Téléchargement SysPmt - Téléchargement du code source SysPmt

SysPmt

Code Source AI

v1.0.0

Télécharger

Syspmt readme

Aperçu

SYSPMT est un outil basé sur Python conçu pour convertir le pseudo-code écrit dans une syntaxe de type Python en invites système précises et exploitables pour les modèles de grande langue (LLMS). Cet outil est destiné à aider les développeurs et les ingénieurs proches qui sont aptes à la programmation, mais peuvent avoir besoin d'aide pour fabriquer des invites de système efficaces pour les LLM.

Comment ça marche

SYSPMT traite un fichier pseudo-code ( .pmt ) et un fichier de configuration ( .yaml ) pour traduire le pseudo-code en une invite système à l'aide des mappages définis dans la configuration YAML. Le texte généré est ensuite fourni à un LLM (dans notre cas, Chatgpt 4) pour créer l'invite du système final.

Installation et configuration

Clone le référentiel:
```
git clone [repository-url]
```
Assurez-vous que Python 3.x est installé sur votre machine.
Installer les dépendances requises:
```
pip install -r requirements.txt
```
Remplacez la touche API d'espace réservé dans le script par votre touche API OpenAI réelle.

Usage

Exécutez SYSPMT en spécifiant les chemins de temps vers votre configuration et vos fichiers pseudo-code:

python3 syspmt.py --config path/to/config.yaml --prompt path/to/prompt.pmt

Fichier de configuration ( `config.yaml` )

Le fichier de configuration définit les traductions et les formats de message pour convertir le pseudo-code en invites. Voici un exemple de configuration:

 messages :
  assign : " The AI assistant's '{var}' is set to {value}. "
  if_condition : " If the condition '{condition}' is met, perform the following actions: "
  else_condition : " Otherwise, perform the following actions: "

translations :
  check_language : " check if the language is "
  mission : " set the mission to "
  context : " set the context to "
  reject : " reject with the message: "
  proceed : " Proceed with the request "

Fichier pseudo-code ( `prompt.pmt` )

Ce fichier contient votre pseudo-code personnalisé. Exemple:

 mission = "travel agency support"
context = "travel discussion"
language = "English"
age = 28
gender = "Male"

if check_language ( language ):
    mission ( mission )
    context ( context )
elif check_language ( "French" ):
    mission ( "French travel consultant specializing in Paris" )
    context ( "discussion about travel offers in Paris" )
else :
    reject ( "We are sorry, we cannot assist you at the moment." )

if context ( "travel discussion" ):
    if check_language ( "English" ):
        mission ( "English travel specials" )
        context ( "exploring travel packages tailored for English speakers" )
    elif check_language ( "Spanish" ):
        mission ( "Spanish travel specials" )
        context ( "exploring travel packages tailored for Spanish speakers" )
    else :
        proceed ()
elif context ( "adventure tourism" ):
    mission ( "adventure tourism specialist" )
    context ( "providing information on adventure tourism packages" )
    if check_language ( "German" ):
        mission ( "German-speaking adventure tourism specialist" )
    else :
        proceed ()
else :
    reject ( "Unfortunately, we cannot provide assistance for this request. Please check your input and try again." )

Sortir

SYSPMT sort les invites du système prêtes pour le traitement LLM. Exemple de sortie basée sur le pseudo-code ci-dessus:

 As a 28-year-old male AI assistant set in the travel agency support mission, and operating in a travel discussion context, your task is to communicate in English. However, you need to attend to the user query dynamically according to the preferred language. If you detect that the user's language is English, you should continue providing assistance about travel discussions as an English travel specials consultant. But if the user shifts the language to French, your role must be changed to a French travel consultant specializing in Paris, discussing travel offers in that region. 

Nonetheless, if any other language than English or French is detected, you are supposed to inform the user with a message, stating, 'We are sorry, we cannot assist you at the moment.'. Also, it is important that you adjust the discussion context according to the user's command. If the context switches to 'travel discussion,' you should cater to the user in the language they are speaking, English or Spanish, exploring travel packages tailored for English or Spanish speakers, respectively. Still, if the user's language is different from these two, you should proceed with the initial settings. 

Conversely, if the context becomes 'adventure tourism,' modify your mission to an adventure tourism specialist, and if the user is speaking German, serve as a German-speaking adventure tourism specialist. But, should the language setting not be identified or if the context does not match any predefined settings, you should provide a message that states, 'Unfortunately, we cannot provide assistance for this request. Please check your input and try again.'.