Update app.py

app.py

@@ -1,10 +1,22 @@
 import gradio as gr
 from transformers import pipeline
 
-# Load summarization pipeline
-summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
+# 1. Use a lighter model and GPU if available
+summarizer = pipeline(
+    "summarization",
+    model="sshleifer/distilbart-cnn-12-6",
+    device=0  # set to -1 for CPU-only
+)
+
+def chunked_summary(text, chunk_size=800):
+    tokens = text.split()
+    chunks = [" ".join(tokens[i:i+chunk_size]) for i in range(0, len(tokens), chunk_size)]
+    summaries = [
+        summarizer(c, max_length=80, min_length=20, do_sample=False)[0]["summary_text"]
+        for c in chunks
+    ]
+    return " ".join(summaries)
 
-# Simple keyword-based action classifier
 def classify_action(email_text):
     email_lower = email_text.lower()
     if "meeting" in email_lower or "schedule" in email_lower:
@@ -16,30 +28,34 @@ def classify_action(email_text):
     else:
         return "Read and Archive"
 
-# Main function
 def summarize_and_recommend(email_text):
     if not email_text.strip():
         return "No content provided.", "No action"
 
-    # Summarize
-    summary = summarizer(email_text, max_length=130, min_length=30, do_sample=False)[0]['summary_text']
+    # 2. Decide whether to chunk
+    word_count = len(email_text.split())
+    if word_count > 800:
+        summary = chunked_summary(email_text)
+    else:
+        summary = summarizer(
+            email_text,
+            max_length=80,
+            min_length=20,
+            do_sample=False
+        )[0]['summary_text']
     
-    # Recommend action
     action = classify_action(email_text)
-
     return summary, action
 
-# Gradio UI
 iface = gr.Interface(
     fn=summarize_and_recommend,
-    inputs=gr.Textbox(lines=15, placeholder="Paste your email content here..."),
+    inputs=gr.Textbox(lines=15, placeholder="Paste your email here..."),
     outputs=[
         gr.Textbox(label="Summary"),
         gr.Textbox(label="Suggested Action")
     ],
     title="📩 Smart Email Summarizer & Action Recommender",
-    description="Paste an email to get a quick summary and an action suggestion. Uses Hugging Face's BART model for summarization.",
-    theme="default"
+    description="Faster summarization with a distilled model and length controls.",
 )
 
-iface.launch()
+iface.launch(server_name="0.0.0.0", server_port=7860)