|  |  | @ -20,7 +20,7 @@ This operator extracts features for video or text with [MDMMT: Multidomain Multi | 
			
		
	
		
			
				
					|  |  |  | Read the text to generate a text embedding.  | 
			
		
	
		
			
				
					|  |  |  | 
 | 
			
		
	
		
			
				
					|  |  |  | ```python | 
			
		
	
		
			
				
					|  |  |  | from towhee.dc2 import pipe, ops, DataCollection | 
			
		
	
		
			
				
					|  |  |  | from towhee import pipe, ops, DataCollection | 
			
		
	
		
			
				
					|  |  |  | 
 | 
			
		
	
		
			
				
					|  |  |  | p = ( | 
			
		
	
		
			
				
					|  |  |  |     pipe.input('text') \ | 
			
		
	
	
		
			
				
					|  |  | @ -36,7 +36,7 @@ Load a video embeddings extracted from different upstream expert networks, such | 
			
		
	
		
			
				
					|  |  |  | 
 | 
			
		
	
		
			
				
					|  |  |  | ```python | 
			
		
	
		
			
				
					|  |  |  | import torch | 
			
		
	
		
			
				
					|  |  |  | from towhee.dc2 import pipe, ops, DataCollection | 
			
		
	
		
			
				
					|  |  |  | from towhee import pipe, ops, DataCollection | 
			
		
	
		
			
				
					|  |  |  | 
 | 
			
		
	
		
			
				
					|  |  |  | 
 | 
			
		
	
		
			
				
					|  |  |  | torch.manual_seed(42) | 
			
		
	
	
		
			
				
					|  |  | 
 |