Update sentiment_tools.py

sentiment_tools.py

@@ -1,45 +1,47 @@
-from langchain.tools import tool
-from transformers import pipeline
+# sentiment_tools.py - CrewAI Native Version
+from crewai.tools import BaseTool
+from typing import Type
+from pydantic import BaseModel, Field
 
-from langchain.tools import tool
+class SentimentInput(BaseModel):
+    """Input schema for SentimentTool."""
+    text: str = Field(..., description="Text to analyze for sentiment")
 
-@tool("Analyze Sentiment")
-def analyze_sentiment(text: str) -> str:
-    """Analyzes the sentiment of a given text using simple keyword analysis."""
-    try:
-        # Simple sentiment analysis without heavy models for faster execution
-        text_lower = text.lower()
-        
-        # Positive indicators
-        positive_words = [
-            'bull', 'bullish', 'up', 'rise', 'rising', 'gain', 'gains', 
-            'positive', 'strong', 'growth', 'increase', 'rally', 'surge',
-            'optimistic', 'good', 'great', 'excellent', 'buy', 'moon'
-        ]
-        
-        # Negative indicators  
-        negative_words = [
-            'bear', 'bearish', 'down', 'fall', 'falling', 'loss', 'losses',
-            'negative', 'weak', 'decline', 'decrease', 'crash', 'dump',
-            'pessimistic', 'bad', 'poor', 'terrible', 'sell', 'fear'
-        ]
-        
-        positive_count = sum(1 for word in positive_words if word in text_lower)
-        negative_count = sum(1 for word in negative_words if word in text_lower)
-        
-        if positive_count > negative_count:
-            confidence = min(0.9, 0.6 + (positive_count - negative_count) * 0.1)
-            return f"Positive (confidence: {confidence:.1f})"
-        elif negative_count > positive_count:
-            confidence = min(0.9, 0.6 + (negative_count - positive_count) * 0.1)
-            return f"Negative (confidence: {confidence:.1f})"
-        else:
-            return "Neutral (confidence: 0.5)"
-            
-    except Exception as e:
-        return f"Sentiment analysis error: {str(e)}"
+class SentimentTool(BaseTool):
+    name: str = "Analyze Sentiment"
+    description: str = "Analyzes the sentiment of a given text using keyword analysis"
+    args_schema: Type[BaseModel] = SentimentInput
 
-class SentimentTools:
-    """Container class for sentiment tools - for backward compatibility"""
-    def __init__(self):
-        self.analyze_sentiment = analyze_sentiment
+    def _run(self, text: str) -> str:
+        try:
+            # Simple sentiment analysis without heavy models for faster execution
+            text_lower = text.lower()
+            
+            # Positive indicators
+            positive_words = [
+                'bull', 'bullish', 'up', 'rise', 'rising', 'gain', 'gains', 
+                'positive', 'strong', 'growth', 'increase', 'rally', 'surge',
+                'optimistic', 'good', 'great', 'excellent', 'buy', 'moon'
+            ]
+            
+            # Negative indicators  
+            negative_words = [
+                'bear', 'bearish', 'down', 'fall', 'falling', 'loss', 'losses',
+                'negative', 'weak', 'decline', 'decrease', 'crash', 'dump',
+                'pessimistic', 'bad', 'poor', 'terrible', 'sell', 'fear'
+            ]
+            
+            positive_count = sum(1 for word in positive_words if word in text_lower)
+            negative_count = sum(1 for word in negative_words if word in text_lower)
+            
+            if positive_count > negative_count:
+                confidence = min(0.9, 0.6 + (positive_count - negative_count) * 0.1)
+                return f"Positive (confidence: {confidence:.1f})"
+            elif negative_count > positive_count:
+                confidence = min(0.9, 0.6 + (negative_count - positive_count) * 0.1)
+                return f"Negative (confidence: {confidence:.1f})"
+            else:
+                return "Neutral (confidence: 0.5)"
+                
+        except Exception as e:
+            return f"Sentiment analysis error: {str(e)}"