Neo4j Graph Data Science Docs
Docs
Neo4j DBMS
  • Getting Started
  • Operations
  • Migration and Upgrade
  • Status Codes
  • Java Reference
  • Kerberos Add-on
Neo4j Aura
Neo4j Tools
  • Neo4j Bloom
  • Neo4j Browser
  • Neo4j Data Importer
  • Neo4j Desktop
  • Neo4j Enterprise Studio
  • Neo4j Ops Manager
  • Neodash commercial
Neo4j Graph Data Science
  • Neo4j Graph Data Science Library
  • Neo4j Graph Data Science Client
  • Neo4j Graph Analytics for Snowflake
Cypher Query Language
  • Cypher
  • Cypher Cheat Sheet
  • APOC Library
Generative AI
  • Neo4j GraphRAG for Python
  • Embeddings and vector indexes tutorial
  • GenAI plugin
  • Vector search indexes
  • Vector search functions
  • GraphQL vector index search documentation
Create applications
  • Python Driver
  • Go Driver
  • Java Driver
  • JDBC Driver
  • JavaScript Driver
  • .Net Driver
  • Neo4j GraphQL Library
  • Neo4j Visualization Library
  • OGM Library
  • Spring Data Neo4j
  • HTTP API
  • Neo4j Query API
  • Bolt
Connect data sources
  • Neo4j Connector for Apache Spark
  • Neo4j Connector for Apache Kafka
  • Change Data Capture (CDC)
  • BigQuery to Neo4j
  • Google Cloud to Neo4j
Labs
GenAI Ecosystem
  • LLM Knowledge Graph Builder
  • Vector Index & Search
  • LangChain
  • LangChain.js
  • LlamaIndex
  • Haystack
  • DSPy
Developer Tools
  • APOC Extended
  • Aura CLI
  • arrows.app
  • Cypher Workbench
  • ETL Tool
  • NeoDash
Frameworks & Integrations
  • Needle Starter Kit
  • Neo4j Plugin for Liquibase
  • Neo4j Migrations
  • neomodel
RDF & Linked Data
  • Neosemantics (Java)
  • RDFLib-Neo4j (Python)
Get Help
Community Forum
Discord Chat
Product Support
Neo4j Developer Blog
Neo4j Videos
GraphAcademy
Beginners Courses
  • Neo4j Fundamentals
  • Cypher Fundamentals
  • Importing Data Fundamentals
  • Importing CSV Data
  • Graph Data Modeling
Data Scientist Courses
  • Get started with Graph Data Science
  • Path Finding
Generative AI Courses
  • Neo4j & Generative AI Fundamentals
  • Vector Indexes & Unstructured Data
  • Constructing Knowledge Graphs
  • Building Agents in Neo4j Aura
Neo4j Certification
  • Neo4j Certified Professional
  • Neo4j Graph Data Science Certification
Get Started Free
Theme
Light
Dark
Search
Skip to content
Neo4j Graph Data Science
Product Version
    • The Neo4j Graph Data Science Library Manual v2026.08
    • Introduction
    • Installation
      • Supported Neo4j versions
      • Neo4j Desktop
      • Neo4j Server
      • Neo4j on Docker
      • GDS Enterprise Edition
      • Configure Apache Arrow server
      • System Requirements
    • Getting started
      • Basic workflow
      • End-to-end workflow
      • Machine learning pipeline
    • Common usage
      • Memory Estimation
      • Projecting graphs
      • Running algorithms
      • Logging
      • Monitoring system
      • System Information
    • Graph management
      • Creating graphs
        • Cypher projection
        • Native projection
        • Apache Arrow projection
        • Filtering
        • Sampling
          • Random walk with restarts sampling
          • Common Neighbour Aware Random Walk sampling
        • Random generation
        • Cypher projection (deprecated)
      • Catalog operations
        • Listing graphs
        • Check if a graph exists
        • Dropping graphs
      • Reading from graphs
        • Streaming nodes
        • Streaming relationships
      • Updating graphs
        • Adding node labels
        • Converting directed relationships to undirected
        • Collapse Path
        • Scaling node properties
        • Dropping parts of the graph
      • Writing back to Neo4j
        • Writing node properties and labels
        • Writing relationships
      • Exporting graphs
        • Export to a new Neo4j database
        • Export to CSV
        • Export using Apache Arrow
      • Utility functions
      • Administration
        • Access control
        • Backup and restore
    • Graph algorithms
      • Syntax overview
      • Centrality
        • Article Rank
        • Articulation Points
        • Betweenness Centrality
        • Bridges
        • CELF
        • Closeness Centrality
        • Degree Centrality
        • Eigenvector Centrality
        • Harmonic Centrality
        • HITS
        • PageRank
      • Community detection
        • Approximate Maximum k-cut
        • Clique Counting
        • Conductance metric
        • HDBSCAN
        • K-1 Coloring
        • K-Core Decomposition
        • K-Means Clustering
        • Label Propagation
        • Leiden
        • Local Clustering Coefficient
        • Louvain
        • Modularity Optimization
        • Modularity metric
        • Speaker-Listener Label Propagation
        • Strongly Connected Components
        • Triangle Count
        • Weakly Connected Components
      • Similarity
        • Filtered K-Nearest Neighbors
        • Filtered Node Similarity
        • K-Nearest Neighbors
        • Node Similarity
        • Similarity functions
      • Path finding
        • All Pairs Shortest Path
        • A* Shortest Path
        • Bellman-Ford Single-Source Shortest Path
        • Breadth First Search
        • Longest Path for DAG
        • Delta-Stepping Single-Source Shortest Path
        • Depth First Search
        • Dijkstra Single-Source Shortest Path
        • Dijkstra Source-Target Shortest Path
        • Minimum Directed Steiner Tree
        • Minimum Weight k-Spanning Tree
        • Maximum flow
        • Minimum cost maximum flow
        • Minimum Weight Spanning Tree
        • Prize-Collecting Steiner Tree
        • Random Walk
        • Yen’s Shortest Path algorithm
      • DAG algorithms
        • Longest Path for DAG
        • Topological Sort
      • Node embeddings
        • FastPath
        • Fast Random Projection
        • GraphSAGE
        • HashGNN
        • Node2Vec
      • Topological link prediction
        • Adamic Adar
        • Common Neighbors
        • Preferential Attachment
        • Resource Allocation
        • Same Community
        • Total Neighbors
      • Pregel API
    • Machine learning
      • Pre-processing
        • Scale Properties
        • One Hot Encoding
        • Split Relationships
      • Node embeddings
        • Fast Random Projection
        • GraphSAGE
        • Node2Vec
        • HashGNN
        • FastPath
      • Node property prediction
        • Node classification pipelines
          • Configuring the pipeline
          • Training the pipeline
          • Applying a trained model for prediction
        • Node regression pipelines
          • Configuring the pipeline
          • Training the pipeline
          • Applying a trained model for prediction
      • Link prediction pipelines
        • Configuring the pipeline
        • Training the pipeline
        • Applying a trained model for prediction
        • Theoretical considerations
      • Pipeline catalog
        • Listing pipelines
        • Checking if a pipeline exists
        • Removing pipelines
      • Model catalog
        • Listing models
        • Checking if a model exists
        • Dropping models
        • Storing models on disk
        • Publishing models
      • Training methods
        • Logistic regression
        • Random forest
        • Multilayer Perceptron
        • Linear regression
      • Auto-tuning
    • Production deployment
      • Defaults and Limits
      • Transaction Handling
      • Using GDS and composite databases (formerly known as Fabric)
      • GDS with Neo4j cluster
      • GDS Configuration Settings
      • GDS Feature Toggles
    • Python client
    • Aura Graph Analytics
      • Quickstart
      • Cypher API
      • Machine Learning
    • Bloom visualization
    • Using AI tools with GDS
    • Appendix
      • Operations reference
        • Graph Catalog
        • Graph Algorithms
        • Machine Learning
        • Additional Operations
        • Configuration Settings
      • Migration from Graph Data Science library Version 1.x
        • Common changes
        • Graph projection
        • Graph listing
        • Graph drop
        • Memory estimation
        • Algorithms
        • Machine Learning
      • Migration from Legacy to new Cypher projection
      • Migration from Alpha Cypher Aggregation to new Cypher projection

Is this page helpful?

  • Neo4j Graph Data Science
  • Using AI tools with GDS
Raise an issue

Using AI tools with GDS

Neo4j Labs include additional AI tools for graph data science.

The main entry point for GDS is the GDS Agent, which includes an MCP server and a GDS-specific agent skill.

Other tools are available within the Neo4j Labs GenAI Ecosystem:

  • The GDS skill to interact with the GDS plugin (not for Aura Graph Analytics).

  • The AGA skill to create and manage sessions within Aura Graph Analytics (requires the GDS skill).

Machine Learning Operations reference

Graph Data Science courses on GraphAcademy

Follow our Graph Data Analytics learning path to learn how to apply graph thinking to your machine learning pipelines.

Enroll now

Products

  • Neo4j Graph Database
  • Neo4j AuraDB
  • Neo4j Graph Data Science
  • Deployment Center
  • Professional Services
  • Pricing

Developers

  • Developer Home
  • Documentation
  • Deployment Center
  • Developer Blog
  • Community
  • Virtual Events
  • GraphAcademy

Learn

  • Resource Library
  • Neo4j Blog
  • GraphAcademy
  • Research Center
  • Case Studies
  • Events Calendar
  • NODES 2026
  • Webinars

Company

  • About Us
  • Newsroom
  • Awards and Honors
  • Careers
  • Culture
  • Leadership
  • Support

Social Networks

© 2026 Neo4j, Inc. Terms | Privacy Policy | Sitemap

Neo4j®, Neo Technology®, Cypher®, Neo4j® Bloom™, Neo4j® AuraDB℠ and Neo4j® AuraDS℠ are registered trademarks of Neo4j, Inc. All other marks are owned by their respective companies.