HOME/TECHNIQUE/Retrieval & Grounding/Structured & graph RAG

TECHNIQUE

Structured & graph RAG

Retrieval & Grounding

1APPLICATIONS
1OBSERVED OPERATORS
01

State of Practice

GROUNDED

Structured & graph RAG is deployed as an enterprise context layer by Dropbox and LinkedIn; Amazon has announced a graph-augmented recommendation system, while Grab’s pool evidence does not show this technique.

Observed Practices

Build a domain knowledge graph as part of the retrieval context backbone, rather than relying only on unstructured document retrieval.

2 of 3 deployed operators; Amazon is announced-status evidence and not counted, and Grab has no cited structured/graph RAG evidence in this pool.
DropboxLinkedIn

Pair graph context with indexed retrieval stores, including vector indexes and, for Dropbox, lexical BM25 plus dense vectors.

2 of 3 deployed operators.
DropboxLinkedIn

Normalize or enrich source data into LLM-usable structured context before retrieval.

2 of 3 deployed operators.
DropboxLinkedIn

Use LLM-mediated query planning or query generation to turn user requests into retrieval actions over indexes, graphs, or APIs.

2 of 3 deployed operators.
DropboxLinkedIn

Expose graph-grounded retrieval through product, API, or tool interfaces instead of leaving it as a back-end-only capability.

2 of 3 deployed operators.
DropboxLinkedIn

Add ranking, evaluation, or testing around retrieved context and answers.

2 of 3 deployed operators.
DropboxLinkedIn

Where Operators Converge

Among deployed operators with structured/graph RAG evidence, the graph is used alongside search or indexing infrastructure rather than as a standalone graph lookup.

Among deployed operators with evidence, the graph represents proprietary operational context: Dropbox models work content, people, activity, and sources; LinkedIn models security assets and relationships.

Where Operators Diverge

Graph construction differs by data source and validation workflow.

APPROACH 01

Connector-led enterprise content graph: crawl third-party apps, normalize files, enrich content, model information as a graph, and create knowledge bundles.

Dropbox

APPROACH 02

Security asset graph: prepare raw data from diverse databases into structured context and use a Security Knowledge Graph of digital assets and relationships.

LinkedIn

Runtime retrieval surfaces differ.

APPROACH 01

Single universal search tool plus agent delegation: a planning agent decides when search is needed, a specialized search agent constructs retrieval queries, and Dash retrieval is exposed through an MCP server with one tool.

Dropbox

APPROACH 02

GraphQL/Cypher routing: the LLM generates Cypher queries, and query routing directs requests to a knowledge graph or GraphQL backend.

LinkedIn

Retrieval signal mix differs.

APPROACH 01

Hybrid enterprise search: BM25 lexical index, dense vectors, embeddings, chunks, and contextual graph representations.

Dropbox

APPROACH 02

Security graph plus vector index and semantic search refinement.

LinkedIn

Watch Items

Context quality and retrieval accuracy remain active concerns: Dropbox says precision in what is fed to the model is critical and highlights trimming context; LinkedIn describes semantic search refinement when inaccuracies arise and uses an accuracy testing framework.

Multi-source context is a recurring source of complexity: Dropbox describes work content spread across apps and Dash consulting sources such as Confluence, Google Docs, and Jira; LinkedIn describes context generation from diverse databases.

02

Implementation Menu

CURATED DEFAULTS
NameKindMaturity
Neo4j with vector indexserviceestablished
GraphRAG (community summarization)patternemerging
Text-to-Cypher generationpatternemerging
03

Observed in Production

1 APP