What is embedding?

Example

A film's title and plot, stored a second time as numbers.

cypher

MATCH (m:Movie {title:'Godfather, The'})
WHERE m.plot IS NOT NULL AND m.title IS NOT NULL
WITH m, m.title + ' ' + m.plot AS titleAndPlot
WITH m, ai.text.embed(titleAndPlot, 'OpenAI', { token: $openaiToken, model: 'text-embedding-3-small' }) AS vector
CALL db.create.setNodeVectorProperty(m, 'embedding', toFloatList(vector))
RETURN m.embedding AS embedding

m.embedding holds the embedding.

Lessons that use this term

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

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

Introduction to Vector Indexes and Unstructured Data123 mentions

Vectors and EmbeddingsVector indexeshave learned about embeddings and used them with vector indexes to find similar31 mentions
Creating embeddingsImporting unstructured datathe last lesson, embeddings were automatically created for you by the17 mentions
Searching imagesIntroductionprevious lessons, you learned how vectors and embeddings can represent data in different7 mentions
Query a Vector IndexVector indexesuse the Question and Answer embeddings to find similar16 mentions
VectorsIntroductionreferring to vectors in the context of machine learning and NLP, the term "embedding" is typically16 mentions
Create a Vector IndexVector indexesquery embeddings, you need to create a vector7 mentions
Load embeddingsVector indexesthis lesson, you will learn how to load embeddings into a Neo4j7 mentions
Finding Movie PlotsIntroductionsearch works by comparing numerical representations of the text (known as embeddings4 mentions
Create the Answer Vector IndexVector indexesThe embedding has 15361 mention
Create a graphImporting unstructured dataeach chunk, you have to create an embedding of the text and extract the5 mentions
Import data with Python and LangChainImporting unstructured datayou will use Python and LangChain to chunk up course content and create embeddings for each5 mentions
Getting StartedIntroductionthis course, you will explore the concepts of semantic search, embedding, and1 mention
ChunkingImporting unstructured datapieces of data are easier to work with and process. Embedding models also have size (token) limits and can only handle a certain amount of3 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

Context Graphs: Agent Memory with Neo4j28 mentions

Why graphs over vector embeddingsLong-Term Memorymight ask: why not rely on vector embeddings alone for long-term agent13 mentions
Querying the Trace GraphContext Graphs and Reasoning Memoryyou need to run the similarity search in raw Cypher, pass the query embedding as a parameter rather than iterating over stored4 mentions
Installation and ConfigurationIntroduction to Agent Memorylibrary calls a language model to extract entities from messages, and an embedding model to make memory3 mentions
Promote entities to long-term memoryLong-Term Memorywhich calls the language model to find the entities in it, then generates an embedding for each1 mention
Why Graphs for Agent MemoryIntroduction to Agent Memoryuses vector embeddings too — every Message and Entity node has an embedding property for semantic2 mentions

Using Neo4j with LangChain15 mentions

Vector SearchVectorshave been created for 1000 movie12 mentions
Vector RetrieverVectorsan embedding3 mentions

Neo4j and Generative AI Workshop32 mentions

Vector RAGRetrievalreferring to vectors in the context of machine learning and NLP, the term "embedding" is typically18 mentions
Constructing knowledge graphsKnowledge Graph Constructionfor querying and searching the data, you may need to create vector embeddings6 mentions
Vector + Cypher retrieverRetrievalThe chunks in the knowledge graph include vector embeddings that allow for similarity search based on vector4 mentions
Create a graphKnowledge Graph ConstructionCreate embeddings for each2 mentions

Neo4j & GenerativeAI Fundamentals40 mentions

Vector RAGRetrieval Augmented Generation (RAG)referring to vectors in the context of machine learning and NLP, the term "embedding" is typically18 mentions
Vector IndexesRetrieval Augmented Generation (RAG)In the last lesson, you learned about embeddings, vectors and their role in16 mentions
Vector RetrieverIntegrating Neo4j with Generative AIYou must use the same embedding model as the one used to create the movie plots embeddings, text-embedding-ada-002, to ensure the vectors are3 mentions

Building Agents in Neo4j Aura18 mentions

Using the Similarity Search toolBuilding an AgentSimilarity Search tool finds nodes whose vector embeddings are closest to the embedding of the user's10 mentions
Designing and managing agentsIntroduction to Aura AgentSearch requires your graph nodes to have vector embeddings stored as properties, and a vector index built on those4 mentions

Analyze Graph Data with Python23 mentions

Scaled Properties and FastRP EmbeddingsGDS Python ClientEmbeddings encode them into vectors for machine22 mentions

Constructing Knowledge Graphs with Neo4j GraphRAG for Python12 mentions

Constructing knowledge graphsIntroductionfor querying and searching the data, you may need to create vector embeddings6 mentions
Vector + Cypher retrieverRetrievalchunks in the knowledge graph include vector embeddings that allow for similarity search based on vector4 mentions
Create a graphKnowledge Graph PipelineCreate embeddings for each2 mentions

Building Knowledge Graphs with LLMs10 mentions

How to Construct a Knowledge Graph with an LLMLLM Graph Builderfor querying and searching the data, you may need to create vector embeddings6 mentions

Aura Graph Analytics fundamentals12 mentions

Train and publish machine learning modelsAura Graph Analytics in the Aura Workspacein a single call, takes node features and a graph, and produces embeddings you can mutate, stream, or write10 mentions
Drive AGA from the neo4j driverFrom the Python clientyou're embedding AGA into an existing app, a batch script, or a service that already speaks Neo4j, you can drive AGA from the plain2 mentions

Neo4j Agent Memory Workshop15 mentions

Facts and PreferencesLong-term Memorycarries an embedding of the whole statement, so it is found by semantic similarity rather than by2 mentions
Entities and RelationshipsLong-term Memorydoes not give those entities an embedding, so search_entities can't find them by meaning6 mentions

Graph Data Science in Practice6 mentions

Applying AlgorithmsGDS Foundationsdifferently Apply community detection, similarity, pathfinding, and embedding algorithms Choose the right algorithm category based on your analytical3 mentions

All glossary terms