Update app.py

app.py

@@ -0,0 +1,25 @@
+from fastapi import FastAPI
+from pydantic import BaseModel
+from transformers import pipeline
+
+# Load AI Model for Question Extraction
+question_extractor = pipeline("text-classification", model="textattack/bert-base-uncased-MRPC")
+
+app = FastAPI()
+
+# Define API Input Format
+class OCRText(BaseModel):
+    text: str
+
+@app.post("/extract_question")
+def extract_question(data: OCRText):
+    text = data.text
+    lines = text.split("\n")
+    
+    # Use AI Model to Identify Question Parts
+    ranked_lines = sorted(lines, key=lambda line: question_extractor(line)[0]['score'], reverse=True)
+    top_sentences = [line for line in ranked_lines[:3] if len(line) > 10]  # Keep Top 3 Sentences
+    
+    question_text = " ".join(top_sentences)
+    
+    return {"extracted_question": question_text}