How do I start a local FalkorDB server?

You can start a local FalkorDB server easily using Docker. Run 'docker run -p 6379:6379 -it --rm falkordb/falkordb:latest' to launch FalkorDB locally. For more deployment options, refer to the official documentation.

What are the steps to build and query a knowledge graph from unstructured data using FalkorDB?

The process involves: 1) Extracting structured data from unstructured documents with Diffbot API, 2) Creating a knowledge graph and storing it in FalkorDB, and 3) Querying the graph using LangChain. This enables you to answer complex questions from unstructured data efficiently. See the full guide and code samples in the official blog post.

How quickly can I implement FalkorDB for my project?

FalkorDB is designed for rapid deployment, allowing teams to go from concept to enterprise-grade solutions in weeks, not months. You can get started immediately with FalkorDB Cloud, Docker, or by scheduling a demo. Comprehensive documentation and community support are available to accelerate onboarding.

Where can I find technical documentation and API references for FalkorDB?

All technical documentation and API references are available at docs.falkordb.com. For the latest updates and release notes, visit the GitHub Releases Page.

Is there a free trial or demo available for FalkorDB?

Yes, you can try FalkorDB for free by launching a cloud instance or running it locally with Docker. You can also schedule a personalized demo with the FalkorDB team via the demo page.

What is FalkorDB and what does it do?

FalkorDB is a high-performance graph database designed for managing complex relationships and enabling advanced AI applications. It supports real-time and interactive environments, making it ideal for use cases like Text2SQL, security graphs, GraphRAG, agentic AI, chatbots, and fraud detection. Learn more.

What are the key features of FalkorDB?

Key features include ultra-low latency (up to 496x faster than competitors), 6x better memory efficiency, support for 10,000+ multi-graphs (multi-tenancy), open-source licensing, linear scalability, advanced AI integration (GraphRAG, agent memory), and flexible deployment (cloud & on-prem). Source.

Does FalkorDB support integration with AI and LLM frameworks?

Yes, FalkorDB integrates with frameworks such as LangChain, LlamaIndex, Graphiti (by ZEP), and Cognee. These integrations enable advanced AI use cases like GraphRAG, agent memory, and natural language querying. Learn more.

What programming languages and APIs does FalkorDB support?

FalkorDB provides official API references and guides for developers, data scientists, and engineers. It supports integration with Python (via LangChain, LlamaIndex), and offers a Cypher query interface. See API documentation for details.

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. Source.

What deployment options are available for FalkorDB?

FalkorDB can be deployed in the cloud, on-premises, or locally via Docker. This flexibility supports a wide range of enterprise and developer needs. Documentation.

What pricing plans does FalkorDB offer?

FalkorDB offers four main 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 with VPC, custom backups, and 24/7 support). See details.

What features are included in the FREE plan?

The FREE plan is designed for building a powerful MVP and includes community support. It is ideal for developers and small teams starting with graph database projects. More info.

What advanced features are available in the PRO and ENTERPRISE plans?

The PRO plan includes advanced features like cluster deployment and high availability, starting at 0/8GB/month. The ENTERPRISE plan offers VPC, custom backups, 24/7 support, and tailored pricing for large-scale or regulated organizations. See all features.

What are the main use cases for FalkorDB?

FalkorDB is used for Text2SQL (natural language to SQL on complex schemas), security graphs (CNAPP, CSPM, CIEM), GraphRAG (advanced graph-based retrieval), agentic AI & chatbots, fraud detection, and high-performance graph storage for complex relationships. Explore use cases.

Who can benefit from using 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. Learn more.

What business impact can customers expect from FalkorDB?

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

What pain points does FalkorDB address?

FalkorDB addresses trust and reliability in LLM-based applications, scalability and data management challenges, alert fatigue in cybersecurity, performance limitations of competitors, interactive data analysis needs, regulatory compliance, and the development of agentic AI and chatbots. Source.

Can you share customer success stories using FalkorDB?

Yes, AdaptX used FalkorDB to analyze clinical data, XR.Voyage overcame scalability challenges in immersive media, and Virtuous AI built a high-performance, multi-modal data store for ethical AI. Read their stories in the case studies.

What industries are represented in FalkorDB's case studies?

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

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. Neo4j uses an on-disk storage model and offers multi-tenancy only in premium plans. See detailed comparison.

How does FalkorDB compare to AWS Neptune?

FalkorDB is open source, supports multi-tenancy, and provides better latency and memory efficiency. AWS Neptune is proprietary, has limited vector search, and does not support multi-tenancy. See comparison.

How does FalkorDB compare to TigerGraph and ArangoDB?

FalkorDB delivers faster latency, better memory efficiency, and flexible horizontal scaling compared to TigerGraph and ArangoDB, which have limited scaling and moderate memory efficiency. Source.

What makes FalkorDB different from other graph databases?

FalkorDB stands out with its in-memory storage model (written in C and Rust), open-source licensing, built-in multi-tenancy, advanced AI integration, and industry-leading performance metrics. Learn more.

Is FalkorDB SOC 2 Type II compliant?

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

What does SOC 2 Type II compliance mean for FalkorDB users?

SOC 2 Type II compliance means FalkorDB protects against unauthorized access, ensures system availability, delivers accurate data processing, safeguards confidentiality, and complies with privacy regulations. Learn more.

What support options are available for FalkorDB users?

Support options include comprehensive documentation, community support via Discord and GitHub Discussions, and access to solution architects for tailored advice. Enterprise customers receive 24/7 support. Contact support.

Where can I find tutorials and practical guides for FalkorDB?

Tutorials and guides are available on the FalkorDB blog, including step-by-step instructions for building knowledge graphs, integrating with LangChain, and more.

How do customers rate the ease of use of FalkorDB?

Customers like AdaptX and 2Arrows have praised FalkorDB for its user-friendly interface, rapid access to insights, and ease of running complex queries. See their feedback in the case studies.

What integrations does FalkorDB support?

FalkorDB supports integrations with Graphiti (by ZEP), g.v() for visualization, Cognee, LangChain, and LlamaIndex for advanced AI and LLM use cases. Learn more.

Can I visualize knowledge graphs built with FalkorDB?

Yes, you can use tools like g.v() for knowledge graph visualization and explore dashboards and custom views for interactive analysis. Try g.v().

Is FalkorDB open source?

Yes, FalkorDB is open source, encouraging community collaboration and transparency. Learn more.

Building & Querying a Knowledge Graph from Unstructured Data

Guy Korland
Date Published: August 16, 2023
Date Updated: August 23, 2024

Diffbot API, FalkorDB, and LangChain are a great combination for building intelligent applications that can understand and answer questions from unstructured data.

Diffbot API has a powerful API that can extract structured data from unstructured documents, such as web pages, PDFs, or emails. With Diffbot API, you can create a Knowledge graph that represents the entities and relationships in your documents, and store it in FalkorDB. Then, you can use Langchain, to query your Knowledge graph and get answers to your questions. Langchain can handle complex and natural queries, and return relevant and accurate answers from your Knowledge graph.

1. Installing LangChain

First, you need to install LangChain and some dependencies on your machine. You can download it from the official website or use the command line:

pip install langchain langchain-experimental openai redis wikipedia

2. Starting FalkorDB server locally

Staring a local FalkorDB is as simple as running a local docker you can go read on the documentation other ways to run it

            > docker run -p 6379:6379 -it --rm falkordb/falkordb:latest

6:C 26 Aug 2023 08:36:26.297 # oO0OoO0OoO0Oo Redis is starting oO0OoO0OoO0Oo

6:C 26 Aug 2023 08:36:26.297 # Redis version=7.2.1, bits=64, commit=00000000, modified=0, pid=6, just started

...

...

6:M 26 Aug 2023 08:36:26.322 * <graph> Starting up FalkorDB version 99.99.99.

6:M 26 Aug 2023 08:36:26.324 * <graph> Thread pool created, using 8 threads.

6:M 26 Aug 2023 08:36:26.324 * <graph> Maximum number of OpenMP threads set to 8

6:M 26 Aug 2023 08:36:26.324 * <graph> Query backlog size: 1000

6:M 26 Aug 2023 08:36:26.324 * Module 'graph' loaded from /FalkorDB/bin/linux-x64-release/src/falkordb.so

6:M 26 Aug 2023 08:36:26.324 * Ready to accept connections

Running the demo

The rest of this blog will cover the simple steps you can take to get started, you can also find try the Google Colab notebook

3. Create a Knowledge Graph

Now, let’s create a demo knowledge graph of Warren Buffett using Wikipedioa

            from langchain_experimental.graph_transformers.diffbot import DiffbotGraphTransformer

from langchain.document_loaders import WikipediaLoader

diffbot_api_key = "DIFFBOT_API_KEY"

diffbot_nlp = DiffbotGraphTransformer(diffbot_api_key=diffbot_api_key)

query = "Warren Buffett"

raw_documents = WikipediaLoader(query=query).load()

graph_documents = diffbot_nlp.convert_to_graph_documents(raw_documents)

4. Storing the Knowledge Graph in FalkorDB

Last step storing the knowledge Graph to FalkorDB

            from langchain.graphs import FalkorDBGraph

graph = FalkorDBGraph(

   "falkordb",

)

graph.add_graph_documents(graph_documents)

graph.refresh_schema()

5. Querying the Graph

You are all set, you can start querying the Knowledge Graph… Let’s try a couple of questions.

            %env OPENAI_API_KEY=OPENAI_API_KEY

from langchain.chains import GraphCypherQAChain

from langchain.chat_models import ChatOpenAI

chain = GraphCypherQAChain.from_llm(

   cypher_llm=ChatOpenAI(temperature=0, model_name="gpt-4"),

   qa_llm=ChatOpenAI(temperature=0, model_name="gpt-3.5-turbo"),

   graph=graph, verbose=True,

)


chain.run("Which university did Warren Buffett attend?")

> Entering new GraphCypherQAChain chain...

Generated Cypher:

MATCH (p:Person {name: "Warren Buffett"})-[:EDUCATED_AT]->(o:Organization)

RETURN o.name

Full Context:

[['Woodrow Wilson High School'], ['Alice Deal Junior High School'], ['Columbia Business School'], ['New York Institute of Finance']]

> Finished chain.

'Warren Buffett attended Columbia Business School.'

chain.run("Who is or was working at Berkshire Hathaway?")

> Entering new GraphCypherQAChain chain...

Generated Cypher:

MATCH (p:Person)-[r:EMPLOYEE_OR_MEMBER_OF]->(o:Organization) WHERE o.name = 'Berkshire Hathaway' RETURN p.name

Full Context:

[['Warren Buffett'], ['Charlie Munger'], ['Howard Buffett'], ['Susan Buffett'], ['Howard'], ['Oliver Chace']]

> Finished chain.

'Warren Buffett, Charlie Munger, Howard Buffett, Susan Buffett, Howard, and Oliver Chace are or were working at Berkshire Hathaway.'

Guy Korland

Guy Korland serves as CEO at FalkorDB, where he drives graph database architecture for generative AI and retrieval-augmented generation workflows. He holds a PhD in Computer Science from Tel Aviv University and brings over 20 years of experience in database engineering. He previously led Redis’ incubation arm as SVP & CTO, oversaw platform architecture as GM & CTO at Stor.ai (Self-Point), co-founded and served as CTO of Shopetti, and directed R&D as VP at GigaSpaces.

Frequently Asked Questions

Getting Started & Implementation