Create model_utils.py

model_utils.py

@@ -0,0 +1,31 @@
+from transformers import pipeline
+
+# Replace this with your fine-tuned MCQ extractor if needed
+classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
+
+labels = ["question", "option", "answer", "other"]
+
+def classify_chunk(text):
+    result = classifier(text, labels)
+    return result['labels'][0]  # Most likely label
+
+def extract_mcqs_with_model(text):
+    chunks = [chunk.strip() for chunk in text.split("\n\n") if chunk.strip()]
+    mcqs = []
+    current = {"question": "", "options": [], "answer": ""}
+
+    for chunk in chunks:
+        label = classify_chunk(chunk)
+        if label == "question":
+            if current["question"]:
+                mcqs.append(current)
+                current = {"question": "", "options": [], "answer": ""}
+            current["question"] = chunk
+        elif label == "option":
+            current["options"].append(chunk)
+        elif label == "answer":
+            current["answer"] = chunk
+
+    if current["question"]:
+        mcqs.append(current)
+    return mcqs