meta prompt generator
1.0.0
O Meta Prompt Generator é um pacote Python que gera avisos detalhados do sistema para modelos de idiomas com base em descrições de tarefas ou prompts existentes. Ele aproveita os modelos GPT da OpenAI para criar prompts bem estruturados e específicos de tarefas que podem ser usados para orientar os modelos de IA para concluir várias tarefas de maneira eficaz. Você também pode usá -lo na CLI.
Para instalar o gerador de meta prompt, você pode clonar ou usar o PIP:
Clone o repositório:
git clone https://github.com/Zakk-Yang/meta-prompt-generator.git
cd meta-prompt-generator
Instale o pacote através do PIP:
pip install meta-prompt-generator --upgrade
Aqui está um exemplo básico de como usar o generador de meta prompt:
from meta_prompt_generator import generate_prompt
# Generate a prompt
task = "Create a prompt for generating creative short stories"
prompt = generate_prompt ( task )
print ( prompt )O prompt gerado é envolvido nos blocos de código de marcação.
Antes de personalizar seu próprio modelo, é recomendável verificar o modelo atual.
from meta_prompt_generator . prompts import META_PROMPT
print ( META_PROMPT )Saída:
Given a task description or existing prompt, produce a detailed system prompt to guide a language model in completing the task effectively.
# Guidelines
- Understand the Task: Grasp the main objective, goals, requirements, constraints, and expected output.
- Minimal Changes: If an existing prompt is provided, improve it only if it's simple. For complex prompts, enhance clarity and add missing elements without altering the original structure.
- Reasoning Before Conclusions: Encourage reasoning steps before any conclusions are reached. ATTENTION! If the user provides examples where the reasoning happens afterward, REVERSE the order! NEVER START EXAMPLES WITH CONCLUSIONS!
- Reasoning Order: Call out reasoning portions of the prompt and conclusion parts (specific fields by name). For each, determine the ORDER in which this is done, and whether it needs to be reversed.
- Conclusion, classifications, or results should ALWAYS appear last.
- Examples: Include high-quality examples if helpful, using placeholders [ in brackets ] for complex elements.
- What kinds of examples may need to be included, how many, and whether they are complex enough to benefit from placeholders.
- Clarity and Conciseness: Use clear, specific language. Avoid unnecessary instructions or bland statements.
- Formatting: Use markdown features for readability. DO NOT USE ``` CODE BLOCKS UNLESS SPECIFICALLY REQUESTED.
- Preserve User Content: If the input task or prompt includes extensive guidelines or examples, preserve them entirely, or as closely as possible. If they are vague, consider breaking down into sub-steps. Keep any details, guidelines, examples, variables, or placeholders provided by the user.
- Constants: DO include constants in the prompt, as they are not susceptible to prompt injection. Such as guides, rubrics, and examples.
- Output Format: Explicitly the most appropriate output format, in detail. This should include length and syntax (e.g. short sentence, paragraph, JSON, etc.)
- For tasks outputting well-defined or structured data (classification, JSON, etc.) bias toward outputting a JSON.
- JSON should never be wrapped in code blocks (```) unless explicitly requested.
The final prompt you output should adhere to the following structure below. Do not include any additional commentary, only output the completed system prompt. SPECIFICALLY, do not include any additional messages at the start or end of the prompt. (e.g. no "---")
[ Concise instruction describing the task - this should be the first line in the prompt, no section header ]
[ Additional details as needed. ]
[ Optional sections with headings or bullet points for detailed steps. ]
# Steps [ optional ]
[ optional: a detailed breakdown of the steps necessary to accomplish the task ]
# Output Format
[ Specifically call out how the output should be formatted, be it response length, structure e.g. JSON, markdown, etc ]
# Examples [ optional ]
[ Optional: 1-3 well-defined examples with placeholders if necessary. Clearly mark where examples start and end, and what the input and output are. User placeholders as necessary. ]
[ If the examples are shorter than what a realistic example is expected to be, make a reference with () explaining how real examples should be longer / shorter / different. AND USE PLACEHOLDERS! ]
# Notes [ optional ]
[ optional: edge cases, details, and an area to call or repeat out specific important considerations ]
Em seguida, você pode alterar seu próprio modelo e aplicar:
my_meta_prompt = """ Customize your own template here """
task = "Create a prompt for generating creative short stories"
prompt = generate_prompt ( task , prompt_template = my_meta_prompt )
print ( prompt )Saída no formato JSON: você chan verifica o modelo de esquema primeiro:
from meta_prompt_generator . prompts import META_SCHEMA_PROMPT , META_SCHEMA
print ( META_SCHEMA_PROMPT )
print ( META_SCHEMA )Crie saída JSON:
from meta_prompt_generator . generator import generate_meta_schema
print ( generate_meta_schema ( 'generate KPIs for a data team' ))Saída:
{
"name" : " kpis_data_team " ,
"type" : " object " ,
"properties" : {
"kpi_list" : {
"type" : " array " ,
"description" : " A list of KPIs defined for the data team. " ,
"items" : {
"type" : " object " ,
"properties" : {
"name" : {
"type" : " string " ,
"description" : " The name of the KPI. "
},
"description" : {
"type" : " string " ,
"description" : " A brief description of what the KPI measures. "
},
"target" : {
"type" : " string " ,
"description" : " The target value or goal for the KPI. "
},
"frequency" : {
"type" : " string " ,
"description" : " The frequency of measuring this KPI (e.g., weekly, monthly). "
},
"owner" : {
"type" : " string " ,
"description" : " The individual or role responsible for this KPI. "
}
},
"required" : [
" name " ,
" description " ,
" target " ,
" frequency " ,
" owner "
],
"additionalProperties" : false
}
}
},
"required" : [
" kpi_list "
],
"additionalProperties" : false
} Sinta -se à vontade para alterar META_SCHEMA_PROMPT e META_SCHEMA ou outros parâmetros pelo exemplo abaixo: task_or_prompt: str, api_key: opcional [str] = nenhum, schema_template: dict = meta_schema, prompt. "GPT-4o-mini",
from meta_prompt_generator . generator import generate_meta_schema
print ( generate_meta_schema ( task_or_prompt = 'generate KPIs for a data team' ,
schema_template = 'your schema template' ,
prompt_template = 'your prompt template' ,
model_name = 'your preferred openai model name' # default is gpt-4o-mini
))Use na CLI:
Por padrão, ele está usando o modelo gpt-4o-mini .
meta-prompt " Create a prompt for generating creative short stories "Você pode optar por usar um modelo diferente.
meta-prompt " Design a system to classify customer feedback " --model-name gpt-4oNão é recomendável adicionar seu modelo de prompt personalizado aqui, pois pode ser muito demorado.
O pacote requer uma chave de API do OpenAI. Você pode fornecê -lo de três maneiras:
Como um argumento para a função generate_prompt :
prompt = generate_prompt ( task , api_key = "your-api-key-here" ) Como uma variável de ambiente denominada OPENAI_API_KEY :
export OPENAI_API_KEY= " your-api-key-here "Criar .env na raiz para incluir
OPENAI_API_KEY = 'sk-xxx'
Nota: Certifique -se de adicionar .env ao seu arquivo .gitignore para evitar cometer acidentalmente sua chave da API.
As contribuições para o gerador de meta prompt são bem -vindas! Sinta -se à vontade para enviar uma solicitação de tração.
Este projeto está licenciado sob a licença do MIT - consulte o arquivo de licença para obter detalhes.
