Pré-Publication, Document De Travail Année : 2025

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

Virgile Boraud
  • Fonction : co premier-auteur
  • PersonId : 1556534
Yannis Bendi-Ouis
  • Fonction : co premier-auteur
  • PersonId : 1421979
Paul Bernard
  • Fonction : Collaborateur
  • PersonId : 1416087
Xavier Hinaut

Résumé

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.

Fichier principal
Vignette du fichier
main-ijcnn.pdf (2.05 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05132988 , version 1 (03-07-2025)

Licence

Identifiants

Citer

Virgile Boraud, Yannis Bendi-Ouis, Paul Bernard, Xavier Hinaut. ReservoirChat: Interactive Documentation Enhanced with LLM and Knowledge Graph for ReservoirPy. 2025. ⟨hal-05132988⟩
144 Consultations
414 Téléchargements

Altmetric

Partager

  • More