fix: using pipeline

app.py

@@ -1,7 +1,7 @@
 from fastapi import FastAPI
 from fastapi.middleware.cors import CORSMiddleware
 from pydantic import BaseModel
-from transformers import AutoTokenizer, AutoModelForSequenceClassification
+from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
 import torch
 
 # Inisialisasi model dan tokenizer
@@ -26,17 +26,18 @@ class TextInput(BaseModel):
 
 # Fungsi untuk analisis sentimen
 def predict_sentiment(text):
-    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
-    outputs = model(**inputs)
-    scores = outputs.logits[0].detach().numpy()
-    predictions = torch.nn.functional.softmax(torch.tensor(scores), dim=0)
-    sentiment = torch.argmax(predictions).item()
-    
-    # Map sentiment to label
-    labels = ["positive", "negative", "neutral"]
-    sentiment_label = labels[sentiment]
-    
-    return sentiment_label, predictions[sentiment].item()
+    nlp = pipeline(
+        "sentiment-analysis",
+        model=model_name,
+        tokenizer=model_name
+    )
+
+    result = nlp(text)[0]
+    sentiment = result['label']
+    confidence = result['score']
+    return sentiment, confidence
+
+
 
 # Endpoint untuk analisis sentimen
 @app.post("/predict")