Neo4j adds vector search capability within its native graph database to provide richer generative AI insights

Emil Eifrem, Chief Executive Officer and Co-Founder of Neo4j
Emil Eifrem, Chief Executive Officer and Co-Founder of Neo4j

Neo4j®, the world-renown graph database and analytics solutions provider, announced that it has integrated native vector search as part of its core database capabilities. The result enables customers to achieve richer insights from semantic search and generative AI applications, and serve as long-term memory for LLMs, all while reducing hallucinations.

What is the market offering of the updated database?

Neo4j’s graph database can be used to create knowledge graphs, which capture and connect explicit relationships between entities, enabling artificial intelligence systems to reason, infer, and retrieve relevant information effectively. The result ensures more accurate, explainable, and transparent outcomes for LLMs and other generative artificial intelligence applications.

By contrast, vector searches capture implicit patterns and relationships based on items with similar data characteristics, rather than exact matches, which are useful when searching for similar text or documents, making recommendations, and identifying other patterns.  

Neo4j today powers generative artificial intelligence deployments for multiple Fortune 500 enterprises that include an Asia-based energy multinational, a US-based pharmaceutical manufacturer, and an EMEA-based information and analytics leader, among others.

The June 2023 Gartner® research report, AI Design Patterns for Knowledge Graphs and Generative AI, states that Knowledge graphs provide the perfect complement to LLM-based solutions where high thresholds of accuracy and correctness need to be attained.

What does this mean for Neo4j?

“We see value in combining the implicit relationships uncovered by vectors with the explicit and factual relationships and patterns illuminated by graph. Also, customers when innovating with generative AI also need to trust that the results of their deployments are accurate, transparent, and explainable,” commented Emil Eifrem, Co-Founder and CEO at Neo4j.

“With LLMs evolving so dynamically, Neo4j has become foundational for enterprises seeking to push the envelope on what’s possible for their data and their business,” Eifrem further said.

This latest advancement follows from Neo4j’s recent product integration with Google Cloud’s generative AI features in Vertex AI in June, enabling users to transform unstructured data into knowledge graphs, which users can then query using natural language and ground their large language models (LLMs) against factual set of patterns and criteria to prevent hallucinations.

Neo4j’s graph database was fully integrated with Microsoft Azure in April 2023. In December 2022, the firm was recognised for the first time in the Gartner®️ Magic Quadrant™️ for Cloud Database Management Systems, which was a first time that native graph vendors. 

Neo4j created the property graph model and is a revered graph database in the market, used by over 75 of the Fortune 100. More details on its vector index search capability are here.