Neo4j lowers barriers to graph technology with gen AI copilot, 15x read capacity

Credit: VentureBeat made with Midjourney V6

As enterprises continue to double down on AI and analytics, data infrastructure vendors are doing everything they can to lower the adoption barriers to their products and deliver maximum ROI to teams looking to drive value from their data assets. We’ve already seen efforts from platforms like Snowflake. Now Neo4j, the startup pioneering the next phase of data innovations with graph technologies, is jumping on the bandwagon.

Today, the Emil Eifrem-led company announced a major upgrade for its fully managed AuraDB offering, making it easier to use with the power of generative AI and improving its performance with 15x read capacity and advanced controls for data security and compliance. It also announced a new self-serve product version at a lower price so that more enterprises can adopt and use graph databases, particularly for generative AI and advanced analytics applications.

“Today’s announcement marks a pivotal leap forward in our mission to empower enterprises with the industry’s most robust, scalable, and performant graph database management solution. Simultaneously, these innovations lower adoption barriers for graph technology and GraphRAG for gen AI, enabling organizations to push the envelope on what’s possible for their data and their business,” Sudhir Hasbe, chief product officer at the company, said in a statement.

What exactly is AuraDB?

Neo4j has been offering AuraDB as a fully managed cloud graph database service that leverages relationships in data and enables ultra-fast queries for real-time analytics and advanced generative AI applications. 

The database mirrors data design like sketching on a whiteboard, storing all the information in nodes (representing entities, people and concepts) with relevant context and connections between them. Using this graph structure, users can identify complex patterns and relationships that may not be apparent in traditional relational databases, deploy graph algorithms for tasks like centrality measures and pathfinding and gain insights for business decisions in milliseconds rather than minutes.

Now, as part of an effort to simplify how enterprise users build with the managed graph database, Neo4j is adding new capabilities to AuraDB. 

New offering includes gen AI copilot and no/low code interactive dashboard builder, among other features

First, the company is introducing a generative AI copilot to the Aura console. The offering uses a large language model (LLM) from OpenAI and provides real-time suggestions, optimizations and explanations to help users write Cypher queries to extract insights from their data — which previously took a lot of time. 

“The co-pilot users enter a natural language query and receive search phrases or Cypher code generated by the LLM. The LLM is primed with the context of your current database schema. This means every request will have a reasonable understanding of your database. The prompt sent to OpenAI includes the original natural language query, a description of the user database schema, and a few short examples and guidelines. Users can edit and adjust the generated Cypher code before executing it,” Hasbe told VentureBeat.

The company is also adding NeoDash, a no/low-code interactive dashboard builder, into the mix. The builder quickly creates maps, graphs, bar and line charts, tables and other visuals. This allows enterprise users to easily understand, analyze and interact with their data. 

For instance, it could leverage an organization’s graph database to map active security risks or visualize the real-time supply chain.

Among other things, AuraDB is getting advanced security, audit and compliance capabilities, including customer-managed keys to encrypt and protect data and the ability to stream and audit security logs in real-time. Most importantly, the upgrade also ensures enhanced read capacity, enabling the database to process 15 times more real-time data within each cluster without compromising on latency. Hasbe said this improvement has been delivered by adding read-only secondaries to AuraDB.

“This feature distributes read-heavy workloads across secondaries, making it ideal for applications with high read-to-write ratios. It ensures consistent performance as data grows by routing read queries to secondaries and non-leader primaries within the same region. Customers can add up to 15 AuraDB secondaries per database instance and is available across AWS, Azure and GCP,” he noted.

Significant growth for graph technologies

The upgrade for AuraDB comes at a time when graph technologies are gaining significant traction in the market. Gartner estimates that these technologies will be used in 80% of the data and analytics workloads by 2025 – marking a significant jump from 10% in 2021. It also notes that the technology will play a significant role in building highly performant retrieval augmented generation (RAG) AI applications.

“RAG techniques in an enterprise context suffer from problems related to the veracity and completeness of responses caused by limitations in the accuracy of retrieval, contextual understanding and response coherence. KGs [Knowledge Graphs], a well-established technology, can represent data held within documents and the metadata relating to the documents. Combining both aspects allows RAG applications to retrieve text based on the similarity to the question and contextual representation of the query and corpus, improving response accuracy,” the firm notes in its hype cycle report.

For Neo4j, the plan is pretty straightforward: cash in on the demand with enhanced and easy-to-access offerings. 

To further push AuraDB’s growth, the company has also added a new, more affordable pricing tier called AuraDB Business Critical. It is just like the company’s premier enterprise offering but 20% cheaper due to its self-serve nature. Meanwhile, the flagship plan, now known as AuraDB Virtual Dedicated Cloud, is hosted on dedicated infrastructure with a virtual private cloud and specific networking requirements.

Over the past 12 quarters, Hasbe said, 30-40% of new Neo4j customers have signed up for Aura. Broadly, the company has roped in more than 1,700 customers and 300K+ developers, serving as the world’s leading provider of scalable graph technology.