Progress Announces Powerful New Generative AI Capabilities in Latest Release of MarkLogic Server
Rhea-AI Summary
Progress (Nasdaq: PRGS) has announced the early-access release of MarkLogic Server 12, featuring powerful new generative AI capabilities. This update significantly enhances the platform's ability to integrate AI into enterprise applications, offering:
1. Native vector support for improved similarity searches
2. BM25 relevance ranking for better document ranking
3. Graph shortest path functionality for optimized recommendation systems
The release also introduces MarkLogic Flux, a new application for enhanced data movement and transformation. These improvements aim to double the accuracy of AI responses while simplifying the development of secure, AI-enhanced applications. The MarkLogic platform now provides a more flexible Retrieval Augmented Generation (RAG) pattern, allowing enterprises to ground LLM models in their private data for fact-based query responses.
Positive
- Introduction of native vector support for improved AI retrieval accuracy
- Implementation of BM25 relevance ranking for better search result relevance
- Addition of graph shortest path functionality for optimized recommendation systems
- Launch of MarkLogic Flux for enhanced data movement and transformation capabilities
- Improved integration of generative AI in enterprise applications
Negative
- None.
Insights
Progress's MarkLogic Server 12 represents a significant leap in AI-powered database management. The introduction of native vector support and BM25 relevance ranking addresses critical challenges in enterprise AI adoption. These features substantially improve the accuracy and relevance of AI-generated responses, potentially doubling the accuracy of GenAI applications.
The simplified RAG architecture is a game-changer, allowing for easier integration of GenAI into enterprise applications. This could accelerate AI adoption across industries, particularly in sectors dealing with sensitive data. The graph shortest path feature enhances contextual relevance, which is important for complex AI applications like recommendation systems.
While these advancements are impressive, the real test will be in real-world enterprise deployments. The success of MarkLogic Server 12 will depend on its ability to deliver on the promise of improved accuracy and security in diverse enterprise environments.
MarkLogic Server 12's focus on secure grounding of LLM models in private data is a critical feature for enterprises concerned about data privacy and intellectual property protection. This approach allows organizations to leverage the power of GenAI while maintaining control over sensitive information.
The unified Optic API for combining queries and re-ranking results enhances security by ensuring that only the most relevant and authorized content is passed to LLM models. This reduces the risk of data leakage and unauthorized access.
However, as with any AI system handling sensitive data, it's important for organizations to implement robust access controls and monitoring systems. While MarkLogic Server 12 provides a secure foundation, the overall security of GenAI applications will still depend on proper implementation and ongoing management by the enterprise.
The early-access release of MarkLogic Server 12 signifies a major step towards democratizing AI in enterprise environments. The flexible RAG pattern and enhanced search capabilities lower the barrier for integrating GenAI into existing enterprise applications, potentially accelerating AI adoption across various industries.
The introduction of MarkLogic Flux for improved data movement and transformation is particularly noteworthy. Support for diverse data sources, including cloud storage systems like Amazon S3, addresses a common pain point in AI integration projects. This could significantly reduce the time and complexity involved in preparing data for AI workloads.
However, while these advancements are promising, enterprises should be prepared for a learning curve in effectively utilizing these new capabilities. The true value of MarkLogic Server 12 will be realized when organizations can seamlessly blend these AI enhancements with their existing data ecosystems and workflows.
New release more than doubles accuracy of response and simplifies development of secure generative AI-enhanced applications
BURLINGTON, Mass., Sept. 05, 2024 (GLOBE NEWSWIRE) -- Progress (Nasdaq: PRGS), the trusted provider of AI-powered infrastructure software, today announced the early-access release of Progress® MarkLogic® Server 12. With this release, Progress expands on the proven search capabilities within MarkLogic Server by delivering native vector support and new relevance-based algorithms to provide advanced capabilities for customers to harness the power of AI in the enterprise. Customers can now more easily integrate generative AI (GenAI) in their enterprise applications with a flexible Retrieval Augmented Generation (RAG) pattern and securely ground LLM models in their private data to enable fact-based query responses generated from AI models.
The new features in MarkLogic Server 12 enhance the relevance and accuracy of GenAI responses through improved search techniques. A single API allows users to define, orchestrate and re-rank search scores for faster, flexible and more secure graph RAG implementation. The simplified RAG architecture matches the data model and metadata maturity, enabling greater use of enterprise data for GenAI-enhanced applications.
"As AI becomes increasingly integrated into the enterprise, it is crucial to not only improve the precision of the results delivered but also to safeguard the enterprise’s valuable data,” said John Ainsworth, EVP and General Manager, Application and Data Platform, Progress. “With the latest release of MarkLogic Server, our customers have access to a dependable database management system capable of generating top-quality AI responses, while also protecting their reputation and intellectual property investment.”
What’s New in MarkLogic Server 12:
- Native vector support – Enable large-scale similarity searches for AI systems on vast amounts of unstructured data. Natively perform vector operations in MarkLogic Server to improve GenAI retrieval accuracy. Store vector embeddings close to your data in r JSON or XML format. Complement with full-text queries through Optic API for the highest results relevance.
- BM25 relevance ranking – Improve recall with better document ranking to return the most relevant search results at the top. Combine best-match and vector search to re-rank results for optimal search relevance. With MarkLogic Server comprehensive search, organizations can combine queries, merge result scores and re-rank them with a single expression via its unified Optic API that parses the content most relevant to a user query to the LLM model.
- Graph shortest path – Solve real-world problems related to route planning, network optimization and resource allocation. Improve contextual relevance of results and response time in AI-enhanced recommendation systems using semantic searches against knowledge graphs or semantic data in graph RAG architectures.
Progress also released a new application, MarkLogic® Flux™, to add improved data movement and transformation capabilities to the core functionality of the MarkLogic platform. These include support for significantly more data sources, such as relational databases and cloud storage systems like Amazon S3, as well as better performance through faster ingestion of extremely large, high-volume data, supporting any operational, analytical or AI workload.
The Progress MarkLogic platform, which includes MarkLogic Server, combines multi-model data management with real-time, relevance-based search and semantic capabilities to provide an adaptable, secure foundation for an organization’s GenAI solutions. They can leverage GenAI in their enterprise with a flexible RAG architecture that augments LLMs with domain-specific knowledge to increase response accuracy, democratize access to information across the organization and power AI-enhanced applications.
To learn more about MarkLogic Server 12, click here.
About Progress
Progress (Nasdaq: PRGS) empowers organizations to achieve transformational success in the face of disruptive change. Our software enables our customers to develop, deploy and manage responsible AI-powered applications and experiences with agility and ease. Customers get a trusted provider in Progress, with the products, expertise and vision they need to succeed. Over 4 million developers and
technologists at hundreds of thousands of enterprises depend on Progress. Learn more at www.progress.com.
Progress, MarkLogic, and MarkLogic Flux are trademarks or registered trademarks of Progress Software Corporation and/or one of its subsidiaries or affiliates in the U.S. and other countries. Any other trademarks contained herein are the property of their respective owners.
Press Contacts:
Kim Baker
Progress
+ 1-800-213-3407
pr@progress.com
FAQ
What are the key features of Progress MarkLogic Server 12?
How does MarkLogic Server 12 improve AI integration for enterprises?
What is the impact of MarkLogic Server 12 on AI response accuracy?
When was the early-access release of Progress MarkLogic Server 12 announced?
