Create app.py

app.py

@@ -0,0 +1,52 @@
+import gradio as gr
+from PyPDF2 import PdfReader
+from transformers import pipeline
+import json
+
+def generate_questions(pdf_file):
+    # Step 1: Extract text
+    reader = PdfReader(pdf_file.name)
+    text = ""
+    for page in reader.pages:
+        text += page.extract_text() + "\n"
+
+    # Step 2: Hugging Face QG model
+    qg_pipeline = pipeline("text2text-generation", model="valhalla/t5-small-qg-prepend")
+    questions = qg_pipeline(f"generate questions: {text[:2000]}")  # Demo: first 2000 chars
+
+    # Step 3: Build XML
+    generated_questions = []
+    for q in questions:
+        generated_questions.append({
+            "questiontext": q['generated_text'],
+            "questiontype": "single_select",
+            "marks": 10,
+            "options": [
+                {"optiontext": "Answer1", "score": "10"},
+                {"optiontext": "Answer2", "score": "0"}
+            ]
+        })
+
+    questiondata_json = json.dumps({
+        "title": "Certification Title",
+        "totalmarks": "50",
+        "time": "20",
+        "cutoff": "35",
+        "failurl": "",
+        "passurl": "",
+        "sendpassemail": True,
+        "questions": json.dumps({"questions": generated_questions}),
+        "maxattempts": 3
+    })
+
+    xml_output = f'<questiondata><![CDATA[{questiondata_json}]]></questiondata>'
+    return xml_output
+
+# Gradio UI
+iface = gr.Interface(
+    fn=generate_questions,
+    inputs=gr.File(file_types=['.pdf']),
+    outputs=gr.Textbox(label="Generated XML")
+)
+
+iface.launch()