app.py

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

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

model_name = "TheBloke/Pygmalion-7B-GPTQ"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", trust_remote_code=True)

generator = pipeline("text-generation", model=model, tokenizer=tokenizer)

def chatbot(input_text):
    memory_response = check_memory(input_text)
    if memory_response:
        return memory_response

    prompt = f"{personality}\nUser: {input_text}\nAI:"
    outputs = generator(prompt, max_length=200, do_sample=True, temperature=0.7, top_p=0.9)
    response = outputs[0]["generated_text"].split("AI:")[-1].strip()

    update_memory(input_text, response)
    return response

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

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