import gradio as gr
from huggingface_hub import InferenceClient
import spaces
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
from transformers import pipeline

#pipe = pipeline("text-generation", model="microsoft/Phi-3-mini-128k-instruct", trust_remote_code=True)

#client = InferenceClient("microsoft/Phi-3-mini-128k-instruct")
#client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
#client = InferenceClient("google/gemma-1.1-7b-it")
pipe = pipeline("text-generation", model="Qwen/Qwen2-1.5B-Instruct")

@spaces.GPU
def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    messages = [{"role": "system", "content": system_message}]

    for val in history:
        if val[0]:
            messages.append({"role": "user", "content": val[0]})
        if val[1]:
            messages.append({"role": "assistant", "content": val[1]})

    messages.append({"role": "user", "content": message})

    response = ""

    for message in pipe.chat_completion(
        messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        token = message.choices[0].delta.content

        response += token
        yield response


demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are a cybersecurity analyst who can interpret different types of logs resulting from various cyberattacks such as phishing attacks, malware attacks, advanced persistent threats, denial-of-service (DoS) and distributed denial-of-service (DDoS) attacks, man-in-the-middle (MitM) attacks, SQL injection attacks, and zero-day exploits. Using logs such as login failures, event logs, firewall logs, and brute force logs, analyze the data and respond in English with your interpretation of the analysis.",
                   label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
        gr.Slider(
            minimum=0.1,
            maximum=1.0,
            value=0.95,
            step=0.05,
            label="Top-p (nucleus sampling)",
        ),
    ],
)


if __name__ == "__main__":
    demo.launch()