Curated for content, computing, and digital experience professionals

Month: November 2023 (Page 1 of 2)

Gilbane Advisor 11-29-23 — LLM overkill, knowledge graph not

This week we feature articles from Kurt Cagle, and Mike Dillinger.

Additional reading comes from Michael Parekh, Jeremy Arancio, Sam Shedden, and Mike Loukides.

News comes from Neoj4, Acquia, Ontotext, and Fivetran.

Reminder: We don’t usually publish in December. We’ll be back in January. Hope you all have healthy and happy holidays! 

All previous issues are available at https://gilbane.com/gilbane-advisor-index


Opinion / Analysis

Do you really NEED that LLM?

Kurt Cagle explains why large language models (LLMs), specialized or not, may be overkill for many applications, describes some of the characteristics of those applications, and suggests knowledge graphs and other existing technologies that may be preferable. (6 min)

https://metaphoricalweb.substack.com/p/do-you-really-need-that-llm?

Knowledge graphs or plain ol’ snake oil: How would you know?

Mike Dillinger addresses the question of what a knowledge graph is, is not, and how it is different from related technologies and resources.

“The overarching goal of knowledge graphs is to store and reproduce conceptual information in a machine-accessible way, as verifiable facts linked to objective data — not only as statements or opinions…” (11 min)

https://medium.com/@mike.dillinger/knowledge-graphs-or-plain-ol-snake-oil-how-would-you-know-0e810a868d28

More Reading

All Gilbane Advisor issues


Content technology news

Neo4j collaborating with AWS to enhance generative AI results

The agreement includes integration with Amazon Bedrock for enterprise generative AI outcomes that are more accurate, transparent, and explainable.
https://neo4j.com/press-releases/neo4j-aws-bedrock-integration/

Acquia Site Studio introduces capabilities to create Drupal and headless applications from a single platform

Now developers and marketers can create and manage digital experiences for traditional Drupal websites and headless applications using the same content.
https://www.acquia.com/newsroom/press-releases/site-studio-drupal-headless

Ontotext and TopQuadrant partner to accelerate adoption of graph and semantic technologies

Ontotext clients gain a knowledge graph creation and curation tool, while TopQuadrant clients get improved scalability, usability, performance.
https://www.ontotext.com/company/news/ontotext-and-topquadrant-a-powerful-partnership/

Fivetran deepens relationship with Microsoft; adds new data lake destinations

Fivetran supports Microsoft OneLake through integration with Microsoft Fabric and Delta Lake on Azure Data Lake Storage Gen2.
https://www.fivetran.com/blog/fivetran-supports-microsoft-onelake-as-a-destination-through-integration-with-microsoft-fabric

All content technology news


The Gilbane Advisor is authored by Frank Gilbane and is ad-free, cost-free, and curated for content, computing, web, data, and digital experience technology and information professionals. We publish recommended articles and content technology news weekly. We do not sell or share personal data.

Subscribe | View online | Editorial policy | Privacy policy | Contact

Neo4j collaborating with AWS to enhance generative AI results

Neo4j announced a multi-year Strategic Collaboration Agreement (SCA) with Amazon Web Services (AWS) to enable enterprises to achieve better generative artificial intelligence (AI) outcomes through a combination of knowledge graphs and native vector search that reduces generative AI hallucinations while making results more accurate, transparent, and explainable.

Neo4j also anncounced a new integration with Amazon Bedrock, a managed service that makes foundation models from AI companies accessible via an API to build and scale generative AI applications. Neo4j’s native integration with Amazon Bedrock enables:

  1. Reduced Hallucinations: Neo4j with Langchain and Amazon Bedrock can now work together using Retrieval Augmented Generation (RAG) to create virtual assistants grounded in enterprise knowledge.
  2. Personalized experiences: Neo4j’s context-rich knowledge graphs integration with Amazon Bedrock can invoke an ecosystem of foundation models that generate personalized text generation and summarization for end users.
  3. Get complete answers during real-time search: Developers can leverage Amazon Bedrock to generate vector embeddings from unstructured data (text, images, and video) and enrich knowledge graphs using Neo4j’s new vector search and store capability.
  4. Kickstart a knowledge graph creation: Developers can leverage new generative AI capabilities using Amazon Bedrock to process unstructured data so it becomes structured and load it into a knowledge graph.

https://neo4j.com/press-releases/neo4j-aws-bedrock-integration/

Ontotext and TopQuadrant partner to accelerate adoption of graph and semantic technologies

Ontotext, a semantic data and knowledge graph technology provider, and TopQuadrant, a provider of software tools for data governance and semantics, announced a partnership to bring advantages to their shared customer base. With TopQuadrant, Ontotext clients gain a knowledge graph creation and curation tool that enables new data governance use cases, while TopQuadrant clients benefit from improved scalability, usability, and performance. The combination of front and back-end systems enables:

  1. Scalability and Performance for Large Data Sets: With Ontotext’s RDF database GraphDB, semantic data products such as taxonomies, tag lists, metadata stores, and code lists, can now scale to handle master data management and enterprise data quality and validation efforts.
  2. Policy Enforcement and Automation: TopQuadrant’s expertise in data governance and metadata management will help clients enforce policies across organizations’ full data landscape, mitigating risk of regulatory fines such as for GDPR.
  3. Pharma R&D Semantic Solution: This solution will enable data models to capture data and improve data quality, enhancing collaboration and efficiency, automating regulatory reporting and ultimately enabling new insights into drug discovery.
  4. Semantic Data Catalog: The semantic approach for active metadata management harmonizes data and metadata across an entire organization. The semantic data catalog actively populates metadata and makes data more interoperable and reusable.

https://www.ontotext.com/company/news/ontotext-and-topquadrant-a-powerful-partnership/

Fivetran deepens relationship with Microsoft; adds new data lake destinations

Fivetran announced its support for Microsoft OneLake through integration with Microsoft Fabric as a new data lake destination, and that Fivetran has been named a Microsoft Fabric Interoperability Partner. Together with support for Delta Lake on Azure Data Lake Storage (ADLS) Gen2, also announced today, Fivetran customers now have two Microsoft data lake destinations to securely consolidate their data workloads with any of Fivetran’s 400-plus pre-built, fully managed data pipelines. 

Because Fivetran automates data extraction, cleansing, conforming and converting data to Delta Lake format, customers are able to move faster in developing AI and generative AI-based projects.

OneLake serves as the unified data foundation for Microsoft Fabric, making it simple for customers to access their data through a file explorer, similar to Microsoft’s OneDrive for files. With OneLake, customers can create multiple workspaces within a single tenant.

Fivetran offers the flexibility and scalability that enterprises need to build a solid data lake foundation, across on-premise, cloud-based and third-party sources. Whether an organization has a hybrid or multi-cloud environment, Fivetran provides high-volume data movement with enterprise-ready reliability and uptime, and industry-standard practices for data encryption, with GDPR, IS0 27001 and SOC 2 Type II compliance.

https://www.fivetran.com/blog/fivetran-supports-microsoft-onelake-as-a-destination-through-integration-with-microsoft-fabric

Acquia Site Studio introduces capabilities to create Drupal and headless applications from a single platform

Acquia announced new capabilities for Acquia Site Studio, the low-code Drupal website builder. Now, developers and marketers can create and manage digital experiences for traditional Drupal websites and headless applications using the same content. This allows marketers to create engaging digital experiences across digital channels from a single content platform, reducing demands on development and IT resources. 

Acquia Site Studio offers an intuitive visual page building and content authoring experience for Drupal. In a traditional website build, Site Studio allows non-technical users to create components, layouts, and content without the need for PHP and JavaScript. Now, with the launch of the new JSON:API for Site Studio, JavaScript and front end developers can easily access the content and layouts created via Site Studio in decoupled or headless apps to create more engaging, interactive digital experiences. The new feature requires Acquia Site Studio 7.4 and above and use of a modern version of Drupal. 

https://www.acquia.com/newsroom/press-releases/site-studio-drupal-headless

Gilbane Advisor 11-15-23 — CMSs & ESUS, creative remixing

This week we feature articles from Michael Andrews and Mike Loukides.

Additional reading comes from Alan Morrison, Cobus Greyling, Thomas Macaulay, and Nicholas Megaw.

News comes from Transperfect & Sitecore, OpenAI, Brightcove & Socialive, and Elastic.

Note: We’ll be off next week due to the Thanksgiving holiday.

All previous issues are available at https://gilbane.com/gilbane-advisor-index


Opinion / Analysis

How to compare CMSs, objectively

“There are literally hundreds of CMSs on the market, possibly thousands. So much choice, but often so little satisfaction, judging by the gripes of end-users. Why is the right option so muddled? Old CMS vendors soldier on, and new ones enter the market all the time, promising a better future. How do we make sense of this?”

Michael Andrews provides some help. He argues for benchmarking usability, and illustrates how using the recently proposed Enterprise System Usability Scale (ESUS). (7 min)

https://storyneedle.com/how-to-compare-cmss-objectively/

Creativity isn’t just remixing

Mike Loukides has a delightful post on generative AI and creativity. His conclusion is uncontroversial, but his discussion is a gem.

“It’s amazing that an AI system can produce derivative works, but we have to remember that they are derivative works. And we have to recognize that AI, as a tool for artists, makes perfect sense. Just as we don’t confuse the artist’s creativity with the paintbrush, we shouldn’t confuse their creativity with the AI.” (8 min)

https://www.oreilly.com/radar/creativity-isnt-just-remixing/

More Reading

All Gilbane Advisor issues


Content technology news

TransPerfect announces integrated translation solution for Sitecore XM Cloud

The integration provides the ability to create, manage, and deliver multilingual content with an enterprise content management system (CMS).
https://www.transperfect.com ■ https://www.sitecore.com

OpenAI introduces custom GPTs

You can now create custom versions of ChatGPT that combine instructions, extra knowledge, and any combination of skills.
https://openai.com/blog/introducing-gpts

Brightcove and Socialive partner

Brightcove customers can leverage Socialive’s remote production features to improve their content operations for internal communications.
https://www.brightcove.com ■ https://socialive.us

Elastic unveils Elasticsearch Query Language (ES|QL)

The dedicated query language to simplify data investigation enables data aggregation and transformation within a single query.
https://www.elastic.co

All content technology news


The Gilbane Advisor is authored by Frank Gilbane and is ad-free, cost-free, and curated for content, computing, web, data, and digital experience technology and information professionals. We publish recommended articles and content technology news weekly. We do not sell or share personal data.

Subscribe | View online | Editorial policy | Privacy policy | Contact

Gilbane Advisor 11-8-23 — OpenAI dashboard, knowledge graph representations

This week we feature articles from Cobus Greyling, and Julia Cohen, Ana Iglesias-Molina, Kian Ahrabian, Filip Ilievski, Jay Pujara & Oscar Corcho.

Additional reading comes from Michael Parekh, Caroline Mimbs Nyce, and Ethan Zuckerman.

News comes from DataStax, Cloudera & Pinecone, SnapLogic & Acolad, and Fivetran.

All previous issues are available at https://gilbane.com/gilbane-advisor-index


Opinion / Analysis

What is happening to OpenAI’s playground?

“Creating solutions with longevity which are based on LLMs and Generative AI will demand exceptional UX, a solid layer of IP which creates differentiation” and “Users do not care about the underlying technology, they are looking for exceptional experiences.” 

Greyling provides a useful update on what OpenAI is doing to make sure they don’t miss out on the value of direct UX control. (6 min)

https://cobusgreyling.medium.com/what-is-happening-to-openais-playground-76c04816adc2

Comparison of knowledge graph representations

In addition to RDF, knowledge graphs can be represented using 
alternative models such as property graphs, the Wikidata model, and RDF-star, which may more useful for certain use-cases. When might they be advantageous? This paper looks at the fitness of popular knowledge graph representations for three consumer scenarios: knowledge exploration, systematic querying, and graph completion. 

(3 min intro): https://viterbischool.usc.edu/news/2023/11/finding-answers-about-the-best-way-to-find-answers/
Paper: https://link.springer.com/chapter/10.1007/978-3-031-47240-4_15

More Reading

All Gilbane Advisor issues


Content technology news

DataStax launches RAGStack

RAGStack, is a retrieval augmented generation solution to simplify RAG implementations for enterprises building generative AI applications.
https://www.datastax.com/products/ragstack

Cloudera and Pinecone announce strategic partnership

With the combination of Pinecone vector database and semantic search customers can improve and accelerate generative AI use cases.
https://www.cloudera.com ■ https://www.pinecone.io

SnapLogic and Acolad partner to provide generative AI translation solutions

Pre-built integration connectors for instant document translation allows SnapLogic users to add Acolad’s translations to integration pipelines.
https://www.snaplogic.com ■ https://www.acolad.com

Fivetran unveils new SDKs for connectors and destinations

Enables third-party vendors to build integrations on Fivetran’s infrastructure for extensive compatibility with data sources and integrations.
https://www.fivetran.com

All content technology news


The Gilbane Advisor is authored by Frank Gilbane and is ad-free, cost-free, and curated for content, computing, web, data, and digital experience technology and information professionals. We publish recommended articles and content technology news weekly. We do not sell or share personal data.

Subscribe | View online | Editorial policy | Privacy policy | Contact

Elastic unveils Elasticsearch Query Language (ES|QL)

Elastic the company behind Elasticsearch, today announced Elasticsearch Query Language (ES|QL), its new piped query language designed to transform, enrich and simplify data investigation with concurrent processing. ES|QL enables site reliability engineers (SREs), developers and security professionals to perform data aggregation and analysis across a variety of data sources from a single query. 

Over the last two decades, the data landscape has become more fragmented, opaque, and complex, driving the need for greater productivity and efficiency among developers, security professionals, and observability practitioners. Organizations need tools and services that offer iterative workflow, a broad range of operations, and central management to make security and observability professionals more productive. Elasticsearch Query Language key benefits include:

  • Delivers a comprehensive and iterative approach to data investigation with ES|QL piped query syntax.
  • Improves speed and efficiency regardless of data’s source or structure with a new ES|QL query engine that leverages concurrent processing.
  • Streamlines observability and security workflows with a single user interface, which allows users to search, aggregate and visualize data from a single screen.

ES|QL is currently available as a technical preview. The general availability version, scheduled for release in 2024, will include additional features to further streamline data analysis and decision-making.

https://www.elastic.co

« Older posts

© 2024 The Gilbane Advisor

Theme by Anders NorenUp ↑