AI knowledge graph

iText2KG is a Python package designed to leverage large language models to extract entities and relationships from text documents and incrementally build consistent knowledge graphs. It has zero-shot capabilities, allowing knowledge extraction across different domains without specific training. The package includes document distillation, entity extraction, and relationship extraction modules, ensuring entities and relationships are resolved and unique. It provides visual representation of knowledge graphs through Neo4j, supporting interactive exploration and analysis of structured data.

KG-RAG is a task-agnostic framework that combines the explicit knowledge of knowledge graphs and the tacit knowledge of large language models. Here, we utilize SPOKE, a huge biomedical knowledge graph, as the provider of biomedical context. The main feature of KG-RAG is that it extracts “prompt-related context” from the SPOKE knowledge graph, which is defined as the minimum context required to respond to user prompts.