Update app.py

app.py

@@ -1,7 +1,85 @@
+# --------------------------------------------------------
+# 📘 Multi-Document Summarizer (using BART + Clustering)
+# --------------------------------------------------------
+
+import numpy as np
+import streamlit as st
+from transformers import BartTokenizer, BartForConditionalGeneration
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.cluster import KMeans
+from nltk.tokenize import sent_tokenize
+import nltk
+import PyPDF2
+from io import BytesIO
+
+# ✅ Streamlit Page Configuration
+st.set_page_config(page_title="Multi-Document Summarizer", layout="centered")
+
+# --------------------------------------------------------
+# 📦 Download NLTK data
+# --------------------------------------------------------
+@st.cache_resource
+def download_nltk_data():
+    try:
+        nltk.data.find('tokenizers/punkt')
+    except LookupError:
+        nltk.download('punkt', quiet=True)
+        nltk.download('punkt_tab', quiet=True)
+
+download_nltk_data()
+
+# --------------------------------------------------------
+# 🤖 Load BART Model
+# --------------------------------------------------------
+@st.cache_resource
+def load_model():
+    tokenizer = BartTokenizer.from_pretrained('facebook/bart-large-cnn')
+    model = BartForConditionalGeneration.from_pretrained('facebook/bart-large-cnn')
+    return tokenizer, model
+
+tokenizer, model = load_model()
+
+# --------------------------------------------------------
+# 🧰 Helper Functions
+# --------------------------------------------------------
+def extract_text_from_pdf(file) -> str:
+    """Extract text from uploaded PDF file."""
+    pdf_reader = PyPDF2.PdfReader(BytesIO(file.read()))
+    text = ""
+    for page in pdf_reader.pages:
+        text += page.extract_text() or ""
+    return text.strip()
+
+
+def chunk_text(text, max_words=800):
+    """Split long text into smaller chunks for summarization."""
+    if len(text.split()) <= max_words:
+        return [text]
+
+    sentences = sent_tokenize(text)
+    chunks, current_chunk, current_word_count = [], [], 0
+
+    for sentence in sentences:
+        sentence_words = len(sentence.split())
+        if current_word_count + sentence_words <= max_words:
+            current_chunk.append(sentence)
+            current_word_count += sentence_words
+        else:
+            chunks.append(" ".join(current_chunk))
+            current_chunk = [sentence]
+            current_word_count = sentence_words
+
+    if current_chunk:
+        chunks.append(" ".join(current_chunk))
+
+    return chunks
+
+
 def summarize_large_text(text, max_length=150, min_length=50):
     """Summarize long text by splitting into chunks and combining summaries."""
     chunks = chunk_text(text, max_words=800)
     summaries = []
+
     for chunk in chunks:
         inputs = tokenizer([chunk], max_length=1024, truncation=True, return_tensors='pt')
         summary_ids = model.generate(
@@ -28,15 +106,23 @@ def summarize_large_text(text, max_length=150, min_length=50):
     return final_summary
 
 
+def cluster_documents(documents, n_clusters=3):
+    """Cluster similar documents using TF-IDF + KMeans."""
+    vectorizer = TfidfVectorizer(stop_words='english')
+    X = vectorizer.fit_transform(documents)
+    kmeans = KMeans(n_clusters=n_clusters, random_state=42).fit(X)
+    return kmeans.labels_
+
+
 def multi_document_summarize(documents):
-    """Summarize multiple related documents using clustering + improved BART summarization."""
+    """Summarize multiple related documents using clustering + BART."""
     results = {
         'individual_summaries': [],
         'cluster_summaries': [],
         'final_summary': None
     }
 
-    # 1️⃣ Individual summaries (using improved function)
+    # 1️⃣ Individual summaries
     for doc in documents:
         doc_summary = summarize_large_text(doc)
         results['individual_summaries'].append(doc_summary)
@@ -45,7 +131,7 @@ def multi_document_summarize(documents):
     if len(documents) > 1:
         n_clusters = min(3, len(documents))
         clusters = cluster_documents(documents, n_clusters=n_clusters)
-        
+
         for cluster_id in np.unique(clusters):
             cluster_docs = [doc for doc, c in zip(documents, clusters) if c == cluster_id]
             combined_text = " ".join(cluster_docs)
@@ -54,16 +140,48 @@ def multi_document_summarize(documents):
                 'doc_indices': [i for i, c in enumerate(clusters) if c == cluster_id],
                 'summary': cluster_summary
             })
-        
+
         # 3️⃣ Final overall summary
         all_summaries = results['individual_summaries'] + [cs['summary'] for cs in results['cluster_summaries']]
         results['final_summary'] = summarize_large_text(" ".join(all_summaries))
     else:
         results['final_summary'] = results['individual_summaries'][0]
-    
+
     return results
 
 
+# --------------------------------------------------------
+# 🖥️ Streamlit Interface
+# --------------------------------------------------------
+st.title("🧠 Multi-Document Summarizer")
+st.markdown("Upload one or more **PDFs or text files** to generate a smart summary using AI.")
+
+uploaded_files = st.file_uploader("Upload your documents", type=["pdf", "txt"], accept_multiple_files=True)
+
+if uploaded_files:
+    documents = []
+    for file in uploaded_files:
+        if file.name.endswith(".pdf"):
+            text = extract_text_from_pdf(file)
+        else:
+            text = file.read().decode("utf-8")
+        documents.append(text)
+
+    if st.button("Generate Summary"):
+        with st.spinner("Generating summary... please wait ⏳"):
+            results = multi_document_summarize(documents)
+
+        st.subheader("📄 Final Summary")
+        st.write(results['final_summary'])
+
+        st.download_button(
+            label="📥 Download Summary",
+            data=results['final_summary'],
+            file_name="summary.txt",
+            mime="text/plain"
+        )
+
+
 
  # --------------------------- STREAMLIT UI ---------------------------