ReservoirChat: Interactive Documentation Enhanced with LLM and Knowledge Graph for ReservoirPy
This tool addresses the need for more reliable and domain-specific AI assistance for developers and researchers using the ReservoirPy library, though it is incremental as it builds on existing RAG and knowledge graph techniques.
The authors tackled the problem of improving Large Language Models' assistance with code development and complex questions in Reservoir Computing by introducing a tool that integrates Retrieval-Augmented Generation and knowledge graphs to reduce hallucinations and increase factual accuracy. Their model outperformed proprietary models like ChatGPT-4o and NotebookLM on coding tasks and showed significant improvement over its base model, Codestral-22B.
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.