Simplify Prompt Engineering
Leverage prompt templates with placeholders to make complex prompts easy.
Streamline Your Interactions with GenAI Models
Prompt engineering is neither fast nor easy. Moreover, different models and their fine-tunes might require different prompt formats and tricks, or perhaps the information you work with requires special models to be used. PromptingTools.jl is meant to unify the prompts for different backends and make the common tasks (like templated prompts) as simple as possible.
Add PromptingTools, set OpenAI API key and generate your first answer:
using Pkg
Pkg.add("PromptingTools")
# Requires OPENAI_API_KEY environment variable!
ai"What is the meaning of life?"
For more information, see the Getting Started section.
Ready to simplify your GenerativeAI tasks? Dive into PromptingTools.jl now and unlock your productivity.
PromptingTools offers many advanced features:
Easy prompt templating and automatic serialization and tracing of your AI conversations for great observability
Ability to export into a ShareGPT-compatible format for easy fine-tuning
Code evaluation and automatic error localization for better LLM debugging
RAGTools module: from simple to advanced RAG implementations (hybrid index, rephrasing, reranking, etc.)
AgentTools module: lazy ai* calls with states, automatic code feedback, Monte-Carlo tree search-based auto-fixing of your workflows (ie, not just retrying in a loop)
and more!