using distilbert-base-uncased

app.py

@@ -19,10 +19,10 @@ def anomalies_detector(logs: str) -> list[tuple[int, str]]:
     Returns:
         list[tuple[int, str]]: List of tuples containing (line_number, anomalous_text)
     """
-    # Initialize the text classification pipeline with a model specialized in text classification
+    # Initialize the text classification pipeline with a smaller, more reliable model
     classifier = pipeline(
         "text-classification",
-        model="distilbert-base-uncased-finetuned-sst-2-english",  # Using a model fine-tuned for sentiment/classification
+        model="distilbert-base-uncased",  # Using a smaller, more reliable model
         top_k=2  # Get both normal and anomalous probabilities
     )
     
@@ -41,7 +41,7 @@ def anomalies_detector(logs: str) -> list[tuple[int, str]]:
         # Check if the line is classified as anomalous
         # The model returns probabilities for both classes
         for result in results:
-            if result['label'] == 'NEGATIVE' and result['score'] > 0.7:  # NEGATIVE indicates potential anomaly
+            if result['label'] == 'LABEL_1' and result['score'] > 0.7:  # LABEL_1 indicates potential anomaly
                 anomalies.append((line_num, line))
                 break
     
@@ -53,7 +53,7 @@ demo = gr.Interface(
     inputs="textbox",
     outputs="text",
     title="Log Anomaly Detector",
-    description="Enter log entries to detect anomalous patterns using AI. The system will identify unusual patterns, errors, and potential issues in your logs."
+    description="Enter log entries to detect anomalous patterns using BERT Model. The system will identify unusual patterns, errors, and potential issues in your logs."
 )
 
 # Launch both the Gradio web interface and the MCP server