import torch
import torch.nn as nn
import torch.nn.functional as F
import gradio as gr
from huggingface_hub import InferenceClient
from llama_cpp import Llama
import spaces

# Initialize the InferenceClient
client = InferenceClient()

llm = Llama.from_pretrained(
    repo_id="bartowski/perplexity-ai_r1-1776-distill-llama-70b-GGUF",
    filename="perplexity-ai_r1-1776-distill-llama-70b-IQ4_NL.gguf",
)

# Fixed system message
SYSTEM_MESSAGE = """You are H, an artificial reasoning inteligence(AIR) created by the ACC(Algorithmic Computer-generated Consciousness).
"""

# RNN Model
class RNNModel(nn.Module):
    def __init__(self, input_size, hidden_size, output_size, num_layers=1):
        super(RNNModel, self).__init__()
        self.rnn = nn.RNN(input_size, hidden_size, num_layers, batch_first=True)
        self.fc = nn.Linear(hidden_size, output_size)

    def forward(self, x):
        h0 = torch.zeros(1, x.size(0), self.rnn.hidden_size).to(x.device)
        out, _ = self.rnn(x, h0)
        out = self.fc(out[:, -1, :])  # Get the last output
        return out

# CNN Model
class CNNModel(nn.Module):
    def __init__(self, num_classes):
        super(CNNModel, self).__init__()
        self.conv1 = nn.Conv2d(3, 16, kernel_size=3, stride=1, padding=1)
        self.pool = nn.MaxPool2d(kernel_size=2, stride=2, padding=0)
        self.conv2 = nn.Conv2d(16, 32, kernel_size=3, stride=1, padding=1)
        self.fc1 = nn.Linear(32 * 8 * 8, 128)
        self.fc2 = nn.Linear(128, num_classes)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 32 * 8 * 8)  # Flatten
        x = F.relu(self.fc1(x))
        x = self.fc2(x)
        return x

# NN Model (Feedforward Neural Network)
class NNModel(nn.Module):
    def __init__(self, input_size, hidden_size, output_size):
        super(NNModel, self).__init__()
        self.fc1 = nn.Linear(input_size, hidden_size)
        self.fc2 = nn.Linear(hidden_size, output_size)

    def forward(self, x):
        x = F.relu(self.fc1(x))
        x = self.fc2(x)
        return x

# PHI Model (Example: Softmax-Based Regression)
class PHIModel(nn.Module):
    def __init__(self, input_size, output_size):
        super(PHIModel, self).__init__()
        self.fc = nn.Linear(input_size, output_size)
        self.softmax = nn.Softmax(dim=1)

    def forward(self, x):
        x = self.fc(x)
        x = self.softmax(x)
        return x

# Chatbot Response Logic

def respond(
    message,
    history: list[tuple[str, str]],
    max_tokens,
    temperature,
    top_p,
):
    # Use fixed system message
    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 = ""

    # Use the client to get the chat completion
    for message in client.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

# Gradio Chat Interface with Models
demo = gr.ChatInterface(
    fn=respond,
    type="messages",
    chatbot=gr.Chatbot(
        type="messages",
        label="🟢H🟢", 
        placeholder="🟢-Hi, I'm H-🟢", 
    ),
    additional_inputs=[
        gr.Slider(minimum=1, maximum=2048, value=2048, step=1, label="📏Maximum Response Length📏"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.3, step=0.1, label="👨‍🎨🎨Creativity🎨👨‍🎨"),
        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="🧠⚡️Neural Activity⚡️🧠")
    ],
    theme=gr.themes.Ocean()
)

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