Update app.py

app.py

@@ -24,10 +24,10 @@ DELAY_REASONS = {
 }
 
 def load_video(video_data, strategy='chat'):
+    """Loads and processes video data into a format suitable for model input."""
     bridge.set_bridge('torch')
     num_frames = 24
     
-   
     if isinstance(video_data, str): 
         decord_vr = VideoReader(video_data, ctx=cpu(0))
     else:  
@@ -50,6 +50,7 @@ def load_video(video_data, strategy='chat'):
     return video_data
 
 def load_model():
+    """Loads the pre-trained model and tokenizer with quantization configurations."""
     quantization_config = BitsAndBytesConfig(
         load_in_4bit=True,
         bnb_4bit_compute_dtype=TORCH_TYPE,
@@ -69,6 +70,7 @@ def load_model():
     return model, tokenizer
 
 def predict(prompt, video_data, temperature, model, tokenizer):
+    """Generates predictions based on the video and textual prompt."""
     video = load_video(video_data, strategy='chat')
     
     inputs = model.build_conversation_input_ids(
@@ -103,6 +105,7 @@ def predict(prompt, video_data, temperature, model, tokenizer):
     return response
 
 def get_analysis_prompt(step_number, possible_reasons):
+    """Constructs the prompt for analyzing delay reasons based on the selected step."""
     return f"""You are an AI expert system specialized in analyzing manufacturing processes and identifying production delays in tire manufacturing. Your role is to accurately classify delay reasons based on visual evidence from production line footage.
 Task Context:
 You are analyzing video footage from Step {step_number} of a tire manufacturing process where a delay has been detected. Your task is to determine the most likely cause of the delay from the following possible reasons:
@@ -122,17 +125,13 @@ Important: Base your analysis solely on visual evidence from the video. Focus on
 model, tokenizer = load_model()
 
 def inference(video, step_number):
+    """Analyzes video to predict the most likely cause of delay in the selected manufacturing step."""
     try:
         if not video:
             return "Please upload a video first."
         
-        # Get possible reasons for the selected step
         possible_reasons = DELAY_REASONS[step_number]
-        
-        # Generate the analysis prompt
         prompt = get_analysis_prompt(step_number, possible_reasons)
-        
-        # Get model prediction
         temperature = 0.8
         response = predict(prompt, video, temperature, model, tokenizer)
         
@@ -140,8 +139,8 @@ def inference(video, step_number):
     except Exception as e:
         return f"An error occurred during analysis: {str(e)}"
 
-# Gradio Interface
 def create_interface():
+    """Creates the Gradio interface for the Manufacturing Delay Analysis System."""
     with gr.Blocks() as demo:
         gr.Markdown("""
         # Manufacturing Delay Analysis System
@@ -151,18 +150,17 @@ def create_interface():
         
         with gr.Row():
             with gr.Column():
-                video = gr.Video(label="Upload Manufacturing Video", sources=["upload"])
+                video = gr.Video(label="Upload Manufacturing Video", sources=["upload"], value="delay_tyre.mp4")
                 step_number = gr.Dropdown(
                     choices=list(DELAY_REASONS.keys()),
                     label="Manufacturing Step",
-                    value="Step 1"
+                    value="Step 8"
                 )
                 analyze_btn = gr.Button("Analyze Delay", variant="primary")
             
             with gr.Column():
                 output = gr.Textbox(label="Analysis Result", lines=10)
         
-        # Trigger analysis when button is clicked
         analyze_btn.click(
             fn=inference,
             inputs=[video, step_number],
@@ -173,4 +171,4 @@ def create_interface():
 
 if __name__ == "__main__":
     demo = create_interface()
-    demo.launch(share=True)  # Added share=True to create a public link
+    demo.launch(share=True)