Update app.py

app.py

@@ -1,62 +1,43 @@
 import gradio as gr
-from transformers import pipeline, AutoModelForSequenceClassification, AutoTokenizer
+from transformers import pipeline
 
-# Model name
-model_name = "ElKulako/cryptobert"
-
-# Load model and tokenizer explicitly
-try:
-    model = AutoModelForSequenceClassification.from_pretrained(model_name)
-    tokenizer = AutoTokenizer.from_pretrained(model_name)
-
-    # Load sentiment pipeline
-    sentiment_pipeline = pipeline(
-        "text-classification",
-        model=model,
-        tokenizer=tokenizer
-    )
-except Exception as e:
-    print(f"Error loading model: {e}")
-    exit(1)
+# Load a crypto-specific sentiment model (e.g., ElKulako/cryptobert)
+sentiment_pipeline = pipeline(
+    "text-classification",
+    model="ElKulako/cryptobert",  # Pre-trained on crypto data
+    tokenizer="ElKulako/cryptobert"
+)
 
-# Sentiment analysis function with keyword overrides
 def analyze(text):
-    if not text or text.strip() == "":
-        return {"error": "No text provided."}
-
-    try:
-        # Get model's prediction
-        result = sentiment_pipeline(text)[0]
+    # Get the model's initial prediction
+    result = sentiment_pipeline(text)[0]
+    
+    # Override logic for crypto-specific keywords (case-insensitive)
+    text_lower = text.lower()
+    
+    # Force "positive" for bullish terms
+    bullish_keywords = ["etf approved", "bullish", "halving", "burn", "greenlighted"]
+    if any(keyword in text_lower for keyword in bullish_keywords):
+        return {"label": "positive", "score": 0.99}
         
-        # Override logic for crypto-related keywords (case-insensitive)
-        text_lower = text.lower()
-        
-        # Force "positive" for bullish terms
-        bullish_keywords = ["etf approved", "bullish", "halving", "burn", "greenlighted"]
-        if any(keyword in text_lower for keyword in bullish_keywords):
-            return {"label": "positive", "score": 0.99}
-            
-        # Force "negative" for bearish terms
-        bearish_keywords = ["sec lawsuit", "hack", "fud", "sell-off", "delist"]
-        if any(keyword in text_lower for keyword in bearish_keywords):
-            return {"label": "negative", "score": 0.99}
-        
-        # Return original prediction if no keywords matched
-        return {"label": result["label"], "score": result["score"]}
-
-    except Exception as e:
-        return {"error": str(e)}
+    # Force "negative" for bearish terms
+    bearish_keywords = ["sec lawsuit", "hack", "fud", "sell-off", "delist"]
+    if any(keyword in text_lower for keyword in bearish_keywords):
+        return {"label": "negative", "score": 0.99}
+    
+    # Return original prediction if no keywords matched
+    return {"label": result["label"], "score": result["score"]}
 
 # Configure Gradio interface for API compatibility
-gr.Interface(
+app = gr.Interface(
     fn=analyze,
     inputs=gr.Textbox(placeholder="Enter crypto news headline..."),
-    outputs=gr.JSON(),
-    title="Crypto Sentiment Analysis",
-    description="Analyzes sentiment of crypto-related news headlines.",
-    flagging_mode="never"  # Fixed deprecated warning
-).launch(
-    server_name="0.0.0.0",
-    server_port=7860
+    outputs=gr.JSON(),  # JSON output for n8n integration
+    title="Crypto-Specific Sentiment Analysis",
+    description="Analyzes sentiment of crypto news headlines. Overrides neutral predictions for key terms like 'ETF approved' or 'SEC lawsuit'.",
+    flagging_mode="never"
 )
 
+# Enable sharing and API
+app.launch(share=True, api_name="predict")
+