ReservoirChat: Interactive Documentation Enhanced with LLM and Knowledge Graph for ReservoirPy

TL;DR

ReservoirChat is an interactive tool that leverages LLMs, retrieval-augmented generation, and knowledge graphs to enhance code development and question answering specifically for ReservoirPy, improving factual accuracy and user experience.

Contribution

The paper presents ReservoirChat, a novel system integrating LLMs with knowledge graphs and RAG for domain-specific coding assistance and knowledge retrieval in ReservoirPy.

Findings

Outperforms base models on coding tasks

Reduces hallucinations and improves factual accuracy

Provides an interactive, domain-specific coding environment

Abstract

We introduce a tool designed to improve the capabilities of Large Language Models (LLMs) in assisting with code development using the ReservoirPy library, as well as in answering complex questions in the field of Reservoir Computing. By incorporating external knowledge through Retrieval-Augmented Generation (RAG) and knowledge graphs, our approach aims to reduce hallucinations and increase the factual accuracy of generated responses. The system provides an interactive experience similar to ChatGPT, tailored specifically for ReservoirPy, enabling users to write, debug, and understand Python code while accessing reliable domain-specific insights. In our evaluation, while proprietary models such as ChatGPT-4o and NotebookLM performed slightly better on general knowledge questions, our model outperformed them on coding tasks and showed a significant improvement over its base model, Codestral-22B.