Ask questions with Natural Language (GraphRAG)

How to use GraphRAG to ask questions with natural language.

What is GraphRAG?

RAG (Retrieval-Agumented Generation) is a framework used to improve the accuracy of information provided by LLMs. It improves LLM accuracy by retrieving information from external sources. This provides the LLM with up to date information grounded on the basis of relevant data rather than solely relying on the data the LLM was trained with. GraphRAG take this a step further, and retrieves information from a knowledge graph. GraphRAG enables teams to use natural language and obtain information directly from their knowledge graph.

GraphRAG AI Agents on the BioBox platform

We have two AI agents on the platform designed to make retrieving information from your graph as simple as possible.

Agent Orion converts Natural Language into Query Language, allowing you to explore the comprehensive answers returned with query language without having to write in Query Language. Agent Iris provides you with short summarized answers and allows you to converse with your data, retaining the context from previously asked questions.