app.py

from fastapi import FastAPI
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import torch

## Create FastAPI app instance
app = FastAPI()

# Initialize a text generation pipeline
# Load model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("google/flan-t5-small")
model = AutoModelForSeq2SeqLM.from_pretrained("google/flan-t5-small")

# Check for GPU availability
device = 0 if torch.cuda.is_available() else -1

@app.get("/")
def home():
    return {"message": "Welcome to the Text Generation API!"}

#Define a function to handle the GET request at /generate 
@app.get("/generate")
def generate(text: str):
    ## Generate text using the model
    input_ids = tokenizer(text, return_tensors="pt").input_ids
    outputs = model.generate(input_ids, max_length=100)
    output_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
    
    ##return the text generated in Json response
    return {"output": output_text}