Update app.py

app.py

@@ -1,49 +1,12 @@
 from fastapi import FastAPI, HTTPException
-from pydantic import BaseModel
-from transformers import T5ForConditionalGeneration, T5Tokenizer
-import torch
-import nest_asyncio
 import uvicorn
 
 # Initialize FastAPI app
 app = FastAPI()
 
-# Load pre-trained T5 model and tokenizer for paraphrasing
-model_name = "t5-small"  # You can use "t5-base" or other variants for better performance
-tokenizer = T5Tokenizer.from_pretrained(model_name)
-model = T5ForConditionalGeneration.from_pretrained(model_name)
-
-# Define request body model
-class ParaphraseRequest(BaseModel):
-    text: str
-
-# Define response model
-class ParaphraseResponse(BaseModel):
-    paraphrased_text: str
-
-# Function to generate paraphrased text
-def paraphrase_text(input_text: str) -> str:
-    try:
-        # Prepare input for T5 model (prepend "paraphrase:" to the input text)
-        input_ids = tokenizer.encode("paraphrase: " + input_text, return_tensors="pt", max_length=512, truncation=True)
-
-        # Generate paraphrased text
-        outputs = model.generate(input_ids, max_length=512, num_beams=5, early_stopping=True)
-
-        # Decode the generated text
-        paraphrased_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
-        return paraphrased_text
-    except Exception as e:
-        raise HTTPException(status_code=500, detail=f"Error during paraphrasing: {str(e)}")
-
-# API endpoint for paraphrasing
-@app.post("/paraphrase", response_model=ParaphraseResponse)
-async def paraphrase(request: ParaphraseRequest):
-    paraphrased_text = paraphrase_text(request.text)
-    return {"paraphrased_text": paraphrased_text}
-
-# Apply nest_asyncio to allow nested event loops
-nest_asyncio.apply()
+@app.route('/')
+def index():
+    return "Hello"
 
 # Run the app with Uvicorn (use this command in terminal: uvicorn your_script_name:app --reload)
 if __name__ == "__main__":