Update app.py

app.py

@@ -1,27 +1,23 @@
-import re
 import gradio as gr
 from transformers import pipeline, BartTokenizer, BartForConditionalGeneration
 
-# Load the BART model and tokenizer for text generation (answer suggestions)
-model_name = "facebook/bart-large-cnn"
+# Load the BART model and tokenizer for text generation
+model_name = "facebook/bart-small"
 tokenizer = BartTokenizer.from_pretrained(model_name)
 model = BartForConditionalGeneration.from_pretrained(model_name)
 
-# Question detection function
 def detect_questions(email_text):
-    # Use regex to find questions in the email
-    questions = re.findall(r'([^\.\!\?]*\?)', email_text)
+    # Simple heuristic to detect questions
+    questions = [sentence.strip() + "?" for sentence in email_text.split(".") if "?" in sentence]
     return questions
 
-# Generate answers using the BART model
 def generate_answers(question):
-    # Use the BART model to generate a response
+    # Generate an answer for the given question using the BART model
     inputs = tokenizer(question, return_tensors="pt", max_length=1024, truncation=True)
     summary_ids = model.generate(inputs["input_ids"], num_beams=4, max_length=50, early_stopping=True)
     answer = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
     return answer
 
-# Main function to handle the email input
 def process_email(email_text):
     questions = detect_questions(email_text)
     responses = {}
@@ -32,14 +28,12 @@ def process_email(email_text):
     
     return responses
 
-# Create a Gradio interface
 iface = gr.Interface(
     fn=process_email,
     inputs="textbox",
-    outputs="json",
-    title="Email Question Detector and Responder",
-    description="Input an email, and the AI will detect questions and provide suggested responses.",
+    outputs="text",
+    title="Email Question Responder",
+    description="Input an email, and the AI will detect questions and provide possible answers.",
 )
 
-# Launch the interface
 iface.launch()