Hybrid retrieval in one query
Find semantically similar entities, then traverse their relationships to build connected context — in a single pipeline, without round-tripping between systems.
Vector Search
Find similar. Understand connected.
Similarity and structure in a single engine. Run vector search and graph traversal together or use Memgraph alongside your existing vector database.
CALL vector_search.search('movies_index', 5, $query_vector) YIELD node, similarityONE QUERY
Vector search
[ ... ]
[ ... ]
[ ... ]
Graph traversal
MemgraphONE ENGINE
Result
Modern AI needs both. Memgraph delivers it.
Vector search finds what's semantically similar. Graph traversal finds what's structurally connected. Memgraph handles both in a single engine — with 85% less memory for vector storage.
85%
Memory reduction
(Single Store Index)
(Single Store Index)
HNSW
Powered by
USearch (C++)
USearch (C++)
3 metrics
Cosine, L2, and
inner product
inner product
v3.2+
Production-ready
since Memgraph 3.2
since Memgraph 3.2
DeploymentTwo ways to add graph intelligence
Two ways to add graph intelligence
to vector search.
Native vector search in Memgraph
No separate vector database, no data duplication, no synchronization overhead.
- 👁 Image
Single Store Vector Index — vectors stored once, not duplicated - 👁 Image
Node and edge vector indexes - 👁 Image
Configurable scalar kinds (f32, f16) for precision/memory trade-off
Best for: teams building new systems who want a single engine for hybrid retrieval.
Memgraph + external vector database
Keep Pinecone, Weaviate, Qdrant, Chroma, or Milvus. Add Memgraph as the graph layer.
- 👁 Image
Memgraph handles graph storage and traversal - 👁 Image
Vector DB handles embedding storage and similarity search - 👁 Image
No migration required, add Memgraph to your existing stack
Best for: teams with an established vector pipeline who need to add graph reasoning.
Native search
How it works in Memgraph.
0101
STEP 1. Create a vector index
CREATE VECTOR INDEX movies_index ON :Movie(embedding) WITH CONFIG {'dimension': 384, 'capacity': 10000, 'metric': 'cos'};
0202
STEP 2. Search by similarity
CALL vector_search.search('movies_index', 5, $query_vector) YIELD node, similarity
0303
STEP 3. Combine with graph traversal
CALL vector_search.search('movies_index', 5, $query_vector) YIELD node, similarity MATCH (node)-[:DIRECTED_BY]->(director)-[:DIRECTED]->(other) RETURN other.title, similarity ORDER BY similarity DESC
One query. Both similarity and structure. No external system required.
Benefits
Why this matters for AI workloads.
No synchronization overhead
When vectors and graph live in the same engine, there's no ETL between databases, no eventual consistency, no data drift between your vector index and your knowledge graph.
In-memory speed for both
Both vector search and graph traversal run in memory. No disk IO for either operation. Sub-millisecond latency for both.
Decision guide
Which approach is right for you?
02
Use Memgraph + external vector DB when:
Integrations
Works with your stack.
LangGraph
Memgraph toolkit with 7+ tools for building stateful, multi-actor agent applications with graph-backed state management.
Read docsLlamaIndex
Create knowledge graphs from unstructured data and query with natural language via Memgraph graph store.
Read docsLightRAG
Fast retrieval-augmented generation combining graph databases with LLMs for creating and querying knowledge graphs.
Read docs