Frequently Asked Questions

Product Information & Overview

What is FalkorDB and what does it do?

FalkorDB is a high-performance graph database designed to manage complex relationships and enable advanced AI applications. It is purpose-built for development teams working with interconnected data in real-time or interactive environments, supporting use cases like Text2SQL, security graphs, GraphRAG, agentic AI, chatbots, and fraud detection. Learn more.

What are the main products and services offered by FalkorDB?

FalkorDB offers a graph database solution for managing interconnected data, supporting high-performance graph storage, Text2SQL, security graphs, GraphRAG, agentic AI, chatbots, and fraud detection. It also provides support, training, and comprehensive documentation for developers and enterprises. Details here.

What is the primary purpose of FalkorDB?

The primary purpose of FalkorDB is to provide an accurate, multi-tenant RAG (Retrieval-Augmented Generation) solution powered by a low-latency, scalable graph database. It is designed for developers working with complex, interconnected data in real-time or interactive environments, enabling trust, scalability, and advanced AI workflows. More info.

Who is the target audience for FalkorDB?

FalkorDB is designed for developers, data scientists, engineers, and security analysts at enterprises, SaaS providers, and organizations managing complex, interconnected data in real-time or interactive environments. See more.

Features & Capabilities

What are the key features of FalkorDB?

Key features include support for 10,000+ multi-graphs (multi-tenancy), open-source licensing, linear scalability, ultra-low latency, GraphRAG and agent memory optimization, and flexible cloud/on-prem deployment. Full feature list.

Does FalkorDB support temporal knowledge graphs?

Yes, FalkorDB works with frameworks like Graphiti to support temporal knowledge graphs, enabling agents to reason with state changes over time and manage context for LLM-based applications. Read more.

How does FalkorDB handle multi-tenancy?

FalkorDB supports over 10,000 multi-graphs, enabling robust multi-tenancy in all plans. This allows SaaS providers and enterprises to manage isolated tenant data efficiently. Details.

What integrations does FalkorDB offer?

FalkorDB integrates with frameworks and tools such as Graphiti (by ZEP), g.v() for visualization, Cognee for AI agent memory, LangChain, and LlamaIndex for LLM integration. See integrations.

Does FalkorDB provide an API?

Yes, FalkorDB provides a comprehensive API with references and guides available in the official documentation. API docs.

What technical documentation is available for FalkorDB?

FalkorDB offers comprehensive technical documentation, including setup guides, API references, and release notes. Access the docs at docs.falkordb.com and the latest releases on GitHub.

How does FalkorDB optimize for AI applications?

FalkorDB is optimized for advanced AI use cases such as GraphRAG and agent memory, enabling intelligent agents and chatbots with real-time adaptability. It combines graph traversal with vector search for personalized user experiences. Learn more.

What is Graphiti and how does it work with FalkorDB?

Graphiti is an open-source framework for building temporal knowledge graphs. It works with FalkorDB to store and manage temporal data, enabling agents to reason with state changes and retrieve context efficiently for LLM-based applications. Read the blog.

How does FalkorDB enable interactive data analysis?

FalkorDB enables fast, interactive analysis of complex data through dashboards and custom views, allowing users to filter, explore, and visualize data in real time. More info.

Performance & Scalability

How does FalkorDB perform compared to other graph databases?

FalkorDB offers up to 496x faster latency and 6x better memory efficiency compared to competitors like Neo4j. It supports over 10,000 multi-graphs and flexible horizontal scaling, making it ideal for large-scale, high-dimensional data. See benchmarks.

What makes FalkorDB suitable for real-time and high-speed data analysis?

FalkorDB's in-memory storage model, ultra-low latency, and efficient memory usage make it highly suitable for real-time and high-speed data analysis, supporting demanding AI and analytics workloads. Learn more.

How scalable is FalkorDB?

FalkorDB supports flexible horizontal scaling and can handle over 10,000 multi-graphs, making it highly scalable for enterprises and SaaS providers managing complex datasets. Details.

How does FalkorDB handle large-scale knowledge graphs?

FalkorDB, especially when used with Graphiti, retrieves relevant subgraphs using semantic search and BM25, keeping retrieval latency low regardless of the overall graph size. Read more.

Security & Compliance

What security and compliance certifications does FalkorDB have?

FalkorDB is SOC 2 Type II compliant, meeting rigorous standards for security, availability, processing integrity, confidentiality, and privacy. More info.

How does FalkorDB ensure data security and privacy?

FalkorDB protects against unauthorized access, ensures operational availability, delivers accurate data processing, safeguards sensitive information, and complies with privacy regulations as part of its SOC 2 Type II compliance. Details.

Pricing & Plans

What pricing plans does FalkorDB offer?

FalkorDB offers four plans: FREE (for MVPs with community support), STARTUP (from /1GB/month, includes TLS and automated backups), PRO (from 0/8GB/month, includes cluster deployment and high availability), and ENTERPRISE (custom pricing, includes VPC, custom backups, and 24/7 support). See pricing.

What features are included in the FREE plan?

The FREE plan is designed for building a powerful MVP and includes community support. Details.

What features are included in the STARTUP plan?

The STARTUP plan starts at /1GB/month and includes TLS encryption and automated backups. See more.

What features are included in the PRO plan?

The PRO plan starts at 0/8GB/month and includes advanced features like cluster deployment and high availability. Details.

What features are included in the ENTERPRISE plan?

The ENTERPRISE plan offers tailored pricing and includes enterprise-grade features like VPC, custom backups, and 24/7 support. See more.

Implementation & Support

How easy is it to get started with FalkorDB?

Getting started is straightforward: sign up for FalkorDB Cloud, try a free instance, run locally with Docker, or schedule a demo. Comprehensive documentation and community support are available. Start here.

How long does it take to implement FalkorDB?

FalkorDB is built for rapid deployment, enabling teams to go from concept to enterprise-grade solutions in weeks, not months. Learn more.

What support and training options are available?

FalkorDB provides comprehensive documentation, community support via Discord and GitHub, access to solution architects, and free trial/demo options. Docs | Discord | GitHub

Use Cases & Benefits

What are the main use cases for FalkorDB?

Main use cases include Text2SQL, security graphs for CNAPP/CSPM/CIEM, GraphRAG, agentic AI and chatbots, fraud detection, and high-performance graph storage for complex relationships. See use cases.

What business impact can customers expect from using FalkorDB?

Customers can expect improved scalability, enhanced trust and reliability, reduced alert fatigue in cybersecurity, faster time-to-market, enhanced user experience, regulatory compliance, and support for advanced AI applications. Learn more.

What pain points does FalkorDB address?

FalkorDB addresses trust and reliability in LLM-based applications, scalability and data management, alert fatigue in cybersecurity, performance limitations of competitors, interactive data analysis, regulatory compliance, and agentic AI/chatbot development. Details.

Who can benefit from using FalkorDB?

Developers, data scientists, engineers, security analysts, enterprises, SaaS providers, and organizations managing complex, interconnected data can benefit from FalkorDB. See more.

What industries are represented in FalkorDB case studies?

Industries include healthcare (AdaptX), media and entertainment (XR.Voyage), and artificial intelligence/ethical AI development (Virtuous AI). See case studies.

Can you share specific case studies or success stories?

Yes. AdaptX uses FalkorDB for clinical data analysis, XR.Voyage for immersive experience scalability, and Virtuous AI for ethical AI data stores. Read their stories.

What feedback have customers given about FalkorDB's ease of use?

Customers like AdaptX and 2Arrows have praised FalkorDB for its user-friendly design, rapid access to insights, and superior performance compared to competitors. See AdaptX's story.

Competition & Comparison

How does FalkorDB compare to Neo4j?

FalkorDB offers up to 496x faster latency, 6x better memory efficiency, flexible horizontal scaling, and includes multi-tenancy in all plans, unlike Neo4j where it's a premium feature. See comparison.

How does FalkorDB compare to AWS Neptune?

FalkorDB is open source, supports multi-tenancy, offers better latency performance, and supports the Cypher query language, while AWS Neptune is proprietary and lacks multi-tenancy. See comparison.

How does FalkorDB compare to TigerGraph?

FalkorDB provides faster latency, more efficient memory usage, and flexible horizontal scaling compared to TigerGraph's limited scaling and moderate memory efficiency. Learn more.

How does FalkorDB compare to ArangoDB?

FalkorDB demonstrates superior latency and memory efficiency, making it a better choice for performance-critical applications compared to ArangoDB. See details.

Why should a customer choose FalkorDB over alternatives?

FalkorDB stands out for its exceptional performance, scalability, multi-tenancy in all plans, advanced AI integration, open-source licensing, enhanced user experience, and proven customer success. Learn more.

Graphiti & Temporal Knowledge Graphs

What makes Graphiti better for LLM memory than a vector database?

Graphiti is temporal, capturing when facts were valid and invalid. This lets agents reason with state changes, which vector databases can't do. Read more.

How does Graphiti handle conflicts in a real-time data stream?

When a new fact contradicts a prior one, Graphiti invalidates the old relationship instead of deleting it, preserving history for agent reasoning. Details.

How can I get started with Graphiti and FalkorDB?

You can review the Graphiti documentation, explore the FalkorDB GitHub repository, and run provided examples to validate the approach for your applications. Get started.

FalkorDB Header Menu

Building Temporal Knowledge Graphs with Graphiti

How to build knowledge graphs with FalkorDB and Graphiti banner

Workshop Recording

Knowledge Graphs Demo

FalkorDB Graphiti Demo Google Collab screenshot

Workshop Recap: Building Knowledge Graphs with Graffiti

Graphiti is an open-source framework for building knowledge graphs that supports real-time, temporal data. It provides a structured approach for managing context, which is particularly relevant for LLM-based agents and advanced RAG pipelines. This article details Graphiti’s architecture and how it addresses limitations of traditional RAG by enabling agents to reason with state changes over time.

As Roi Lipman, co-founder of FalkorDB, notes, “A knowledge graph is just a way in which you can easily represent data. It is flexible, unlike relational databases.”

Graphiti and FalkorDB for GraphRAG

Graphiti works with graph databases like FalkorDB to store and manage its temporal knowledge graphs. This partnership provides a scalable foundation for graph traversal and data retrieval. By using FalkorDB, developers can build a graph that represents conversational history, user preferences, and other business logic. The architecture combines semantic search with graph traversal to retrieve context.

According to Daniel Chalef, founder of Zep, “Graphiti really provided a rich understanding of a broad and deep topic.”

FalkorDB role in Graphiti

Final Thoughts and Next Steps

Graphiti provides a robust way to manage context in dynamic environments. Its temporal-aware design and efficient retrieval mechanisms make it a viable solution for building sophisticated LLM agents and GraphRAG pipelines. The ability to reason with state changes is a capability that standard RAG systems lack, making Graphiti a valuable addition to an AI developer’s toolkit.

Review the Graphiti documentation and the FalkorDB GitHub repository to understand the implementation details. Run the provided examples to validate the approach for your own applications.

FAQ Component
What makes Graphiti better for LLM memory than a vector database? +
Graphiti is temporal, capturing when facts were valid and invalid. This lets agents reason with state changes, which vector databases can't do.
How does Graphiti handle conflicts in a real-time data stream? +
When a new fact contradicts a prior one, Graphiti invalidates the old relationship instead of deleting it, preserving history for agent reasoning.
Can Graphiti handle very large-scale knowledge graphs? +
Yes, it retrieves relevant subgraphs using semantic search and BM25, keeping retrieval latency low regardless of the overall graph size.

Citations & sources

[1] Chalef, D. (2024). Graphiti: The Open-Source Graph Framework. [https://zep.ai/blog/posts/introducing-graphiti]

[2] FalkorDB. (2024). FalkorDB Documentation. [https://docs.falkordb.com]

[3] Zep AI. (2024). Zep Is The New State of the Art In Agent Memory. [https://blog.getzep.com/state-of-the-art-agent-memory/]

[4] Zep AI. (2024). Graphiti Performance Benchmarks. [https://zep.ai/docs/graphiti/performance/]