Update app.py

app.py

@@ -6,12 +6,12 @@ from decord import cpu, VideoReader, bridge
 from transformers import AutoModelForCausalLM, AutoTokenizer
 from transformers import BitsAndBytesConfig
 
-# Model Configuration
+
 MODEL_PATH = "THUDM/cogvlm2-llama3-caption"
 DEVICE = 'cuda' if torch.cuda.is_available() else 'cpu'
 TORCH_TYPE = torch.bfloat16 if torch.cuda.is_available() and torch.cuda.get_device_capability()[0] >= 8 else torch.float16
 
-# Define delay reasons for each step
+
 DELAY_REASONS = {
     "Step 1": ["No raw material available", "Person repatching the tire"],
     "Step 2": ["Person repatching the tire", "Lack of raw material"],
@@ -25,9 +25,13 @@ DELAY_REASONS = {
 
 def load_video(video_data, strategy='chat'):
     bridge.set_bridge('torch')
-    mp4_stream = video_data
     num_frames = 24
-    decord_vr = VideoReader(io.BytesIO(mp4_stream), ctx=cpu(0))
+    
+   
+    if isinstance(video_data, str): 
+        decord_vr = VideoReader(video_data, ctx=cpu(0))
+    else:  
+        decord_vr = VideoReader(io.BytesIO(video_data), ctx=cpu(0))
     
     frame_id_list = []
     total_frames = len(decord_vr)
@@ -100,44 +104,41 @@ def predict(prompt, video_data, temperature, model, tokenizer):
 
 def get_analysis_prompt(step_number, possible_reasons):
     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:
 1. Carefully observe the video for visual cues indicating production interruption
 2. Compare observed evidence against each possible delay reason
 3. Select the most likely reason based on visual evidence
-
 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."""
 
+# Load model globally
 model, tokenizer = load_model()
 
 def inference(video, step_number):
-    if not video:
-        return "Please upload a video first."
-    
-    with open(video_path, "rb") as f:
-            video_data = f.read()
+    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_data, temperature, model, tokenizer)
-    
-    return response
+        # 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)
+        
+        return response
+    except Exception as e:
+        return f"An error occurred during analysis: {str(e)}"
 
 # Gradio Interface
 def create_interface():
@@ -172,4 +173,4 @@ def create_interface():
 
 if __name__ == "__main__":
     demo = create_interface()
-    demo.launch()
+    demo.launch(share=True)  # Added share=True to create a public link