mtllm 0.4.0

MTLLM Provides Easy to use APIs for different LLM Providers to be used with Jaseci's Jaclang Programming Language.

MTLLM - AI Integration Framework for Jac-lang

Meaning Typed Programming (MTP) is a programming paradigm for AI integration where prompt engineering is hidden through code semantics. MTLLM is the plugin built, exploring this hypothesis. MTLLM is built as a plugin to the Jaseci ecosystem. This plugin can be installed as a PyPI package.

pip install mtllm

Basic Example

A basic usecase of MTP can be demonstrated as follows:

import from mtllm{Model}

glob llm = Model(model_name="openai\gpt-4o");

def translate_to(language: str, phrase: str) -> str by llm();

with entry {
    output = translate_to(language="Welsh", phrase="Hello world");
    print(output);
}

AI-Powered Object Generation

import from mtllm {Model}

glob llm = Model(model_name="gpt-4o");

obj Task {
    has description: str,
        priority: int,
        estimated_time: int;
}

sem Task.priority = "priority between 0 (highest priority) and 10(lowest priority)";

def create_task(description: str, previous_tasks: list[Task]) -> Task by llm();

with entry {
    tasks = [];
    new_task = create_task("Write documentation for the API", tasks);
    print(f"Task: {new_task.description}, Priority: {new_task.priority}, Time: {new_task.estimated_time}min");
}

The by abstraction allows to automate semantic extraction from existing code semantics, eliminating manual prompt engineering while leveraging type annotations for structured AI responses.

Documentation and Examples

📚 Full Documentation: Jac MTLLM Documentation

🎮 Complete Examples:

• Fantasy Trading Game - Interactive RPG with AI-generated characters
• RPG Level Generator - AI-powered game level creation
• RAG Chatbot Tutorial - Building chatbots with document retrieval

🔬 Research: The research journey of MTP is available on Arxiv.

Quick Links

• Getting Started Guide
• Model Configuration
• Jac Language Documentation
• GitHub Repository