astra-langchain4j: Experiences Combining LLMs and Agent Programming

TL;DR

This paper discusses integrating large language models with the ASTRA agent programming language, exploring how AI impacts traditional agent toolkits and sharing practical development experiences.

Contribution

It presents a prototype integration of LLMs into ASTRA and shares insights from three example implementations and their development experiences.

Findings

Successful integration of LLMs with ASTRA

Insights into combining AI with traditional agent toolkits

Practical experiences from prototype implementations

Abstract

Given the emergence of Generative AI over the last two years and the increasing focus on Agentic AI as a form of Multi-Agent System it is important to explore both how such technologies can impact the use of traditional Agent Toolkits and how the wealth of experience encapsulated in those toolkits can influence the design of the new agentic platforms. This paper presents an overview of our experience developing a prototype large language model (LLM) integration for the ASTRA programming language. It presents a brief overview of the toolkit, followed by three example implementations, concluding with a discussion of the experiences garnered through the examples.