from flask import Flask, request, jsonify, render_template
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline

# Load the fine-tuned model
model_path = "./gpt2_finetuned"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path)

# Create a Flask app
app = Flask(__name__)

# Define a route for the chat API
@app.route("/chat", methods=["POST"])
def chat():
    data = request.json
    user_input = data.get("message", "")
    if not user_input:
        return jsonify({"error": "No input provided"}), 400

    # Generate a response
    generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
    response = generator(user_input, max_length=100, num_return_sequences=1, temperature=0.7)
    bot_reply = response[0]["generated_text"]

    return jsonify({"reply": bot_reply})

# Serve the chat interface
@app.route("/")
def index():
    return render_template("index.html")

if __name__ == "__main__":
    app.run(debug=True)