import torch
import torch.nn as nn
from transformers import AutoTokenizer, AutoModel
import gradio as gr

# Model multitask (Topik & Sentimen) dengan nama layer sesuai model.pt
class MultiTaskModel(nn.Module):
    def __init__(self, base_model_name, num_topic_classes, num_sentiment_classes):
        super(MultiTaskModel, self).__init__()
        self.encoder = AutoModel.from_pretrained(base_model_name)
        hidden_size = self.encoder.config.hidden_size
        self.topik_classifier = nn.Linear(hidden_size, num_topic_classes)
        self.sentiment_classifier = nn.Linear(hidden_size, num_sentiment_classes)

    def forward(self, input_ids, attention_mask, token_type_ids=None):
    outputs = self.encoder(
        input_ids=input_ids,
        attention_mask=attention_mask,
        token_type_ids=token_type_ids
    )
    pooled_output = outputs.last_hidden_state[:, 0]
    topik_logits = self.topik_classifier(pooled_output)
    sentimen_logits = self.sentiment_classifier(pooled_output)
    return topik_logits, sentimen_logits


# Load tokenizer & model
tokenizer = AutoTokenizer.from_pretrained("tokenizer")
model = MultiTaskModel("indobenchmark/indobert-base-p1", num_topic_classes=5, num_sentiment_classes=3)
model.load_state_dict(torch.load("model.pt", map_location=torch.device("cpu")))
model.eval()

# Label mapping
topik_labels = ["Produk", "Layanan", "Pengiriman", "Lainnya"]
sentimen_labels = ["Negatif", "Netral", "Positif"]

def klasifikasi(text):
    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
    with torch.no_grad():
        topik_logits, sentimen_logits = model(**inputs)
        topik_probs = torch.softmax(topik_logits, dim=-1).squeeze()
        sentimen_probs = torch.softmax(sentimen_logits, dim=-1).squeeze()

    topik_result = {label: float(prob) for label, prob in zip(topik_labels, topik_probs)}
    sentimen_result = {label: float(prob) for label, prob in zip(sentimen_labels, sentimen_probs)}
    return {"Topik": topik_result, "Sentimen": sentimen_result}

demo = gr.Interface(fn=klasifikasi, inputs="text", outputs="json", title="Klasifikasi Topik dan Sentimen Pelanggan")
demo.launch()