Request AI Module

Module for pay-respects to request AI for suggestions.

Configurations

Configuration is done via environment variables:

• _PR_AI_API_KEY: Your own API key
• _PR_AI_URL: Any OpenAI compatible URL can be used, e.g.:
  • https://api.openai.com/v1/chat/completions: OpenAI ChatGPT
  • https://api.groq.com/openai/v1/chat/completions: GroqCloud
  • http://localhost:11434/api/chat: Local Ollama
• _PR_AI_MODEL: Model used. Reasoning models are also supported
• _PR_AI_DISABLE: Setting to any value disables AI integration
• _PR_AI_LOCALE: Locale in which the AI explains the suggestion. Defaults to user system locale. Useful when you use small models that speak only English, for example.
• _PR_AI_ADDITIONAL_PROMPT: Additional prompts to be included. (Yes, you can include role-playing prompts you pervert)
  • User's environment is Zsh running in Arch Linux.
  • You are a cute catgirl. Always use cute phrases and expressions to prove your cuteness in the <note> section, including cat imitations like nya~, にゃ~,　喵～.

Compile time variables: Default values for the respective variables above when not set

• _DEF_PR_AI_API_KEY
• _DEF_PR_AI_URL
• _DEF_PR_AI_MODEL

If default values were not provided, pay-respects' own values will be used. Your request will be filtered to avoid abuse usages. Request will then be forwarded to a LLM provider that will not use your data for training. This service is provided free and is not guaranteed to always work. Donations would be appreciated:

Advanced Usages

For non-trivial suggestions, you can add more context as comments (for Bash and Zsh, interactive comments needs to be explicitly enabled):

pacman -S # how do I install Rust?