skills.rest
eklyukin
eklyukinCOMMUNITY
Explore all skills by this author →
GitHub

neo4j-aura-graph-analytics-skill

Runs GDS algorithms in serverless Aura Graph Analytics sessions via the Python client.

Updated Jul 24, 2026
Search Tags:#python#aura#neo4j#pagerank#gds#graph analytics#graph projection
One-click install
npx skills add https://github.com/eklyukin/my-ai-config --skill neo4j-aura-graph-analytics-skill-eklyukin
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: neo4j-aura-graph-analytics-skill
Source: https://github.com/eklyukin/my-ai-config/tree/main/skills/neo4j-aura-graph-analytics-skill
Command: npx skills add https://github.com/eklyukin/my-ai-config --skill neo4j-aura-graph-analytics-skill-eklyukin

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires graphdatascience, and includes references (resource) components.

What problem does it solve? Running graph algorithms at scale normally requires installing and sizing the embedded GDS plugin on a Neo4j database, which competes with production workloads for resources. This Skill guides agents through Aura Graph Analytics (AGA), Neo4j's serverless GDS compute environment, so algorithms run in isolated ephemeral sessions billed per minute without touching the live database. ## Core Features & Use Cases - Session Lifecycle Management: Authenticate with Aura API credentials, estimate memory with sessions.estimate(), create or reconnect to sessions with get_or_create(), set TTLs, and delete sessions to stop billing. - Three Data Source Modes: Project graphs from a connected AuraDB instance, a self-managed Neo4j database, or standalone Pandas/Spark DataFrames via gds.v2.graph.construct(). - Algorithm Execution & Write-Back: Run PageRank, FastRP, Louvain and other algorithms in mutate/stream/write modes, poll async jobs, stream node properties, and write results back to the connected database before cleanup. - Use Case: A data scientist needs PageRank and embeddings over a 1M-node social graph in AuraDB. The Skill walks through credential setup, memory tier selection, remote projection with gds.graph.project.remote(), algorithm chaining, and write-back — all inside an isolated session deleted afterward. ## Quick Start Ask the agent to create an Aura Graph Analytics session, project a graph from your Neo4j database, and run PageRank on it.

Frequently Asked Questions about neo4j-aura-graph-analytics-skill

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run GDS algorithms on Neo4j Aura without the embedded plugin?▼

Use Aura Graph Analytics sessions via the graphdatascience Python client. Authenticate with AuraAPICredentials.from_env(), create a session with GdsSessions.get_or_create(), project a graph remotely, and run algorithms through gds.v2 endpoints like gds.v2.page_rank.mutate().

How to project a graph into an Aura Graph Analytics session?▼

For connected Neo4j, call gds.v2.graph.project() with a query containing gds.graph.project.remote(). For standalone data, use gds.v2.graph.construct() with Pandas DataFrames containing nodeId, labels, sourceNodeId, targetNodeId, and relationshipType columns.

Does Aura Graph Analytics work with Aura Pro or self-managed Neo4j?▼

AGA works with Aura Business Critical and VDC tiers, plus self-managed Neo4j via a Bolt URI and cloud location. Aura Pro uses the embedded GDS plugin instead, which is covered by the neo4j-gds-skill, not this one.

What is the difference between Aura Graph Analytics and the embedded GDS plugin?▼

AGA runs in isolated serverless sessions billed per minute and supports non-Neo4j data sources like Pandas and Spark. The embedded plugin shares database resources, supports topological link prediction and persistent ML models, and is included with Aura Pro.

Why does my Aura Graph Analytics session return SessionNotFoundError?▼

The session expired because its TTL elapsed or the name is misspelled. List active sessions with sessions.list() to verify, then recreate the session with get_or_create() and re-project your graph before running algorithms.

How do I avoid unexpected Aura Graph Analytics billing costs?▼

Set a TTL when creating the session (default 1 hour idle, maximum 7 days) and delete the session when finished using sessions.delete() or gds.delete(). Always write or stream results before deletion, since unwritten results are lost.

Related Skills

Explore More Data & Analytics Skills→
FalkorDBFalkorDB
22

Migrate Neo4j to FalkorDB

Extracts Neo4j nodes and relationships into CSV files for FalkorDB import.

Official
Intermediate
neo4j-contribneo4j-contrib
101

neo4j-snowflake-graph-analytics-skill

Run Neo4j Graph Analytics algorithms on Snowflake tables via SQL CALL.

Official
Intermediate
truongnattruongnat

nestjs-neo4j-pro

Integrates NestJS applications with Neo4j for graph data modeling, Cypher queries, and session management.

Community
Advanced
neo4j-contribneo4j-contrib
101

neo4j-gds-skill

Execute Neo4j GDS algorithms via graph projections and stream, stats, mutate, or write modes.

Official
Advanced