What is vector?

Example

Three words, each as a list of two numbers.

text

dog          [0.9, 0.1]
puppy        [0.8, 0.2]
carburettor  [0.1, 0.9]

Measured in a straight line, dog and puppy are 0.14 apart. Dog and carburettor are 1.13 apart.

A vector from an embedding model normally holds hundreds or thousands of numbers rather than two.

Distance can be measured in more than one way. Neo4j offers cosine and Euclidean, set on the vector index. The Graph Data Science library adds Pearson and a true Euclidean distance.

Vectors are often used to represent semantic meaning, but that is a convention, not a limitation.

Lessons that use this term

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

70 lessons use this term. The 40 with the highest term density are listed here.

Introduction to Vector Indexes and Unstructured Data53 mentions

VectorsIntroductionVectors are a fundamental concept in linear34 mentions
Getting StartedIntroductionto "Introduction to Vector Indexes and Unstructured3 mentions
Create the Answer Vector IndexVector indexesproperty contains the answer text, and the embedding property is the vector representation of the answer2 mentions
Unstructured dataIntroductionwill also learn how vectors and graphs can help you understand and find the data you need, even when it's4 mentions
Searching imagesIntroductionprevious lessons, you learned how vectors and embeddings can represent data in different2 mentions
Create a Vector IndexVector indexesthe speed of similarity searches by pre-computing the similarity between vectors and storing them in the2 mentions
Structured and Unstructured DataImporting unstructured dataindexes and embeddings go some way to allow you to search and query unstructured data, but they are not a complete2 mentions
Vectors and EmbeddingsVector indexeshave learned about embeddings and used them with vector indexes to find similar2 mentions

Neo4j and Generative AI Workshop48 mentions

Vector RAGRetrievalthis lesson, you will learn about semantic search and how vector indexes can help you find relevant information from a user's30 mentions
Vector + Cypher retrieverRetrievalThe chunks in the knowledge graph include vector embeddings that allow for similarity search based on vector6 mentions
Constructing knowledge graphsKnowledge Graph Constructionrequirements for querying and searching the data, you may need to create vector5 mentions
Create an agentAgentstools that run Cypher queries against the graph and return the results Vector + Cypher retrievers to semantically search the knowledge1 mention
Search lesson contentAgentslesson, you will enhance your agent by adding a search lesson tool using a vector + cypher2 mentions

Neo4j & GenerativeAI Fundamentals64 mentions

Vector RAGRetrieval Augmented Generation (RAG)this lesson, you will learn about semantic search and how vector indexes can help you find relevant information from a user's30 mentions
Vector RetrieverIntegrating Neo4j with Generative AIthis lesson, you will create a vector retriever to retrieve relevant data from6 mentions
Vector IndexesRetrieval Augmented Generation (RAG)In the last lesson, you learned about embeddings, vectors and their role in13 mentions
RAG PipelineIntegrating Neo4j with Generative AIthis lesson, you will use the vector retriever you created to pass additional context to an LLM allowing it to generate more accurate and relevant5 mentions
GenAI FrameworksIntegrating Neo4j with Generative AILLM usage, prompt and output management. Embedding model integration . Vector and database integration (including2 mentions
GraphRAGRetrieval Augmented Generation (RAG)can be used in conjunction with vector4 mentions
Graph-Enhanced Vector RetrieverIntegrating Neo4j with Generative AIallows you to perform vector searches and then traverse the graph to find related nodes or2 mentions

Using Neo4j with LangChain23 mentions

Vector RetrieverVectorsthis lesson, you will update the LangChain agent to use a vector retriever that will allow you to search for movies based on7 mentions
Vector SearchVectorsthis lesson, you will learn how to use vectors indexes with LangChain to perform vector10 mentions
Graph RetrievalVectorscan enhance a vector retriever using GraphRAG to include additional6 mentions

Analyze Graph Data with Python33 mentions

Scaled Properties and FastRP EmbeddingsGDS Python Clientencode them into vectors for machine31 mentions

Importing CSV data into Neo4j2 mentions

Congratulations and Next StepsImporting data considerationsgraph more performant with Cypher constraints and indexes Introduction to Vector Indexes and Unstructured Data - Understand and search2 mentions

Context Graphs: Agent Memory with Neo4j27 mentions

Why graphs over vector embeddingsLong-Term Memorymight ask: why not rely on vector embeddings alone for long-term agent7 mentions
Why Graphs for Agent MemoryIntroduction to Agent Memorynot a vector database, a relational database, or a document6 mentions
Store your first memoryIntroduction to Agent Memorylonger than later ones, because the library creates its constraints and vector indexes before writing1 mention
Entity Extraction PipelineLong-Term Memorythe previous lesson, you learned why a graph outperforms a pure vector store for long-term memory — multi-hop traversal, temporal validity, and combined vector-plus-graph search are all2 mentions
Querying the Trace GraphContext Graphs and Reasoning Memorycorrect pattern uses a single query vector $query_embedding from outside the2 mentions
The reasoning memory schemaContext Graphs and Reasoning Memory| Archival — permanent audit history | | Access pattern | Trace lookup and vector similarity for precedent search | | Primary question | "How did you reach this conclusion?"2 mentions

Building Agents in Neo4j Aura11 mentions

Using the Similarity Search toolBuilding an AgentSimilarity Search tool finds nodes whose vector embeddings are closest to the embedding of the user's5 mentions

Constructing Knowledge Graphs with Neo4j GraphRAG for Python13 mentions

Vector + Cypher retrieverRetrievalchunks in the knowledge graph include vector embeddings that allow for similarity search based on vector7 mentions
Constructing knowledge graphsIntroductionrequirements for querying and searching the data, you may need to create vector5 mentions

Building Knowledge Graphs with LLMs12 mentions

How to Construct a Knowledge Graph with an LLMLLM Graph Builderrequirements for querying and searching the data, you may need to create vector5 mentions
Querying using CypherExploring your knowledge graphpipeline | ENABLES | [Benefit] | more accurate responses | | [Skill] | Vector Indexes | USE_IN | [Technology] | Neo4J | | [Technology] | Pip | INSTALLS | [Technology] | Youtube-Search6 mentions

Graph Data Science in Practice5 mentions

Applying AlgorithmsGDS FoundationsEmbeddings convert nodes into vector representations that capture their structural5 mentions

Aura In Production3 mentions

Monitoring database store sizeMonitoring Database Healthembeddings and vector indexes are particularly storage-intensive and may warrant2 mentions

Neo4j Management, Optimization, and Refactoring Workshop2 mentions

Database Store Size ManagementAura Administrationembeddings and vector indexes are particularly storage-intensive and may warrant2 mentions

Neo4j Agent Memory Workshop3 mentions

Configure the Memory ClientShort-term Memorysets the provider and model that turn messages, entities, and traces into vectors, so you can search memory by meaning rather than by exact2 mentions

All glossary terms