Update app.py

app.py

@@ -4,54 +4,63 @@ from pptx import Presentation
 import re
 import json
 
-# Create a text classification pipeline
+# Load the classification and summarization pipelines
 classifier = pipeline("text-classification", model="Ahmed235/roberta_classification", tokenizer="Ahmed235/roberta_classification")
 summarizer = pipeline("summarization", model="Falconsai/text_summarization")
 
+# Cache for model weights
+classification_model_loaded = False
+summarization_model_loaded = False
+
+def load_models():
+ global classifier, summarizer, classification_model_loaded, summarization_model_loaded
+ if not classification_model_loaded:
+ classifier = pipeline("text-classification", model="Ahmed235/roberta_classification", tokenizer="Ahmed235/roberta_classification")
+ classification_model_loaded = True
+ if not summarization_model_loaded:
+ summarizer = pipeline("summarization", model="Falconsai/text_summarization")
+ summarization_model_loaded = True
+
+# Extract text from PowerPoint
 def extract_text_from_pptx(file_path):
- presentation = Presentation(file_path)
- text = []
- for slide_number, slide in enumerate(presentation.slides, start=1):
- for shape in slide.shapes:
- if hasattr(shape, "text"):
- text.append(shape.text)
- return "\n".join(text)
+ try:
+ presentation = Presentation(file_path)
+ text = []
+ for slide in presentation.slides:
+ for shape in slide.shapes:
+ if hasattr(shape, "text"):
+ text.append(shape.text)
+ return "\n".join(text)
+ except Exception as e:
+ print(f"Error extracting text from PowerPoint: {e}")
+ return ""
 
+# Limit text length
 def limit_text_length(text, max_length=512):
- # Truncate or limit the text length
  return text[:max_length]
 
+# Predict content from PowerPoint
 def predict_pptx_content(file_path):
  try:
+ load_models() # Load models if not loaded already
  extracted_text = extract_text_from_pptx(file_path)
  cleaned_text = re.sub(r'\s+', ' ', extracted_text)
- 
- 
  limited_text = limit_text_length(cleaned_text)
-
- 
  result = classifier(limited_text)
-
  predicted_label = result[0]['label']
  predicted_probability = result[0]['score']
  summary = summarizer(cleaned_text, max_length=1000, min_length=30, do_sample=False)[0]['summary_text']
- 
  output = {
  "predicted_label": predicted_label,
  "evaluation": predicted_probability,
  "summary": summary
  }
- 
- output_dict = json.dumps(output, indent = 3)
-
- return output_dict 
-
+ return json.dumps(output, indent=3)
  except Exception as e:
- # Log the error details
- print(f"Error in predict_pptx_content: {e}")
+ print(f"Error predicting content from PowerPoint: {e}")
  return {"error": str(e)}
 
-
+# Gradio interface
 iface = gr.Interface(
  fn=predict_pptx_content,
  inputs=gr.File(type="filepath", label="Upload PowerPoint (.pptx) file"),