import gradio as gr
from huggingface_hub import InferenceClient
from datetime import datetime
import os
import uuid

# ---- System Prompt ----
with open("system_prompt.txt", "r") as f:
    SYSTEM_PROMPT = f.read()

MODEL_NAME = "HuggingFaceH4/zephyr-7b-beta"
client = InferenceClient(MODEL_NAME)

# ---- Setup logging ----
LOG_DIR = "chat_logs"
os.makedirs(LOG_DIR, exist_ok=True)
session_id = str(uuid.uuid4())

def log_chat(session_id, user_msg, bot_msg):
    timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
    log_path = os.path.join(LOG_DIR, f"{session_id}.txt")
    with open(log_path, "a", encoding="utf-8") as f:
        f.write(f"[{timestamp}] User: {user_msg}\n")
        f.write(f"[{timestamp}] Bot: {bot_msg}\n\n")

# ---- Respond Function with Logging ----
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 chunk in client.chat_completion(
        messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        token = chunk.choices[0].delta.content
        if token:
            response += token
            yield response

    # Save full message after stream ends
    log_chat(session_id, message, response)

# ---- Gradio Interface ----
demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value=SYSTEM_PROMPT, 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)"),
    ],
    title="BoundrAI"
)

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