What is vector index?

Example

Creating an index over the embedding property of every (:Movie) node in Neo4j.

cypher

CREATE VECTOR INDEX moviePlots IF NOT EXISTS
FOR (m:Movie)
ON m.embedding
OPTIONS { indexConfig: {
 `vector.dimensions`: 1536,
 `vector.similarity_function`: 'cosine'
}}

Lessons that use this term

The lesson and course links below open in a new tab.

29 lessons use this term. Results are ordered by term density.

Introduction to Vector Indexes and Unstructured Data30 mentions

Create the Answer Vector IndexVector indexesthis challenge, you will apply your knowledge and create the vector index on the3 mentions
Query a Vector IndexVector indexesthis lesson, you will learn how to query a vector index9 mentions
Searching imagesIntroductionused embeddings and a vector index to find similar3 mentions
Import data with Python and LangChainImporting unstructured dataclasses to create the embeddings, the vector index, and store the chunks in a Neo4j graph6 mentions
Create a Vector IndexVector indexesquery embeddings, you need to create a vector index3 mentions
Finding Movie PlotsIntroductioncan find similar movies by using the embedding for the movie plot and a vector index2 mentions
Create a graphImporting unstructured datawill need to create a vector index to query the paragraph2 mentions
Creating embeddingsImporting unstructured datayou are going to use the embedding to query the Neo4j chunkVector vector index you created in the last1 mention
Structured and Unstructured DataImporting unstructured datathe customer sentiment using a vector index1 mention

Neo4j & GenerativeAI Fundamentals16 mentions

Vector RetrieverIntegrating Neo4j with Generative AIwill use the moviePlots vector index you used to search for similar movies using4 mentions
Vector IndexesRetrieval Augmented Generation (RAG)this lesson, you will learn how to use a vector index in Neo4j to compare embeddings to find similar10 mentions
Graph-Enhanced Vector RetrieverIntegrating Neo4j with Generative AIretriever requires the vector index name (moviePlots), the retrieval query, and the embedder to encode the1 mention
Vector RAGRetrieval Augmented Generation (RAG)data is then stored in a vector index1 mention

Using Neo4j with LangChain5 mentions

Vector SearchVectorsvector index, moviePlots, has been created for the .plotEmbedding property of the5 mentions

Building Agents in Neo4j Aura6 mentions

Using the Similarity Search toolBuilding an AgentA vector index built on those4 mentions
Introduction to Aura AgentIntroduction to Aura AgentA vector index created in your AuraDB instance Graph data populated with embeddings generated from a [supported text embedding1 mention
Designing and managing agentsIntroduction to Aura Agentyour graph nodes to have vector embeddings stored as properties, and a vector index built on those1 mention

Constructing Knowledge Graphs with Neo4j GraphRAG for Python7 mentions

Vector + Cypher retrieverRetrievalwill need to create a vector index on the Chunk nodes6 mentions
Constructing knowledge graphsIntroductionVector index allows you to perform semantic searches, similarity searches, and clustering on the1 mention

Neo4j and Generative AI Workshop8 mentions

Vector + Cypher retrieverRetrievalwill need to create a vector index on the Chunk nodes5 mentions
Search lesson contentAgentsCreate a VectorCypherRetriever retriever that uses the Chunk vector index1 mention
Constructing knowledge graphsKnowledge Graph Constructionthese vectors into a Vector index allows you to perform semantic1 mention
Vector RAGRetrievaldata is then stored in a vector index1 mention

Context Graphs: Agent Memory with Neo4j3 mentions

Querying the Trace GraphContext Graphs and Reasoning Memoryembeds the query task, queries the reasoning_trace_embedding vector index, and returns the closest matching traces — letting you compare how the agent reasoned about related tasks over1 mention
Why graphs over vector embeddingsLong-Term Memoryuses embeddings too — every entity node has an embedding property and a vector index1 mention
Installation and ConfigurationIntroduction to Agent Memoryclient handles the connection lifecycle, schema initialization, and vector index creation automatically on first1 mention

Building Knowledge Graphs with LLMs2 mentions

How to Construct a Knowledge Graph with an LLMLLM Graph Builderthese vectors into a Vector index allows you to perform semantic1 mention
Querying using CypherExploring your knowledge graphchunks in the knowledge graph can be queried using the vector index to find similar1 mention

Neo4j Agent Memory Workshop1 mention

Installation and ConfigurationIntroduction to Agent Memorycreates the vector index, then writes the lessons, their content, and the entities extracted from them, printing each count as it1 mention

All glossary terms