_sample=False)[0]['summary_text']
+    return summary
+
+# Main function
+def summarize_text(text, method, length):
+    if method == "Abstractive (BART)":
+        return abstractive_summarization(text, length)
+    else:
+        num_sentences = {"short": 2, "medium": 4, "long": 6}[length]
+        return extractive_summarization(text, num_sentences)
+
+# Function to process file upload
+def process_file(file):
+    return file.read().decode("utf-8")
+
+# UI with Gradio
+with gr.Blocks(theme=gr.themes.Soft()) as iface:
+    gr.Markdown("# 📄 AI-Powered Text Summarizer")
+    gr.Markdown("Summarize long articles, news, and research papers using advanced NLP models.")
+
+    with gr.Row():
+        method_choice = gr.Radio(["Abstractive (BART)", "Extractive (TextRank)"], label="Summarization Type", value="Abstractive (BART)")
+        length_choice = gr.Radio(["short", "medium", "long"], label="Summary Length", value="medium")
+
+    text_input = gr.Textbox(lines=8, placeholder="Paste long text here...", label="Input Text")
+    file_input = gr.File(label="Or Upload a .txt file")
+    summarize_button = gr.Button("Summarize ✨")
+
+    summary_output = gr.Textbox(lines=6, label="Summarized Text", interactive=False)
+    
+    file_input.change(process_file, inputs=file_input, outputs=text_input)
+    summarize_button.click(summarize_text, inputs=[text_input, method_choice, length_choice], outputs=summary_output)
+
+# Launch app
+if __name__ == "__main__":
+    iface.launch()