meta prompt generator
1.0.0
Meta Invite Generator est un package Python qui génère des invites système détaillées pour des modèles de langage basés sur des descriptions de tâches ou des invites existantes. Il exploite les modèles GPT d'OpenAI pour créer des invites bien structurées et spécifiques à la tâche qui peuvent être utilisées pour guider les modèles d'IA pour accomplir efficacement diverses tâches. Vous pouvez également l'utiliser dans CLI.
Pour installer le générateur d'invite Meta, vous pouvez soit cloner ou utiliser PIP:
Clone le référentiel:
git clone https://github.com/Zakk-Yang/meta-prompt-generator.git
cd meta-prompt-generator
Installez le package via PIP:
pip install meta-prompt-generator --upgrade
Voici un exemple de base de la façon d'utiliser le générateur d'invite Meta:
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 )L'invite générée est enveloppée dans les blocs de code de démarque.
Avant de personnaliser votre propre modèle, il est recommandé de vérifier le modèle actuel.
from meta_prompt_generator . prompts import META_PROMPT
print ( META_PROMPT )Sortir:
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 ]
Ensuite, vous pouvez modifier votre propre modèle et postuler:
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 )Sortie au format JSON: vous vérifiez d'abord le modèle de schéma:
from meta_prompt_generator . prompts import META_SCHEMA_PROMPT , META_SCHEMA
print ( META_SCHEMA_PROMPT )
print ( META_SCHEMA )Créer une sortie JSON:
from meta_prompt_generator . generator import generate_meta_schema
print ( generate_meta_schema ( 'generate KPIs for a data team' ))Sortir:
{
"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
} N'hésitez pas à modifier à la fois META_SCHEMA_PROMPT et META_SCHEMA ou autres paramètres par l'exemple ci-dessous: task_or_prompt: str, api_key: facultatif [str] = aucun, schema_template: dict = meta_schema, prompt_template: facultatif [str] = meta_schema_prompt, model_name: optionnel [str] = "gpt-4o"
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
))Utilisation dans la CLI:
Par défaut, il utilise le modèle gpt-4o-mini .
meta-prompt " Create a prompt for generating creative short stories "Vous pouvez choisir d'utiliser un modèle différent.
meta-prompt " Design a system to classify customer feedback " --model-name gpt-4oIl n'est pas recommandé d'ajouter votre modèle d'invite personnalisé ici car il peut être très long.
Le package nécessite une clé API OpenAI. Vous pouvez le fournir de trois manières:
Comme argument à la fonction generate_prompt :
prompt = generate_prompt ( task , api_key = "your-api-key-here" ) En tant que variable d'environnement nommée OPENAI_API_KEY :
export OPENAI_API_KEY= " your-api-key-here "Créer .env dans la racine pour inclure
OPENAI_API_KEY = 'sk-xxx'
Remarque: assurez-vous d'ajouter .env à votre fichier .gitignore pour éviter de commettre accidentellement votre clé API.
Les contributions au générateur invite Meta sont les bienvenues! N'hésitez pas à soumettre une demande de traction.
Ce projet est autorisé en vertu de la licence MIT - voir le fichier de licence pour plus de détails.
