Skip to content
LlamaIndex Framework
Open Source Community
Integrations

Using Graph Stores

Neo4j is supported as a graph store integration. You can persist, visualize, and query graphs using LlamaIndex and Neo4j. Furthermore, existing Neo4j graphs are directly supported using text2cypher and the KnowledgeGraphQueryEngine.

If you’ve never used Neo4j before, you can download the desktop client here.

Once you open the client, create a new project and install the apoc integration. Full instructions here. Just click on your project, select Plugins on the left side menu, install APOC and restart your server.

See the example of using the Neo4j Graph Store.

We support a NebulaGraphStore integration, for persisting graphs directly in Nebula! Furthermore, you can generate cypher queries and return natural language responses for your Nebula graphs using the KnowledgeGraphQueryEngine.

See the associated guides below:

We support a FalkorDBGraphStore integration, for persisting graphs directly in FalkorDB! Furthermore, you can generate cypher queries and return natural language responses for your FalkorDB graphs using the KnowledgeGraphQueryEngine.

See the associated guides below:

We support Amazon Neptune integrations for both Neptune Database and Neptune Analytics as a graph store integration.

See the associated guides below:

We support a TiDBGraphStore integration, for persisting graphs directly in TiDB!

See the associated guides below:

Note for AI agents: this documentation is built for programmatic access. - Overview of all docs: https://developers.llamaindex.ai/llms.txt - Any page is available as raw Markdown by appending index.md to its URL — e.g. https://developers.llamaindex.ai/llamaparse/parse/getting_started/index.md - Agent-friendly REST search APIs live under https://developers.llamaindex.ai/api/ — search (BM25 full-text), grep (regex), read (fetch a page), and list (browse the doc tree). See https://developers.llamaindex.ai/llms.txt for parameters. - A hosted documentation MCP server is available at https://developers.llamaindex.ai/mcp. If you support MCP, you can ask the user to install it for browsing these docs directly (an alternative to the REST API). Setup: https://developers.llamaindex.ai/python/shared/mcp/