prompt ez
1.0.0
Um construtor de prompt de fácil uso para criar avisos estruturados no TypeScript para aplicativos LLMS (Language Models) e AI.
Este projeto tem como objetivo melhorar a legibilidade e a manutenção imediatas por meio de uma interface simples, compatível com vários modelos de IA do OpenAI, Anthropic, Google Gemini e muito mais. Ele também usa uma estrutura de prompt baseada em XML recomendada pela Antrópica para melhorar a qualidade imediata e a compreensão do modelo.
Originalmente desenvolvido para atender às necessidades internas do Dreamloom, nós o abre para beneficiar a comunidade em geral. Congratulamo -nos com suas sugestões de melhorias e outros comentários sobre o Github.
Contribuir para o projeto no GitHub
Este projeto utiliza prompts baseados em XML, que é a estrutura preferida para o modelo AI Claude da Anthrópica. De acordo com a documentação do Anthropic, o uso de tags XML no Prompts oferece várias vantagens:
Embora recomendado pelo Antrópico para Claude, essa abordagem estruturada para pronta a engenharia pode ser extremamente benéfica ao trabalhar com outros modelos LLMS e IA também, ajudando os modelos a entender e responder melhor aos seus avisos, tornando -os mais precisos e úteis.
Instale o prompt-ez usando o npm:
npm install prompt-ez A classe PromptBuilder é a principal interface para criar instruções estruturadas. Aqui está uma rápida visão geral de seus métodos:
tag(name: string, contentFn?: (builder: PromptBuilder) => void): PromptBuilder
name : o nome da tag.contentFn : função opcional para adicionar conteúdo dentro da tag. text(text: string): PromptBuilder
list(items: string[]): PromptBuilder
inputs(): PromptBuilder
build(params?: Record<string, unknown>): string
params : objeto opcional com pares de valor-chave para entradas dinâmicas.Aqui está um exemplo simples de criar um prompt estruturado:
import PromptBuilder from 'prompt-ez' ;
const prompt = new PromptBuilder ( )
. tag ( 'system' , b => b
. text ( 'You are a helpful AI assistant.' )
. text ( 'Please provide accurate and concise information.' )
)
. tag ( 'task' , b => b
. text ( 'Explain the benefits of regular exercise.' )
)
. tag ( 'output_format' , b => b
. text ( 'Provide the explanation in a paragraph.' )
)
. build ( ) ;
console . log ( prompt ) ;Isso gera o seguinte prompt:
< system >
You are a helpful AI assistant.
Please provide accurate and concise information.
</ system >
< task >
Explain the benefits of regular exercise.
</ task >
< output_format >
Provide the explanation in a paragraph.
</ output_format >Veja como usar entradas dinâmicas em seus avisos:
const promptWithInputs = new PromptBuilder ( )
. tag ( 'system' , b => b
. text ( 'You are a language translator.' )
)
. tag ( 'task' , b => b
. text ( 'Translate the following text:' )
. inputs ( )
)
. build ( {
source_language : 'English' ,
target_language : 'French' ,
text : 'Hello, how are you?'
} ) ;
console . log ( promptWithInputs ) ;Isso produz:
< system >
You are a language translator.
</ system >
< task >
Translate the following text:
< source_language >English</ source_language >
< target_language >French</ target_language >
< text >Hello, how are you?</ text >
</ task >Aqui está um exemplo mais complexo que demonstra tags aninhadas, criação de listas e entradas dinâmicas:
import PromptBuilder from 'prompt-ez' ;
export const AI_MEDICAL_DIAGNOSIS_PROMPT = new PromptBuilder ( )
. tag ( 'medical_diagnosis_prompt' , ( builder ) =>
builder
. tag ( 'role' , ( b ) => b . text ( 'Act as an AI medical assistant. Analyze the provided patient information and suggest three potential diagnoses with recommended next steps.' ) )
. inputs ( )
. tag ( 'guidelines' , ( b ) =>
b
. text ( 'For each potential diagnosis:' )
. list ( [
'Consider the patient's symptoms, medical history, and test results' ,
'Provide a brief explanation of the condition' ,
'List key symptoms that align with the diagnosis' ,
'Suggest additional tests or examinations if needed' ,
'Outline potential treatment options' ,
'Indicate the urgency level (e.g., immediate attention, routine follow-up)' ,
'Highlight any lifestyle changes or preventive measures' ,
'Consider possible complications if left untreated' ,
'Use medical terminology appropriately, with layman explanations' ,
'Provide a confidence level for each diagnosis (low, medium, high)' ,
'First analyze the information thoroughly, then produce the output'
] )
)
. tag ( 'reminder' , ( b ) => b . text ( 'Ensure the diagnoses are evidence-based and consider a range of possibilities from common to rare conditions. Always emphasize the importance of consulting with a human healthcare professional for a definitive diagnosis.' ) )
. tag ( 'output_format' , ( b ) =>
b . list ( [
'Present information in a clear, structured manner' ,
'Use bullet points for symptoms and recommendations' ,
'Include relevant medical terms with brief explanations' ,
'Provide a summary of each potential diagnosis' ,
'Suggest follow-up questions to gather more information if needed' ,
'End with a disclaimer about the limitations of AI diagnosis'
] )
)
)
. build ( {
patient_age : 45 ,
patient_gender : 'Female' ,
main_symptoms : 'Persistent headache, blurred vision, and occasional dizziness for the past two weeks' ,
medical_history : 'Hypertension, controlled with medication' ,
recent_tests : 'Blood pressure: 150/95 mmHg, Blood sugar: 110 mg/dL (fasting)'
} ) ;
console . log ( AI_MEDICAL_DIAGNOSIS_PROMPT ) ;Isso gerará um aviso complexo e estruturado para um cenário de diagnóstico médico de IA:
< medical_diagnosis_prompt >
< role >Act as an AI medical assistant. Analyze the provided patient information and suggest three potential diagnoses with recommended next steps.</ role >
< patient_age >45</ patient_age >
< patient_gender >Female</ patient_gender >
< main_symptoms >Persistent headache, blurred vision, and occasional dizziness for the past two weeks</ main_symptoms >
< medical_history >Hypertension, controlled with medication</ medical_history >
< recent_tests >Blood pressure: 150/95 mmHg, Blood sugar: 110 mg/dL (fasting)</ recent_tests >
< guidelines >
For each potential diagnosis:
1. Consider the patient's symptoms, medical history, and test results
2. Provide a brief explanation of the condition
3. List key symptoms that align with the diagnosis
4. Suggest additional tests or examinations if needed
5. Outline potential treatment options
6. Indicate the urgency level (e.g., immediate attention, routine follow-up)
7. Highlight any lifestyle changes or preventive measures
8. Consider possible complications if left untreated
9. Use medical terminology appropriately, with layman explanations
10. Provide a confidence level for each diagnosis (low, medium, high)
11. First analyze the information thoroughly, then produce the output
</ guidelines >
< reminder >Ensure the diagnoses are evidence-based and consider a range of possibilities from common to rare conditions. Always emphasize the importance of consulting with a human healthcare professional for a definitive diagnosis.</ reminder >
< output_format >
1. Present information in a clear, structured manner
2. Use bullet points for symptoms and recommendations
3. Include relevant medical terms with brief explanations
4. Provide a summary of each potential diagnosis
5. Suggest follow-up questions to gather more information if needed
6. End with a disclaimer about the limitations of AI diagnosis
</ output_format >
</ medical_diagnosis_prompt >Congratulamo -nos com contribuições! Consulte nosso guia contribuinte para obter mais detalhes sobre como começar.
O Prompt-EZ é liberado sob a licença do MIT. Consulte o arquivo de licença para obter mais detalhes.
