Arango Documentation
Arango provides the trusted data foundation for the next wave of AI grounded in business context
User manuals by product
The full Arango Contextual Data Platform provides entity-aware retrieval, graph-based reasoning, temporal state management, and platform-level governance to support reliable, stateful agentic AI systems in production environments.
Supercharge your Contextual Data Platform with Ada, AutoGraph, GraphRAG, GraphML, Graph Analytics, queries generated from natural language, and machine learning infrastructure for AI-powered insights.
Enterprise-grade services for scalability, reliability, governance with Kubernetes orchestration, custom services with Bring Your Own Code, as well as a unified web interface with a Graph Visualizer and advanced Query Editor.
The native multi-model database system that unifies graph, document, key-value, full-text, and vector search with one query language.
Arango’s fully-managed cloud offering for a faster time to value, formerly known as ArangoGraph Insights Platform.
Official drivers, integrations, and adapters that help you connect ArangoDB and the Contextual Data Platform to your applications and data science tools, as well as an MCP server.
From graph to AI
Data Persistence
ArangoDB is a scalable database system that you can use to store JSON documents, which allows a flexible data structure for each record. ArangoDB natively supports graphs, letting you connect documents with edges to express relationships between records and build complex information networks.
Data Retrieval
You can query your data in various ways using the core database system. The native support for multiple data models lets you access information in different ways with a single query language called AQL. It has built-in support for aggregation, vector and full-text search, geo-spatial queries, and more.
Data Exploration
You can visually explore and interact with your ArangoDB graphs through an intuitive web interface called the Graph Visualizer. It is part of the Arango Platform Suite that builds on ArangoDB, extending it to a Kubernetes-native environment that unifies data management, monitoring, and automation.
Graph Queries
Utilizing connected data starts with running simple graph queries. Using ArangoDB and its query language, you can determine the shortest paths between nodes as well as execute graph traversals. A traversal starts at a given node of a graph and follows the directly connected edges. The edges indicate what the next connected nodes are, and this discovery of neighbors can repeat.
Graph queries can answer questions like
Who can introduce me to person X?
Graph Analytics
The next level of utilizing connected data in terms of complexity is to use graph analytics or graph algorithms to aggregate information about a graph. Unlike with graph queries, this involves the entire graph at once.
Graph analytics can answer questions like
Who are the most connected persons?
Arango offers a Graph Analytics solution included in the Agentic AI Suite to run algorithms such as connected components, label propagation, and PageRank on your data.
GraphML
For higher-level insights, you can use advanced graph-based data science. Applying machine learning on graphs lets you predict connections, get better product recommendations, and also classify nodes, edges, and graphs.
GraphML can answer questions like:
- Is there a connection between person X and person Y?
- Will a customer churn?
- Is this particular transaction anomalous?
Arango’s enterprise-ready, graph-powered machine learning capabilities are included in the Agentic AI Suite as part of the Arango Contextual Data Platform. See Arango GraphML.
GraphRAG
Generative AI often struggle with hallucinations because the connectedness of data is not properly or cleanly represented. GraphRAG is a technique that lets you ground GenAI applications in trusted context using the power of graph relationships and vector embeddings.
Arango’s GraphRAG included in the Agentic AI Suite is a turn-key solution to transform your organization’s data into a knowledge graph and let everyone utilize the knowledge by asking questions in natural language.
It automatically creates a knowledge graph from raw text by identifying and extracting entities and relationships within the data, groups and summarizes semantically similar entities, and stores everything in ArangoDB. When you ask a question, the large language model (LLM) is supplied with additional context from the knowledge graph, using lexical and semantic search. This enables accurate, context-aware intelligence grounded in enterprise data.
AutoGraph with AutoRAG
Arango AutoGraph extends GraphRAG by automatically discovering knowledge domains in your organization’s data and building a per-domain contextual knowledge graph. Its AutoRAG assigns each domain the right processing depth: full entity extraction for complex content, a lighter partition for simpler content.
It creates knowledge shards for AI agents and co-pilots that let you improve response accuracy, consistency, and explainability across enterprise AI applications.
