Update sentiment_analysis.py

Upgrade to smolagents.
Based on: https://huggingface.co/docs/smolagents/tutorials/tools

sentiment_analysis.py

@@ -1,13 +1,18 @@
 import gradio as gr
 from transformers import pipeline
-from transformers import Tool
+from smolagents import Tool
 
 class SentimentAnalysisTool(Tool):
     name = "sentiment_analysis"
     description = "This tool analyses the sentiment of a given text."
 
-    inputs = {"text": {"type": "text", "description": "The text to analyze"}}
-    outputs = {"json": {"type": "json", "description": "Sentiment analysis results"}}
+    inputs = {
+        "text": {
+            "type": "string",
+            "description": "The text to analyze for sentiment"
+        }
+    }
+    output_type = "list"
     
     # Available sentiment analysis models
     models = {
@@ -22,16 +27,17 @@ class SentimentAnalysisTool(Tool):
     
     def __init__(self, default_model="distilbert"):
         """Initialize with a default model."""
+        super().__init__()
         self.default_model = default_model
         # Pre-load the default model to speed up first inference
         self._classifiers = {}
-        self.get_classifier(self.models[default_model])
+        self._get_classifier(self.models[default_model])
     
-    def __call__(self, text: str): 
+    def forward(self, text: str): 
         """Process input text and return sentiment predictions."""
         return self.predict(text)
         
-    def parse_output(self, output_json):  
+    def _parse_output(self, output_json):  
         """Parse model output into a list of (label, score) tuples."""
         list_pred = []
         for i in range(len(output_json[0])):
@@ -40,23 +46,23 @@ class SentimentAnalysisTool(Tool):
             list_pred.append((label, score))
         return list_pred
     
-    def get_classifier(self, model_id):
+    def _get_classifier(self, model_id):
         """Get or create a classifier for the given model ID."""
         if model_id not in self._classifiers:
             self._classifiers[model_id] = pipeline(
                 "text-classification", 
                 model=model_id, 
-                return_all_scores=True
+                top_k=None  # This replaces return_all_scores=True
             )
         return self._classifiers[model_id]
     
     def predict(self, text, model_key=None):
         """Make predictions using the specified or default model."""
         model_id = self.models[model_key] if model_key in self.models else self.models[self.default_model]
-        classifier = self.get_classifier(model_id)
+        classifier = self._get_classifier(model_id)
         
         prediction = classifier(text)
-        return self.parse_output(prediction)
+        return self._parse_output(prediction)
 
 # For standalone testing
 if __name__ == "__main__":