You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
EEG-RAG is a Retrieval-Augmented Generation (RAG) system specifically designed for electroencephalography (EEG) research. It enables researchers, clinicians, and data scientists to ask natural language questions about EEG literature and receive evidence-based answers with proper citations.
This project is a graph-native memory prototype that addresses one of the main weaknesses of a flat vector index: semantic similarity is useful for recall, but it is not a reliable definition of identity. The codebase combines FastAPI, Neo4j 5 vector indexes, a deterministic local embedding service, lightweight entity extraction, and a conservative