updated app.py to clean text input before sending to model

app.py

@@ -1,4 +1,5 @@
 import os
+import re
 from fastapi import FastAPI
 from pydantic import BaseModel
 from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
@@ -26,10 +27,20 @@ except Exception as e:
 class InputText(BaseModel):
    text: str
 
+def clean_text(text: str) -> str:
+   text = re.sub(r"[\r\n\t]+", " ", text)
+   text = re.sub(r"\s{2,}", " ", text)
+   text = text.strip()
+   return text
+
 @app.post("/summarize")
 async def summarize(input: InputText):
+
+   cleaned_input = clean_text(input.text)
+   prompt = f"summarize: {cleaned_input}"
+
    inputs = tokenizer(
-      input.text,
+      prompt,
       return_tensors="pt",
       max_length=16384,
       truncation=True,