Neo4j, a global graph database and analytics company, has integrated native vector search into 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.
Neo4j's graph database can create knowledge graphs, which capture and connect explicit relationships between entities, enabling AI systems to reason, infer, and retrieve relevant information effectively. Neo4j says the result ensures more accurate, explainable, and transparent outcomes for LLMs and other generative AI applications.
By contrast, vector searches capture implicit patterns and relationships based on items with similar data characteristics rather than exact matches. Neo4j claims these are helpful when searching for similar text or documents, making recommendations, and identifying other patterns.
The June 2023 Gartner report, AI Design Patterns for Knowledge Graphs and Generative AI states that Knowledge Graphs complement LLM-based solutions where high thresholds of accuracy and correctness are needed.
Emil Eifrem, Co-Founder and CEO, Neo4j, says: "We see value in combining the implicit relationships uncovered by vectors with the explicit and factual relationships and patterns illuminated by graph."
"Customers, when innovating with generative AI, also need to trust that the results of their deployments are accurate, transparent, and explainable."
"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," says Eifrem.
This latest advancement follows Neo4j's recent product integration with Google Cloud's generative AI features in Vertex AI in June. The integration enables users to transform unstructured data into knowledge graphs, which users then query using natural language. Users can then ground their LLMs against a factual set of patterns and criteria to prevent hallucinations.
Moreover, Neo4j's native graph database became fully integrated with Microsoft Azure in April 2023, and, In December 2022, the company was recognised in the Gartner Magic Quadrant for Cloud Database Management Systems. This was the first time that native graph vendors were included.
Neo4j today powers generative AI deployments for multiple Fortune 500 enterprises, including an Asia-based energy multinational, a US-based pharmaceutical manufacturer, and an EMEA-based information and analytics leader. Additionally, Neo4j created the property graph model and is used by more than 75 of the Fortune 100.
The graph database & analytics expert helps organisations find hidden relationships and patterns across billions of data connections profoundly and efficiently. Customers leverage the structure of their connected data to reveal new ways of solving their business problems, from fraud detection, customer 360, knowledge graphs, supply chain, personalisation, IoT, network management, and visualisation.
Neo4j's full graph stack delivers native graph storage, data science, advanced analytics, and visualisation with security controls, scalable architecture and ACID compliance.
Neo4j's community of data leaders comprises an open-source community of over 250,000 developers, data scientists, and architects across hundreds of Fortune 500 companies, government agencies and NGOs.