import torch
import torch.nn as nn
import torch.nn.functional as F
from typing import Optional, Tuple

# Multi-Head Attention Mechanism
class MultiHeadAttention(nn.Module):
    def __init__(self, d_model: int, num_heads: int, dropout: float = 0.1):
        super().__init__()
        assert d_model % num_heads == 0

        self.d_model = d_model
        self.num_heads = num_heads
        self.head_dim = d_model // num_heads

        self.q_proj = nn.Linear(d_model, d_model)
        self.k_proj = nn.Linear(d_model, d_model)
        self.v_proj = nn.Linear(d_model, d_model)
        self.o_proj = nn.Linear(d_model, d_model)

        self.dropout = nn.Dropout(dropout)

    def forward(self, x: torch.Tensor, mask: Optional[torch.Tensor] = None) -> torch.Tensor:
        batch_size, seq_len, d_model = x.shape
        
        # Project and reshape for multi-head attention
        q = self.q_proj(x).reshape(batch_size, seq_len, self.num_heads, self.head_dim)
        k = self.k_proj(x).reshape(batch_size, seq_len, self.num_heads, self.head_dim)
        v = self.v_proj(x).reshape(batch_size, seq_len, self.num_heads, self.head_dim)

        # Transpose for attention computation
        q, k, v = q.transpose(1, 2), k.transpose(1, 2), v.transpose(1, 2)

        # Compute attention scores
        scores = torch.matmul(q, k.transpose(-2, -1)) / math.sqrt(self.head_dim)
        if mask is not None:
            scores = scores.masked_fill(mask == 0, float('-inf'))
        
        attn_weights = F.softmax(scores, dim=-1)
        attn_weights = self.dropout(attn_weights)
        
        # Apply attention to values
        out = torch.matmul(attn_weights, v).transpose(1, 2).reshape(batch_size, seq_len, d_model)
        return self.o_proj(out)