GraphAcademy

GenAI and GraphRAG

vector search

Finding the records whose vectors lie closest to a query vector.

Example

Snow White, and the three films whose plots sit nearest to it.

cypher
MATCH (snowWhite:Movie {title: 'Snow White'})
MATCH (movie:Movie)
  SEARCH movie IN (
    VECTOR INDEX moviePlots
    FOR snowWhite.embedding
    LIMIT 4
  ) SCORE AS similarityScore
RETURN movie.title AS title, similarityScore

FOR identifies the vector to search by. The database returns the four embedding vectors lying closest to Snow White. similarityScore shows how close each one is.

Lessons that use this term

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

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

Neo4j & GenerativeAI Fundamentals15 mentions

  • Graph-Enhanced Vector RetrieverIntegrating Neo4j with Generative AIof the relationships in the graph, you can create a retriever that uses both vector search and graph traversal to find relevant6 mentions
  • GraphRAGRetrieval Augmented Generation (RAG)A common approach to GraphRAG is to use a combination of vector search and graph8 mentions
  • What is RAG?Retrieval Augmented Generation (RAG)Full-text search Vector search Text to1 mention

Context Graphs: Agent Memory with Neo4j5 mentions

  • Why graphs over vector embeddingsLong-Term Memory"high-risk financial customer", a vector search returns the entities whose descriptions are closest in3 mentions
  • The Three Memory TypesIntroduction to Agent Memoryof one session | | Access pattern | Sequential — recent messages first; vector search for semantic recall | | Primary question | "What was discussed?"2 mentions

Neo4j and Generative AI Workshop8 mentions

  • GraphRAG?Generative AIFull-text search Vector search Text to7 mentions
  • Search lesson contentAgentsthat the retriever will use to add additional context to the vector search1 mention

Using Neo4j with LangChain4 mentions

  • Graph RetrievalVectorsquery receives the node and score variables yielded by the vector search2 mentions
  • Vector RetrieverVectorsVector search can be used in Retrieval Augmented Generation (RAG) applications to find relevant documents based on their1 mention
  • Vector SearchVectorslesson, you will learn how to use vectors indexes with LangChain to perform vector search1 mention

Building Knowledge Graphs with LLMs10 mentions

  • Querying using CypherExploring your knowledge graphentityId | mentions | | --- | --- | | Neo4J | 10 | | vector search | 10 | | LLM | 9 | | GraphRAG | 9 | | retriever | 79 mentions
  • Neo4j LLM Graph BuilderLLM Graph BuilderGeneration (RAG) approaches to answer questions, including GraphRAG, Vector Search, and1 mention

GraphRAG Hackathon3 mentions

  • Understanding GraphRAGIntroduction to GraphRAGcombines graph traversal with vector search to give LLMs richer3 mentions

Neo4j Fundamentals1 mention

  • Graphs Are EverywhereGraph Thinkingand generative AI](https://neo4j.com/generativeai/) combine vector search, knowledge graphs, and data science to build more accurate AI1 mention

AI on Your Lakehouse: Context Comes in Shapes, Not Queries2 mentions

  • Port the PatternPort the Patternsearch still has a seat - "find me a passage about X" - and works better here, because every hit carries its tree position and1 mention
  • The Outline ShapeNavigate What's There - Table of Contentscould swap in vector search and the outline shape is unchanged: this lesson is about giving the agent a navigable structure, not about which1 mention

Introduction to Vector Indexes and Unstructured Data1 mention

  • VectorsIntroductionthe v5.11 release, Neo4j has a Vector search index, allowing you to query for nodes based1 mention

Neo4j Agent Memory Workshop1 mention

Zero to Production Hands-On Workshop1 mention

  • AgentsAccess your dataSearch - Use embeddings and vector search to find relevant nodes based on a natural language1 mention

Building Agents in Neo4j Aura2 mentions

  • Introduction to Aura AgentIntroduction to Aura AgentSimilarity Search tool finds nodes based on semantic similarity using vector search1 mention
  • Designing and managing agentsIntroduction to Aura AgentCypher structure and aren't looking for a specific known value — they need vector search to find relevant1 mention

Related terms

retrieval-augmented generation
Fetching relevant context from an external data source as additional context to inform a language model's response.8 shared lessons
retriever
A component that searches a data source and returns the information relevant to a query. Often used to provide context for a language model.9 shared lessons
vector
An ordered list of numbers. Distance between two vectors measures how alike the things they represent are.16 shared lessons
GraphRAG
Retrieval-augmented generation whose context comes from a knowledge graph, so the model can follow the relationships between facts.10 shared lessons
embedding
Information represented as a numerical vector, positioned so that similar information sits close together.14 shared lessons
vector index
A structure over a vector property. The database searches it to find the vectors nearest a given one, rather than comparing every vector stored.7 shared lessons
generative AI
Models that produce new content rather than classifying or scoring content that already exists.5 shared lessons
large language model
A model trained on text to predict the next token, and so to generate language.12 shared lessons

All glossary terms