Update app.py

app.py

@@ -107,23 +107,54 @@ def predict(prompt, video_data, temperature, model, tokenizer):
 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:
-    {', '.join(possible_reasons)}
-    Required Analysis:
-     Carefully observe the video for visual cues indicating production interruption.
-     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 repairing it.
-     Compare observed evidence against each possible delay reason.
-     Select the most likely reason based on visual evidence.
-     Also give time duration of each video.
-    Please provide your analysis in the following format:
-    1. Selected Reason: [State the most likely reason from the given options]
-    2. Visual Evidence: [Describe specific visual cues that support your selection]
-    3. Reasoning: [Explain why this reason best matches the observed evidence]
-    4. Alternative Analysis: [Brief explanation of why other possible reasons are less likely]
-    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."""
-
+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)}
+### Task Context:  
+You are analyzing video footage from a specific step in the 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, while tracking the timeline of events to suggest actions that need to be taken at specific points.  
+
+### Required Analysis:  
+Analyze the delay in the 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:  
+1. **Contour Detection**: Extract the contours for each specified color.  
+2. **Movement Tracking**: Track the movement of each object across video frames and log timestamps where delays or anomalies occur.  
+3. **Delay Identification**: Identify and measure delays or inconsistencies in their expected movement patterns.  
+4. **Action Timeline**:  
+   - Provide timestamps where specific actions are required based on observed delays.  
+   - Suggest actions to resolve delays based on identified reasons and visual evidence.  
+
+### Additional Observations:  
+- If no person is visible in any frames, the delay reason might be due to their absence.  
+- If a person is visible and is observed interacting with the tire layers, it could indicate an issue requiring patching or adjustments.  
+
+### Analysis Framework:  
+Analyze the frames and contours for objects such as:  
+- **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**, and **vaccum_blue**.  
+
+Compare the observed evidence against the possible delay reasons. Select the most likely reason based on visual cues.  
+
+### Provide Your Analysis in the Following Format:  
+1. **Selected Reason**: [State the most likely reason from the given options].  
+2. **Visual Evidence**: [Describe specific visual cues that support your selection].  
+3. **Reasoning**: [Explain why this reason best matches the observed evidence].  
+4. **Action Timeline**:  
+   - [Timestamp]: [Describe the action needed].  
+   - [Timestamp]: [Describe the next action needed].  
+5. **Alternative Analysis**: [Brief explanation of why other possible reasons are less likely].  
+
+### Important Notes:  
+- Focus on precise and observable visual evidence from the video.  
+- Provide time-based actionable insights to address detected delays.  
+- Clearly state if no person or specific activity is observed.  
+"""