> ## Documentation Index
> Fetch the complete documentation index at: https://docs.falkordb.com/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> FalkorDB is a graph database that speaks the Redis protocol. Queries are issued as OpenCypher through the GRAPH.QUERY and GRAPH.RO_QUERY commands, not over Bolt or a SQL connection.
> FalkorDB implements a subset of OpenCypher with proprietary extensions. Do not assume Neo4j-only syntax or procedures are available — check /cypher/cypher-support and /cypher/known-limitations before using a clause.
> FalkorDB is the successor to RedisGraph, but they are separate products. Do not present RedisGraph commands, versions, or limitations as current FalkorDB behavior.
> Use the official clients listed in /getting-started/clients rather than generic Redis or Neo4j drivers, and prefer the language the user is already working in.
> Configuration parameters are set with GRAPH.CONFIG SET or at startup; cite the exact parameter name from /getting-started/configuration rather than inventing one.
> This site covers four products: FalkorDB (core), FalkorDB Cloud, FalkorDB Enterprise, and the GraphRAG SDK. Name which one an answer applies to, since setup and operations differ.

# GenAI Tools

> Build intelligent GenAI applications with FalkorDB and LLMs using popular GraphRAG and agent frameworks like LangChain and LlamaIndex.

FalkorDB provides powerful tools and integrations for building intelligent GenAI applications with graph databases and Large Language Models (LLMs).

## Topics in This Section

* [GraphRAG SDK](/genai-tools/graphrag-sdk): Build intelligent GraphRAG applications with FalkorDB and LLMs, self-hosted with the SDK or fully hosted with [GraphRAG Server](https://graphrag.falkordb.com/). Full documentation at [docs.graphrag.falkordb.com](/graphrag).
* [AG2](/genai-tools/ag2): Build multi-agent AI systems with AG2 (formerly AutoGen) and FalkorDB GraphRAG.
* [LangChain](/genai-tools/langchain): Integration with LangChain for AI agents with memory (Python and JavaScript/TypeScript).
* [LangGraph](/genai-tools/langgraph): Build stateful, multi-actor agentic applications with LangGraph.
* [LlamaIndex](/genai-tools/llamaindex): Simplify development of LLM-powered applications with LlamaIndex.
* [GraphRAG Toolkit](/genai-tools/graphrag-toolkit): AWS GraphRAG Toolkit integration for building knowledge graph applications.
* [FalkorDB MCP Server](/genai-tools/mcpserver): Enable AI assistants like Claude to interact with FalkorDB using the Model Context Protocol.
* [QueryWeaver](/genai-tools/queryweaver): Open-source Text2SQL tool that converts plain-English questions into SQL using graph-powered schema understanding.
* [Code-Graph](/genai-tools/code-graph): Visualize codebases as knowledge graphs to analyze dependencies, detect bottlenecks, and query code structure.

## Frequently Asked Questions

<AccordionGroup>
  <Accordion title="What are FalkorDB GenAI Tools?">
    FalkorDB GenAI Tools are a collection of integrations and SDKs that enable developers to build intelligent AI applications using graph-based knowledge retrieval. They include GraphRAG SDK, LangChain/LlamaIndex integrations, AG2 multi-agent framework, LangGraph, MCP Server, QueryWeaver, and Code-Graph.
  </Accordion>

  <Accordion title="Which LLM providers are supported?">
    FalkorDB GenAI Tools support multiple LLM providers including **OpenAI**, **Google Gemini**, **Anthropic**, **Groq**, **Cohere**, and **Azure OpenAI**. The specific providers available depend on the tool you are using.
  </Accordion>

  <Accordion title="Do I need a running FalkorDB instance to use these tools?">
    Yes, all GenAI Tools require a FalkorDB instance. You can run one locally with `docker run -p 6379:6379 -it --rm falkordb/falkordb:edge` or use [FalkorDB Cloud](https://app.falkordb.cloud) for a managed solution.
  </Accordion>

  <Accordion title="What is GraphRAG and how does FalkorDB implement it?">
    GraphRAG (Graph Retrieval-Augmented Generation) combines knowledge graphs with LLMs to provide more accurate, contextual, and explainable AI responses. FalkorDB implements GraphRAG by storing data as a graph, converting natural language to Cypher queries, and using the retrieved graph data to generate answers.
  </Accordion>

  <Accordion title="Which programming languages are supported?">
    Most FalkorDB GenAI Tools support **Python** as the primary language. The LangChain integration also supports **JavaScript/TypeScript**. The MCP Server is built with Node.js. Code-Graph analyzes Python, Java, and C# codebases.
  </Accordion>
</AccordionGroup>