app.py

import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer
from memory import update_memory, check_memory

# Load persona instructions
with open("persona.txt", "r", encoding="utf-8") as f:
    personality = f.read()

# Load fine-tuned model
model_name = "./MoinRomanticBot-Lora"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Function to generate response with memory
def chatbot(input_text):
    # Pehle check karo ki memory me pehle se koi response hai ya nahi
    memory_response = check_memory(input_text)
    if memory_response:
        return memory_response
    
    # Naya response generate karna
    prompt = f"{personality}\nMoin: {input_text}\nAI:"
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(**inputs, max_length=150)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    
    # Memory me store karna
    update_memory(input_text, response)
    
    return response

# Gradio interface
iface = gr.Interface(fn=chatbot, inputs="text", outputs="text", title="MoinRomanticBot")

# Launch app
if __name__ == "__main__":
    iface.launch(server_name="0.0.0.0", server_port=7860)