Fixing errors

gradio_app.py

@@ -1,45 +1,14 @@
 import gradio as gr
 from model.analyzer import analyze_content
-import time  # For simulating the loading bar
 
-# Define the analysis function with a simulated loading bar
-def analyze_with_loading(script):
-    for progress in range(0, 101, 20):
-        time.sleep(0.3)  # Simulate processing delay
-        yield gr.update(value=f"Analyzing... {progress}%")
-    # Final result after analysis
-    result = analyze_content(script)
-    yield gr.update(value=f"Analysis Complete! Triggers Detected: {result['detected_triggers']}")
+# Create and launch the Gradio interface
+iface = gr.Interface(
+    fn=analyze_content,
+    inputs=gr.Textbox(lines=8, label="Input Text"),
+    outputs=gr.JSON(),
+    title="Content Analysis",
+    description="Analyze text content for sensitive topics"
+)
 
-# Create the Gradio interface
-# Create the Gradio interface
-with gr.Blocks(css=".center-text {text-align: center;} .gradient-bg {background: linear-gradient(135deg, #ff9a9e, #fad0c4);}") as iface:
-    # Header with centered text
-    gr.Markdown(
-        """
-        <div class="center-text">
-            <h1><b>TREAT</b></h1>
-            <h3><b>Trigger Recognition for Enjoyable and Appropriate Television</b></h3>
-        </div>
-        """,
-        elem_classes="gradient-bg"
-    )
-    
-    # Input Section
-    script_input = gr.Textbox(lines=8, label="Input Text", placeholder="Paste your script here...")
-    analyze_button = gr.Button("Analyze Content")
-    
-    # Loading Bar and Results
-    loading_bar = gr.Textbox(label="Progress", interactive=False)
-    results_output = gr.JSON(label="Results")
-    
-    # Connect the button to the function
-    analyze_button.click(
-        fn=analyze_with_loading,
-        inputs=script_input,
-        outputs=[loading_bar, results_output],
-    )
-
-# Launch the app
 if __name__ == "__main__":
     iface.launch()

model/analyzer.py

@@ -25,7 +25,7 @@ def analyze_script(script):
         # Load model with token authentication
         model = AutoModelForCausalLM.from_pretrained(
             "meta-llama/Llama-3.2-1B",
-            use_auth_token=hf_token,  # Pass the token to authenticate
+            token=hf_token,  # Pass the token to authenticate
             torch_dtype=torch.float16 if device == "cuda" else torch.float32,  # Use 16-bit precision for CUDA, 32-bit for CPU
             device_map="auto"  # Automatically map model to available device
         )
@@ -188,11 +188,12 @@ def analyze_script(script):
 
     return final_triggers
 
+# Define the Gradio interface
 def analyze_content(script):
-    # Simulate trigger analysis (you can replace this with your actual logic)
+    # Perform the analysis on the input script using the analyze_script function
     triggers = analyze_script(script)
-    
-    # Define the result based on triggers found
+
+    # Define the result based on the triggers found
     if isinstance(triggers, list) and triggers != ["None"]:
         result = {
             "detected_triggers": triggers,
@@ -207,7 +208,7 @@ def analyze_content(script):
             "model": "Llama-3.2-1B",
             "analysis_timestamp": datetime.now().strftime("%Y-%m-%d %H:%M:%S")
         }
-    
+
     print("\nFinal Result Dictionary:", result)
     return result
 
@@ -221,4 +222,4 @@ iface = gr.Interface(
 )
 
 if __name__ == "__main__":
-    iface.launch()
+    iface.launch()