app.py

from io import BytesIO
from flask import Flask, jsonify, request
from transformers import GPT2Tokenizer, GPT2LMHeadModel

# Load the fine-tuned model and tokenizer
model_path = "gpt2"
tokenizer = GPT2Tokenizer.from_pretrained(model_path)
model = GPT2LMHeadModel.from_pretrained(model_path)


def infer_title(input):
    input_text = "Q: " + input + " A:"
    input_ids = tokenizer.encode(input_text, return_tensors='pt')
    output = model.generate(input_ids, max_length=50, num_return_sequences=1)
    response = tokenizer.decode(output[0], skip_special_tokens=True)
    return response

app = Flask(__name__)


@app.route("/")
def endpoint():
    input = request.args.get("input")

    output = infer_title(input)

    return jsonify({"output": output})


if __name__ == "__main__":
    app.run(host="0.0.0.0", port=7860)