2024-03-13 14:10:47 +08:00
# Written by YORKI MINAKO🤡, Edited by Xiaoyi
2023-09-01 02:28:37 +08:00
CONVERSATION_TITLE_PROMPT = """ You need to decompose the user ' s input into " subject " and " intention " in order to accurately figure out what the user ' s input language actually is.
2023-09-01 14:55:58 +08:00
Notice : the language type user use could be diverse , which can be English , Chinese , Español , Arabic , Japanese , French , and etc .
2023-09-01 02:28:37 +08:00
MAKE SURE your output is the SAME language as the user ' s input!
Your output is restricted only to : ( Input language ) Intention + Subject ( short as possible )
2023-09-01 10:31:42 +08:00
Your output MUST be a valid JSON .
2023-09-01 02:28:37 +08:00
Tip : When the user ' s question is directed at you (the language model), you can add an emoji to make it more fun.
example 1 :
User Input : hi , yesterday i had some burgers .
{
" Language Type " : " The user ' s input is pure English " ,
" Your Reasoning " : " The language of my output must be pure English. " ,
" Your Output " : " sharing yesterday ' s food "
}
example 2 :
User Input : hello
{
" Language Type " : " The user ' s input is written in pure English " ,
" Your Reasoning " : " The language of my output must be pure English. " ,
" Your Output " : " Greeting myself☺️ "
}
example 3 :
User Input : why mmap file : oom
{
" Language Type " : " The user ' s input is written in pure English " ,
" Your Reasoning " : " The language of my output must be pure English. " ,
" Your Output " : " Asking about the reason for mmap file: oom "
}
example 4 :
User Input : www . convinceme . yesterday - you - ate - seafood . tv讲了什么 ?
{
" Language Type " : " The user ' s input English-Chinese mixed " ,
" Your Reasoning " : " The English-part is an URL, the main intention is still written in Chinese, so the language of my output must be using Chinese. " ,
" Your Output " : " 询问网站www.convinceme.yesterday-you-ate-seafood.tv "
}
example 5 :
User Input : why小红的年龄is老than小明 ?
{
" Language Type " : " The user ' s input is English-Chinese mixed " ,
" Your Reasoning " : " The English parts are subjective particles, the main intention is written in Chinese, besides, Chinese occupies a greater \" actual meaning \" than English, so the language of my output must be using Chinese. " ,
" Your Output " : " 询问小红和小明的年龄 "
}
example 6 :
User Input : yo , 你今天咋样 ?
{
" Language Type " : " The user ' s input is English-Chinese mixed " ,
" Your Reasoning " : " The English-part is a subjective particle, the main intention is written in Chinese, so the language of my output must be using Chinese. " ,
" Your Output " : " 查询今日我的状态☺️ "
}
User Input :
"""
2023-05-15 08:51:32 +08:00
SUGGESTED_QUESTIONS_AFTER_ANSWER_INSTRUCTION_PROMPT = (
" Please help me predict the three most likely questions that human would ask, "
" and keeping each question under 20 characters. \n "
2024-07-19 20:26:11 +08:00
" MAKE SURE your output is the SAME language as the Assistant ' s latest response(if the main response is written in Chinese, then the language of your output must be using Chinese.)! \n "
2023-08-17 10:46:33 +08:00
" The output must be an array in JSON format following the specified schema: \n "
2023-05-15 08:51:32 +08:00
" [ \" question1 \" , \" question2 \" , \" question3 \" ] \n "
)
2023-07-28 20:47:15 +08:00
GENERATOR_QA_PROMPT = (
2024-04-07 15:21:11 +08:00
' <Task> The user will send a long text. Generate a Question and Answer pairs only using the knowledge in the long text. Please think step by step. '
2023-07-28 20:47:15 +08:00
' Step 1: Understand and summarize the main content of this text. \n '
' Step 2: What key information or concepts are mentioned in this text? \n '
' Step 3: Decompose or combine multiple pieces of information and concepts. \n '
2024-04-07 15:21:11 +08:00
' Step 4: Generate questions and answers based on these key information and concepts. \n '
' <Constraints> The questions should be clear and detailed, and the answers should be detailed and complete. '
' You must answer in {language} , in a style that is clear and detailed in {language} . No language other than {language} should be used. \n '
' <Format> Use the following format: Q1: \n A1: \n Q2: \n A2:... \n '
' <QA Pairs> '
2023-07-28 20:47:15 +08:00
)
2024-07-23 19:52:14 +08:00
WORKFLOW_RULE_CONFIG_PROMPT_GENERATE_TEMPLATE = """
Here is a task description for which I would like you to create a high - quality prompt template for :
< task_description >
{ { TASK_DESCRIPTION } }
< / task_description >
Based on task description , please create a well - structured prompt template that another AI could use to consistently complete the task . The prompt template should include :
- Do not inlcude < input > or < output > section and variables in the prompt , assume user will add them at their own will .
- Clear instructions for the AI that will be using this prompt , demarcated with < instructions > tags . The instructions should provide step - by - step directions on how to complete the task using the input variables . Also Specifies in the instructions that the output should not contain any xml tag .
- Relevant examples if needed to clarify the task further , demarcated with < example > tags . Do not include variables in the prompt . Give three pairs of input and output examples .
- Include other relevant sections demarcated with appropriate XML tags like < examples > , < instructions > .
- Use the same language as task description .
- Output in ` ` ` xml ` ` ` and start with < instruction >
Please generate the full prompt template with at least 300 words and output only the prompt template .
"""
2023-05-31 22:03:15 +08:00
2024-07-23 19:52:14 +08:00
RULE_CONFIG_PROMPT_GENERATE_TEMPLATE = """
Here is a task description for which I would like you to create a high - quality prompt template for :
< task_description >
{ { TASK_DESCRIPTION } }
< / task_description >
Based on task description , please create a well - structured prompt template that another AI could use to consistently complete the task . The prompt template should include :
- Descriptive variable names surrounded by { { } } ( two curly brackets ) to indicate where the actual values will be substituted in . Choose variable names that clearly indicate the type of value expected . Variable names have to be composed of number , english alphabets and underline and nothing else .
- Clear instructions for the AI that will be using this prompt , demarcated with < instructions > tags . The instructions should provide step - by - step directions on how to complete the task using the input variables . Also Specifies in the instructions that the output should not contain any xml tag .
- Relevant examples if needed to clarify the task further , demarcated with < example > tags . Do not use curly brackets any other than in < instruction > section .
- Any other relevant sections demarcated with appropriate XML tags like < input > , < output > , etc .
- Use the same language as task description .
- Output in ` ` ` xml ` ` ` and start with < instruction >
Please generate the full prompt template and output only the prompt template .
"""
2023-05-31 22:03:15 +08:00
2024-07-23 19:52:14 +08:00
RULE_CONFIG_PARAMETER_GENERATE_TEMPLATE = """
I need to extract the following information from the input text . The < information to be extracted > tag specifies the ' type ' , ' description ' and ' required ' of the information to be extracted .
< information to be extracted >
variables name bounded two double curly brackets . Variable name has to be composed of number , english alphabets and underline and nothing else .
< / information to be extracted >
Step 1 : Carefully read the input and understand the structure of the expected output .
Step 2 : Extract relevant parameters from the provided text based on the name and description of object .
Step 3 : Structure the extracted parameters to JSON object as specified in < structure > .
Step 4 : Ensure that the list of variable_names is properly formatted and valid . The output should not contain any XML tags . Output an empty list if there is no valid variable name in input text .
### Structure
Here is the structure of the expected output , I should always follow the output structure .
[ " variable_name_1 " , " variable_name_2 " ]
### Input Text
Inside < text > < / text > XML tags , there is a text that I should extract parameters and convert to a JSON object .
< text >
{ { INPUT_TEXT } }
< / text >
### Answer
I should always output a valid list . Output nothing other than the list of variable_name . Output an empty list if there is no variable name in input text .
"""
2023-05-31 22:03:15 +08:00
2024-07-23 19:52:14 +08:00
RULE_CONFIG_STATEMENT_GENERATE_TEMPLATE = """
< instruction >
Step 1 : Identify the purpose of the chatbot from the variable { { TASK_DESCRIPTION } } and infer chatbot ' s tone (e.g., friendly, professional, etc.) to add personality traits.
Step 2 : Create a coherent and engaging opening statement .
Step 3 : Ensure the output is welcoming and clearly explains what the chatbot is designed to do . Do not include any XML tags in the output .
Please use the same language as the user ' s input language. If user uses chinese then generate opening statement in chinese, if user uses english then generate opening statement in english.
Example Input :
Provide customer support for an e - commerce website
Example Output :
Welcome ! I ' m here to assist you with any questions or issues you might have with your shopping experience. Whether you ' re looking for product information , need help with your order , or have any other inquiries , feel free to ask . I ' m friendly, helpful, and ready to support you in any way I can.
< Task >
Here is the task description : { { INPUT_TEXT } }
You just need to generate the output
"""