
EcoToxFred is a prototype that demonstrates how domain-specific knowledge can be combined with LLMs to facilitate the interaction between users and (domain-specific) knowledge. EcoToxFred can answer questions about chemicals and their measured concentrations in European surface waters like rivers and lakes. EcoToxFred is a friendly and intuitive chatbot designed to help researchers, stakeholders, and users explore and analyze chemical concentrations and toxicity data in European surface waters. By leveraging advanced language models and a graph database, EcoToxFred makes complex environmental toxicology data accessible and understandable for everyone, regardless of their technical background. The web application is accessible at https://ecotoxfred.web.app.ufz.de/.
We gratefully acknowledge the UFZ Research Data Management (RDM) unit for their support in deploying the Neo4j container, setting up the EcoToxFred web application, and ensuring seamless integration betweewo components.
Retrieval-augmented generation, Knowlege graph grounding, Domain-specific chat agent, Environmental toxicology
Retrieval-augmented generation, Knowlege graph grounding, Domain-specific chat agent, Environmental toxicology
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
