Update app.py

app.py

@@ -111,24 +111,6 @@ 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:
 {', '.join(possible_reasons)}
 Required Analysis:
-
-Analyze the delay in movement of the following objects from the provided manufacturing video:
-    
-1. **h_stock_left**: Identified by contours with the color **Green**.
-2. **h_stock_right**: Identified by contours with the color **Pink**.
-3. **compressor_metal**: Identified by contours with the color **Orange**.
-4. **conveyor2**: Identified by contours with the color **Blue**.
-5. **white_down_roller_left**: Identified by contours with the color **White**.
-6. **conveyor1**: Identified by contours with the color **Brown**.
-Steps for analysis:
-- Extract the contours for each specified color.
-- Track the movement of each object across frames in the video.
-- Identify and measure any delays or inconsistencies in their expected movement patterns.
-
-Note:
-- Ensure precise detection of contours based on the given color definitions.
-- Account for occlusions, overlaps, and changes in visibility.
-- Include a summary report of detected delays for each object.
  Carefully observe the video for visual cues indicating production interruption.Analyse frames and contours around the objects: 'h-stock_left','h-stock_right','conveyor1','conveyor2','compressor_metal','person','orange_roller_metal_left','orange_roller_metal_right','white_down_roller_left','white_down_roller_right','vaccum_blue'.
  If no person is visible in any of the frames, the reason probably might be due to his absence.
  If a person is visible in the video and is observed touching and modifying the layers of the tire, it means there is a issue with tyre being patched hence he is repatching it.
@@ -142,6 +124,7 @@ Please provide your analysis in the following format:
 Important: Base your analysis solely on visual evidence from the video. Focus on concrete, observable details rather than assumptions. Clearly state if no person or specific activity is observed."""
 
 
+
 # Load model globally
 model, tokenizer = load_model()