Franz Releases the First Neuro-Symbolic AI Platform Merging Knowledge Graphs, Generative AI, and Vector Storage

(Mathias Rosenthal/Shutterstock)

Large language models (LLMs) have immense potential, and this is evident in the meteoric rise in demand for the technology. However, there are also some inherent shortcomings including lack of explainability and the inability to verify information against external sources. Knowledge Graphs can help address some of these challenges by making LLMs more transparent, accurate, and explainable. 

Franz, one of the early adopters of AI and a leading supplier of Graph Database technology, announced the immediate availability of AllegroGraph 8.0 which features new Knowledge Graph capabilities to validate GenAI content and reveal the hidden knowledge within the data. 

The groundbreaking Neural-Symbolic AI platform incorporates LLM components directly in the SPARQL along with vector generation and vector storage to create a comprehensive AI Knowledge Graph. It also combines Machine Learning with knowledge and reasoning capabilities to allow AutoGraph 8.0 to solve complex problems. The ability of the platform to create a Knowledge Graph with less data has expanded the application for this platform to a wide range of use cases. 

AllegroGraph is utilized by dozens of the top Fortune 500 companies worldwide. With AllegroGraph 7, Franz gained recognition as the leading provider of knowledge graph solutions, and now with the 8.0 upgrade, it would be looking to reinforce its dominant position in the industry. 

“While general-purpose LLMs excel at straightforward tasks that do not necessitate background or changing knowledge, addressing more complex, knowledge-intensive queries demands the capabilities provided with a Knowledge Graph to avoid generating ‘hallucinations,’” said Dr. Jans Aasman, CEO of Franz Inc.

Hallucinations, where the data generated appears to be real but is not grounded in actual data, is one of the biggest challenges in LLMs. It can cause contextual ambiguity, amplification of bias, and an inability to verify information. 

Aasman further added, “We designed AllegroGraph 8.0 with Retrieval Augmented Generation (RAG) capabilities to provide users with seamless Generative AI capabilities within a Knowledge Graph platform, while dynamically fact-checking LLM outputs to ensure that they are grounded in fact-based knowledge.”

The AllegroGraph 8.0 has a new LLMagic function that offers a dynamic natural language interface for both reasoning processes and queries. Users can now engage with the platform in a manner that closely mimics human conversation. This will help boost productivity for current users and make it more accessible to a broader set of new users. 

(Zapp2Photo/Shutterstock)

Another new and unique capability of the platform is the VectorStore tools that bridge the gap between Knowledge Graph and enterprise documents. Users can now access knowledge within the document to gain a comprehensive understanding and deep insight into enterprise data. 

The upgraded platform also has a built-in rule-based system that can be configured for AI symbolic reasoning. This empowers users to turn complex data into interpretable and actionable rules. In addition, symbolic rule generation allows users to predict and classify based on data and gather transparent explanations for their decisions by expressing them in symbolic rules. This feature can help enhance interpretability and trust in AI systems. 

The LLMagic tools in AllegroGraph 8.0 can help streamline time-consuming and complex tasks of crafting taxonomies and ontologies. It does this by analyzing diverse data and identifying relationships, patterns, and semantic connections to generate structured hierarchies and classifications. 

The AllegroGraph 8.0 also features enhanced scalability and performance, a new web interface, and advanced Knowledge Graph visualization through integration with Franz’s industry-leading graph visualization software Gruff v9. 

Related Items 

Data Fabrics: The Killer Use Case for Knowledge Graphs

Franz’s AllegroGraph 7.1 Accelerates Complex Reasoning Across Distributed Graphs, Data Fabrics

Partners Look to Scale ‘Chomsky Knowledge Graph’