import torch
import torch.nn as nn
from torch.nn import functional as F
import gradio as gr  # <--- The new UI library

# --- 1. CONFIGURATION (Must match training!) ---
batch_size = 64
block_size = 64
n_embd = 128
n_head = 4
n_layer = 4
dropout = 0.2
device = 'cpu'  # We use CPU for the web app so it's compatible everywhere

# --- 2. THE BRAIN CODE (Your Custom Architecture) ---
class Head(nn.Module):
    def __init__(self, head_size):
        super().__init__()
        self.key = nn.Linear(n_embd, head_size, bias=False)
        self.query = nn.Linear(n_embd, head_size, bias=False)
        self.value = nn.Linear(n_embd, head_size, bias=False)
        self.register_buffer('tril', torch.tril(torch.ones(block_size, block_size)))
        self.dropout = nn.Dropout(dropout)
    def forward(self, x):
        B,T,C = x.shape
        k = self.key(x)
        q = self.query(x)
        wei = q @ k.transpose(-2, -1) * C**-0.5
        wei = wei.masked_fill(self.tril[:T, :T] == 0, float('-inf'))
        wei = F.softmax(wei, dim=-1)
        wei = self.dropout(wei)
        v = self.value(x)
        out = wei @ v
        return out

class MultiHeadAttention(nn.Module):
    def __init__(self, num_heads, head_size):
        super().__init__()
        self.heads = nn.ModuleList([Head(head_size) for _ in range(num_heads)])
        self.proj = nn.Linear(n_embd, n_embd)
        self.dropout = nn.Dropout(dropout)
    def forward(self, x):
        out = torch.cat([h(x) for h in self.heads], dim=-1)
        out = self.proj(out)
        return self.dropout(out)

class FeedFoward(nn.Module):
    def __init__(self, n_embd):
        super().__init__()
        self.net = nn.Sequential(
            nn.Linear(n_embd, 4 * n_embd),
            nn.ReLU(),
            nn.Linear(4 * n_embd, n_embd),
            nn.Dropout(dropout),
        )
    def forward(self, x):
        return self.net(x)

class Block(nn.Module):
    def __init__(self, n_embd, n_head):
        super().__init__()
        head_size = n_embd // n_head
        self.sa = MultiHeadAttention(n_head, head_size)
        self.ffwd = FeedFoward(n_embd)
        self.ln1 = nn.LayerNorm(n_embd)
        self.ln2 = nn.LayerNorm(n_embd)
    def forward(self, x):
        x = x + self.sa(self.ln1(x))
        x = x + self.ffwd(self.ln2(x))
        return x

class GPTLanguageModel(nn.Module):
    def __init__(self, vocab_size):
        super().__init__()
        self.token_embedding_table = nn.Embedding(vocab_size, n_embd)
        self.position_embedding_table = nn.Embedding(block_size, n_embd)
        self.blocks = nn.Sequential(*[Block(n_embd, n_head=n_head) for _ in range(n_layer)])
        self.ln_f = nn.LayerNorm(n_embd)
        self.lm_head = nn.Linear(n_embd, vocab_size)
    def forward(self, idx, targets=None):
        B, T = idx.shape
        tok_emb = self.token_embedding_table(idx)
        pos_emb = self.position_embedding_table(torch.arange(T, device=device))
        x = tok_emb + pos_emb
        x = self.blocks(x)
        x = self.ln_f(x)
        logits = self.lm_head(x)
        return logits, None
    def generate(self, idx, max_new_tokens):
        for _ in range(max_new_tokens):
            idx_cond = idx[:, -block_size:]
            logits, _ = self(idx_cond)
            logits = logits[:, -1, :]
            probs = F.softmax(logits, dim=-1)
            idx_next = torch.multinomial(probs, num_samples=1)
            idx = torch.cat((idx, idx_next), dim=1)
        return idx

# --- 3. LOAD RESOURCES ---
print("Loading model and vocabulary...")
# Load text to rebuild tokenizer
with open('input.txt', 'r', encoding='utf-8') as f:
    text = f.read()
chars = sorted(list(set(text)))
vocab_size = len(chars)
stoi = { ch:i for i,ch in enumerate(chars) }
itos = { i:ch for i,ch in enumerate(chars) }
encode = lambda s: [stoi[c] for c in s]
decode = lambda l: ''.join([itos[i] for i in l])

# Load Model
model = GPTLanguageModel(vocab_size)
model.load_state_dict(torch.load('model.pt', map_location=device))
model.to(device)
model.eval()

# --- 4. DEFINE THE WEB FUNCTION ---
def generate_text(start_text):
    if not start_text:
        return "Please type something to start!"
    
    try:
        # Convert text to numbers
        context = torch.tensor([encode(start_text)], dtype=torch.long, device=device)
        
        # Ask AI to predict next 200 characters
        output_ids = model.generate(context, max_new_tokens=200)
        
        # Convert numbers back to text
        full_response = decode(output_ids[0].tolist())
        return full_response
    except KeyError:
        return "Error: You used a character the AI has never seen before."

# --- 5. LAUNCH THE INTERFACE ---
print("Launching Web App...")
interface = gr.Interface(
    fn=generate_text,
    inputs=gr.Textbox(lines=2, placeholder="Type a starting word (e.g. 'Nano')..."),
    outputs="text",
    title="My Private AI",
    description="An AI model trained from scratch on my own data."
)

interface.launch()