RAG & Search
GraphRAG
Graph retrieval-augmented generation
AI answering questions using information organized as connected people, things and relationships.
Example
A system connects people or things and relationships before answering a broad document question.
Why people use it
It helps connect information spread across related people, places or topics.
What you'll hear
“Use the relationships between these documents to answer the question.”
What this means for you
Validate the graph and compare results on representative questions.
Can you control it?
Developer-only
The people building or running the AI choose this setup. An everyday user generally needs their help to change how this part works.
Common questions
- Does using a graph guarantee more accurate answers?
- No. Mistakes or missing connections in the stored information can carry through into answers.
- Can it help with a question spanning many documents?
- It can, when the stored relationships capture the connections the question needs.
- Can building the graph add work?
- Yes. Extracting, checking and updating relationships can take additional time and computing resources.