iText2KG is a Python package designed to leverage large language models for extracting entities and relationships from textual documents, incrementally constructing coherent knowledge graphs. It features zero-shot capabilities, enabling knowledge extraction across various domains without specific training. The package includes modules for document distillation, entity extraction, and relationship extraction, ensuring that entities and relationships are resolved and unique. It provides a visual representation of knowledge graphs through Neo4j, supporting interactive exploration and analysis of structured data.