Update app.py

app.py

@@ -106,39 +106,34 @@ def predict(prompt, video_data, temperature, model, tokenizer):
 
 def get_analysis_prompt(step_number, possible_reasons):
     """
-    Constructs a robust prompt for analyzing delay reasons based on the selected manufacturing step.
+    Constructs the prompt for analyzing delay reasons based on the selected step.
     Args:
-        step_number (int): The manufacturing step being analyzed.
+        step_number (int): The manufacturing step number being analyzed.
         possible_reasons (list): A list of possible delay reasons for this step.
     Returns:
-        str: A highly detailed and robust analysis prompt tailored to the given step and reasons.
+        str: A detailed analysis prompt tailored to the given step and reasons.
     """
     return f"""
-    You are a highly advanced AI system specializing in the analysis of tire manufacturing processes to identify and diagnose production delays. You are tasked with analyzing video footage from Step {step_number}, where a delay has been detected. Your goal is to determine the most accurate cause of the delay based on the visual evidence.
+    You are an advanced AI expert system specialized in analyzing manufacturing processes to diagnose production delays. Your task is to analyze video footage from Step {step_number} of a tire manufacturing process, where a delay has been identified. Based on the visual evidence in the footage, determine the most accurate reason for the delay.
 
-    ### Task Context:
+    Task Context:
     - Manufacturing Step: {step_number}
     - Delay Detected: Yes
     - Possible Reasons for Delay: {', '.join(possible_reasons)}
 
-    ### Required Analysis:
-    Carefully examine the video footage frame by frame, focusing on the following aspects:
-
-    #### Technician Presence and Role:
-    - **Technician Availability:**
-        - Determine if a technician is visibly present during the step.
-        - If no technician is present, classify absence as a possible delay cause.
-    - **Technician Actions:**
-        - If a technician is present, observe their actions:
-            - Are they collecting or loading a carcass? Ensure the task is executed efficiently.
-            - Are they repairing the inner liner or sidewall? This indicates an issue with material application or alignment.
-            - Are they manually adjusting components or reworking parts? This suggests equipment malfunction or material misalignment.
-
-    #### Task-Specific Indicators:
-    - **Carcass Handling**: Ensure technicians are promptly collecting and loading carcasses when required.
-    - **Inner Liner Repair**: Note if technicians are involved in patching or reapplying the inner liner.
-    - **Sidewall Repair**: Identify if technicians are working to fix damaged or misaligned sidewalls.
-
+    Required Analysis:
+    1. Carefully observe the video footage frame by frame to identify any visual cues of production interruptions or anomalies.
+    2. Compare the observed evidence with each potential reason for delay, focusing on specific visual indicators:
+        - If no technician or worker is visible in the footage, consider the possibility of absence as the delay reason.
+        - If a technician is present and actively interacting with materials (e.g., touching or adjusting layers), evaluate whether the interaction indicates an issue requiring manual intervention, such as repatching a misaligned tire layer.
+        - Look for machine pauses, material misalignment, missing components, or other visual signals suggesting equipment or procedural issues.
+    
+    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.
+    Output Requirements:
     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]
@@ -146,17 +141,14 @@ def get_analysis_prompt(step_number, possible_reasons):
     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.
 
-    ### Key Considerations:
-    - **Observe Frame-by-Frame**: Carefully analyze each frame to capture subtleties, such as technician actions, material defects, or machine behavior.
-    - **Focus on Visual Evidence**: Base your analysis entirely on observable details from the footage. Avoid unverified assumptions.
-    - **Evaluate Standard Times**: Compare observed task durations with the standard time for this step. Identify where delays occurred and why.
-
-    ### Note:
-    - Prioritize identifying technician involvement in carcass handling, inner liner, or sidewall repair, as these are critical delay causes.
-
+    Important:
+    - Base your analysis exclusively on observable evidence from the video.
+    - Avoid assumptions not supported by visual details.
+    - Clearly state if no conclusive evidence is found and recommend further investigation.
     """
 
 
+
 # Load model globally
 model, tokenizer = load_model()