GraphRAG
A RAG approach that uses knowledge graphs rather than vector databases for retrieval. It combines graph traversal with LLM generation to answer questions requiring multi-hop reasoning.
Why It Matters
GraphRAG excels at questions requiring connecting multiple pieces of information — 'Who manages the team that built the product mentioned in yesterday's support ticket?'
Example
Querying a knowledge graph to find: ticket → product → team → manager, then using the LLM to generate a natural language answer from the traversed path.
Think of it like...
Like a detective following a chain of clues — each clue points to the next, and the full chain reveals the answer that no single document contains.
Related Terms
Retrieval-Augmented Generation
A technique that enhances LLM outputs by first retrieving relevant information from external knowledge sources and then using that information as context for generation. RAG combines the power of search with the fluency of language models.
Knowledge Graph
A structured representation of real-world entities and the relationships between them, stored as a network of nodes (entities) and edges (relationships). Knowledge graphs capture factual information in a machine-readable format.
Graph Neural Network
A type of neural network designed to operate on graph-structured data (nodes and edges). GNNs learn representations of nodes, edges, or entire graphs by aggregating information from neighbors.
Semantic Search
Search that understands the meaning and intent behind a query rather than just matching keywords. It uses embeddings to find results that are conceptually related even if they use different words.