|  | @ -1,20 +1,20 @@ | 
		
	
		
			
				|  |  | # 文心一言 |  |  |  | 
		
	
		
			
				|  |  |  |  |  | # Ernie Bot 文心一言 | 
		
	
		
			
				|  |  | 
 |  |  | 
 | 
		
	
		
			
				|  |  | *author: Jael* |  |  | *author: Jael* | 
		
	
		
			
				|  |  | 
 |  |  | 
 | 
		
	
		
			
				|  |  | <br /> |  |  | <br /> | 
		
	
		
			
				|  |  | 
 |  |  | 
 | 
		
	
		
			
				|  |  | ## Description |  |  |  | 
		
	
		
			
				|  |  |  |  |  | ## Description 描述 | 
		
	
		
			
				|  |  | 
 |  |  | 
 | 
		
	
		
			
				|  |  | A LLM operator generates answer given prompt in messages using a large language model or service. |  |  | A LLM operator generates answer given prompt in messages using a large language model or service. | 
		
	
		
			
				|  |  | This operator is implemented with Ernie Bot from [Baidu](https://cloud.baidu.com/wenxin.html). |  |  | This operator is implemented with Ernie Bot from [Baidu](https://cloud.baidu.com/wenxin.html). | 
		
	
		
			
				|  |  | Please note you will need [Ernie API key & Secret key](https://ai.baidu.com/ai-doc/REFERENCE/Lkru0zoz4) to access the service. |  |  | Please note you will need [Ernie API key & Secret key](https://ai.baidu.com/ai-doc/REFERENCE/Lkru0zoz4) to access the service. | 
		
	
		
			
				|  |  | 
 |  |  | 
 | 
		
	
		
			
				|  |  | <br /> |  |  |  | 
		
	
		
			
				|  |  |  |  |  | LLM 算子使用大语言模型或服务,为输入的问题或提示生成答案。LLM/Ernie 利用了来自百度的[文心一言](https://cloud.baidu.com/wenxin.html)。请注意,您需要[文心一言服务的 API Key 和 Secret Key](https://ai.baidu.com/ai-doc/REFERENCE/Lkru0zoz4)才能访问该服务。 | 
		
	
		
			
				|  |  | 
 |  |  | 
 | 
		
	
		
			
				|  |  | ## Code Example |  |  |  | 
		
	
		
			
				|  |  |  |  |  | <br /> | 
		
	
		
			
				|  |  | 
 |  |  | 
 | 
		
	
		
			
				|  |  | Use the default model to continue the conversation from given messages. |  |  |  | 
		
	
		
			
				|  |  |  |  |  | ## Code Example 代码示例 | 
		
	
		
			
				|  |  | 
 |  |  | 
 | 
		
	
		
			
				|  |  | *Write a pipeline with explicit inputs/outputs name specifications:* |  |  | *Write a pipeline with explicit inputs/outputs name specifications:* | 
		
	
		
			
				|  |  | 
 |  |  | 
 | 
		
	
	
		
			
				|  | @ -24,7 +24,7 @@ from towhee import pipe, ops | 
		
	
		
			
				|  |  | p = ( |  |  | p = ( | 
		
	
		
			
				|  |  |     pipe.input('messages') |  |  |     pipe.input('messages') | 
		
	
		
			
				|  |  |         .map('messages', 'answer', ops.LLM.Ernie(api_key=ERNIE_API_KEY, secret_key=ERNIE_SECRET_KEY)) |  |  |         .map('messages', 'answer', ops.LLM.Ernie(api_key=ERNIE_API_KEY, secret_key=ERNIE_SECRET_KEY)) | 
		
	
		
			
				|  |  |         .output('messages', 'answer') |  |  |  | 
		
	
		
			
				|  |  |  |  |  |         .output('answer') | 
		
	
		
			
				|  |  | ) |  |  | ) | 
		
	
		
			
				|  |  | 
 |  |  | 
 | 
		
	
		
			
				|  |  | messages=[ |  |  | messages=[ | 
		
	
	
		
			
				|  | @ -36,7 +36,7 @@ answer = p(messages).get()[0] | 
		
	
		
			
				|  |  | 
 |  |  | 
 | 
		
	
		
			
				|  |  | <br /> |  |  | <br /> | 
		
	
		
			
				|  |  | 
 |  |  | 
 | 
		
	
		
			
				|  |  | ## Factory Constructor |  |  |  | 
		
	
		
			
				|  |  |  |  |  | ## Factory Constructor 接口说明 | 
		
	
		
			
				|  |  | 
 |  |  | 
 | 
		
	
		
			
				|  |  | Create the operator via the following factory method: |  |  | Create the operator via the following factory method: | 
		
	
		
			
				|  |  | 
 |  |  | 
 | 
		
	
	
		
			
				|  | @ -59,7 +59,7 @@ Other OpenAI parameters such as temperature, etc. | 
		
	
		
			
				|  |  | 
 |  |  | 
 | 
		
	
		
			
				|  |  | <br /> |  |  | <br /> | 
		
	
		
			
				|  |  | 
 |  |  | 
 | 
		
	
		
			
				|  |  | ## Interface |  |  |  | 
		
	
		
			
				|  |  |  |  |  | ## Interface 使用说明 | 
		
	
		
			
				|  |  | 
 |  |  | 
 | 
		
	
		
			
				|  |  | The operator takes a piece of text in string as input. |  |  | The operator takes a piece of text in string as input. | 
		
	
		
			
				|  |  | It returns answer in json. |  |  | It returns answer in json. | 
		
	
	
		
			
				|  | 
 |