Update app.py

app.py

@@ -1,55 +1,62 @@
 from pptx import Presentation
 import re
-from transformers import pipeline
 import gradio as gr
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+import torch
+import torch.nn.functional as F
+from transformers import pipeline
+
+# Load the pre-trained model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained("Ahmed235/roberta_classification")
+model = AutoModelForSequenceClassification.from_pretrained("Ahmed235/roberta_classification")
+
+# Create a summarization pipeline
+summarizer = pipeline("summarization", model="Falconsai/text_summarization")
 
 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)
 
-
 def predict_pptx_content(file_path):
-    print(f"File path received: {file_path}")
-    try:
-        extracted_text = extract_text_from_pptx(file_path)
-        print(f"Extracted text: {extracted_text}")
+    extracted_text = extract_text_from_pptx(file_path)
+    cleaned_text = re.sub(r'\s+', ' ', extracted_text)
 
-        cleaned_text = re.sub(r'\s+', ' ', extracted_text)
-        print(f"Cleaned text: {cleaned_text}")
+    # Tokenize and encode the cleaned text
+    input_encoding = tokenizer(cleaned_text, truncation=True, padding=True, return_tensors="pt")
 
-        classifier = pipeline("text-classification", model="Ahmed235/roberta_classification")
+    # Perform inference
+    with torch.no_grad():
+        outputs = model(**input_encoding)
+        logits = outputs.logits
 
-        # summarizer = pipeline("summarization", model="Falconsai/text_summarization")
+    probabilities = F.softmax(logits, dim=1)
 
-        result = classifier(cleaned_text)[0]
-        predicted_label = result['label']
-        predicted_probability = result['score']
+    predicted_label_id = torch.argmax(logits, dim=1).item()
+    predicted_label = model.config.id2label[predicted_label_id]
+    predicted_probability = probabilities[0][predicted_label_id].item()
 
-        prediction = {
-            "Predicted Label": predicted_label,
-            "Evaluation": f"Evaluate the topic according to {predicted_label} is: {predicted_probability}"
-            # "Summary": summarizer(cleaned_text, max_length=80, min_length=30, do_sample=False)
-        }
+    # Summarize the cleaned text
+    summary = summarizer(cleaned_text, max_length=80, min_length=30, do_sample=False)[0]['summary_text']
 
-        return prediction
-    except Exception as e:
-        print(f"Error processing file: {e}")
-        return {"error": str(e)}
+    prediction = {
+        "Predicted Label": predicted_label,
+        "Evaluation": f"Evaluate the topic according to {predicted_label} is: {predicted_probability}",
+        "Summary": summary
+    }
 
+    return prediction
 
 # Define the Gradio interface
 iface = gr.Interface(
     fn=predict_pptx_content,
-    inputs=gr.File(type="filepath", label="Upload PowerPoint (.pptx) file"),
-    outputs=["text", "text"],  # Predicted Label, Evaluation, Summary
-    live=False,  # Change to False for one-time analysis
+    inputs=gr.File(type="file", label="Upload PowerPoint (.pptx) file"),
+    outputs=["text", "text", "text"],  # Predicted Label, Evaluation, Summary
+    live=False,  # Change to True for one-time analysis
     title="<h1 style='color: lightgreen; text-align: center;'>PPTX Analyzer</h1>",
 )