The Gilbane Advisor

Curated for content, computing, and digital experience professionals

Gilbane Advisor 5-22-24 — Text + KG embeddings, floppies!

This week we feature articles from Sunila Gollapudi, and Leontien Talboom & Chris Knowles.

Additional reading comes from Heather Hedden, Cassie Kozyrkov, and Jim Clyde Monge.

News comes from Elastic, DataStax, Flatfile, and Foxit & Straker Translations.

Note: We’ll be off next week, back on June 5th.

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


Opinion / Analysis

Combine text embeddings and knowledge (graph) embeddings in RAG systems

Sunila Gollapudi provides a good introduction and how-to suitable for technical and not so technical readers.

“In this article, I am excited to present my experiments combining Text Embeddings and Knowledge (Graph) Embeddings and observations on RAG performance. I will start by explaining the concept of Text and Knowledge Embeddings independently, using simple open frameworks, then, we will see how to use both in RAG applications.” (15 min)

https://towardsdatascience.com/combine-text-embeddings-and-knowledge-graph-embeddings-in-rag-systems-5e6d7e493925

Raw flux streams and obscure formats: Further work around imaging 5.25-inch floppy disks

I’m sure the subject has some of you shaking your heads for any number of reasons. But for those connected with digital preservation efforts, this case-study/lessons-learned piece from Leontien Talboom & Chris Knowles at Cambridge University could be very helpful. Some of the comments may also be useful. The just-curious may be shocked at the complexity involved. (8 min)

https://digitalpreservation-blog.lib.cam.ac.uk/raw-flux-streams-and-obscure-formats-further-work-around-imaging-5-25-inch-floppy-disks-5a2cf2e5f0d1

More Reading

All Gilbane Advisor issues


Content technology news

DataStax launches new Hyper-Converged Data Platform

Brings OpenSearch and Apache Pulsar to HCD Platform; DataStax Enterprise 6.9 enables self-managed data workloads for GenAI.
https://www.datastax.com/press-release/datastax-launches-new-hyper-converged-data-platform-giving-enterprises-the-complete-modern-data-center-suite-ceeded-for-ai-in-production

Architecture optimized for real-time, low-latency applications including search, retrieval augmented generation (RAG), observability & security.
https://ir.elastic.co/news/news-details/2024/Elastic-Announces-First-of-its-kind-Search-AI-Lake-to-Scale-Low-Latency-Search/default.aspx

Flatfile unveils new AI-powered data transformation features

Data transformation and data migration capabilities for business users, data analysts, systems integration teams, and enterprise developers.
https://flatfile.com/news/flatfile-unveils-ai-powered-data-transformation/

Foxit partners with Straker Translations

The collaboration adds translation capabilities to Foxit’s eSignature services, enabling users to translate and sign documents in multiple languages.
https://www.foxit.com ■ https://www.straker.ai

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 most Wednesdays. We do not sell or share personal data.

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

Elastic announced Search AI Lake to scale low latency search

Elastic, a Search AI company, today announced Search AI Lake, a cloud-native architecture optimized for real-time, low-latency applications including search, retrieval augmented generation (RAG), observability and security. The Search AI Lake also powers the new Elastic Cloud Serverless offering. All operations, from monitoring and backup to configuration and sizing, are managed by Elastic – users just bring their data and choose Elasticsearch, Elastic Observability, or Elastic Security on Serverless. Benefits include:

  • Fully decoupling storage and compute enables scalability and reliability using object storage, dynamic caching supports high throughput, frequent updates, and interactive querying of large data volumes.
  • Multiple enhancements maintain query performance even when the data is safely persisted on object stores.
  • By separating indexing and search at a low level, the platform can automatically scale to meet the needs of a wide range of workloads.
  • Users can leverage a native suite of AI relevance, retrieval, and reranking capabilities, including a native vector database integrated into Lucene, open inference APIs, semantic search, and first- and third-party transformer models, which work with the array of search functionalities.
  • Elasticsearch’s query language, ES|QL, is built in to transform, enrich, and simplify investigations with fast concurrent processing irrespective of data source and structure.

https://ir.elastic.co/news/news-details/2024/Elastic-Announces-First-of-its-kind-Search-AI-Lake-to-Scale-Low-Latency-Search/default.aspx

DataStax to launch new Hyper-Converged Data Platform

DataStax announced the upcoming launch of DataStax HCDP (Hyper-Converged Data Platform), in addition to the upcoming release of DataStax Enterprise (DSE) 6.9. Both products enable customers to add generative AI and vector search capabilities to their self-managed, enterprise data workloads. DataStax HCDP is designed for modern data centers and Hyper-Converged Infrastructure (HCI) to support the breadth of data workloads and AI systems. It supports on-premises enterprise data systems built to AI-enable data and is designed for enterprise operators and architects.

The combination of OpenSearch’s Enterprise Search capabilities, with the high-performance vector search capabilities of the DataStax cloud-native, NoSQL Hyper-Converged Database, enables users to speed RAG and knowledge retrieval applications into production.

Hyper-converged streaming (HCS) built with Apache Pulsar is designed to provide data communications for a modern infrastructure. With native support of inline data processing and embedding, HCS brings vector data to the edge, allowing for faster response times and enabling event data for better contextual generative AI experiences.

HCDP provides rapid provisioning and data APIs built around the DataStax one-stop GenAI stack for enterprise retrieval-augmented generation (RAG), and it’s all built on the open-source Apache Cassandra platform.

https://www.datastax.com/press-release/datastax-launches-new-hyper-converged-data-platform-giving-enterprises-the-complete-modern-data-center-suite-ceeded-for-ai-in-production

Foxit partners with Straker Translations

Foxit Software, a provider of PDF products and services, today announced a strategic partnership with Straker Translations, integrating Straker’s AI-powered language translation technology into the Foxit ecosystem. Foxit and Straker’s collaboration provides on-demand, accurate translation capabilities to Foxit’s eSignature services, enabling users to seamlessly translate and sign documents in multiple languages.

Straker’s integration within the Foxit eSignature solution will be valuable for Foxit users across critical sectors such as finance, legal, insurance, tax accounting, healthcare, and biotech, where precision and accessibility in documentation are essential.

This integration ensures that Foxit’s diverse international user base can engage with legal documents in their native language, enhancing understanding and compliance while simplifying the signing process for documents that cross linguistic borders. The addition of Straker’s translation technology not only streamlines the workflow but also enhances legal compliance and reduces the risk of misunderstandings in global transactions.

https://www.foxit.comhttps://www.straker.ai

Gilbane Advisor 5-15-24 — Agentic UX, Meta vs OpenAI

This week we feature articles from Alex Klein, and Alberto Romero.

Additional reading comes from Jim Clyde Monge, James O’Donnell, Cobus Greyling, and Scott Brinker.

News comes from Adobe, Apple, SoundHound & Perplexity, and Acquia.

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


Opinion / Analysis

The agentic era of UX

“The future of digital experience is here — but it’s being minced into microscopic use cases.”

Alex Klein argues that AI user experience requires a holistic approach that pulls together point use cases into a workflow that addresses more complete user journeys, and that the role of design is critical. He explains, and has some good advice on how to proceed. (8 min)

https://uxdesign.cc/the-agentic-era-of-ux-4b58634e410b

OpenAI rules the changes but Meta changes the rules

Alberto Romero comes up with an enlightening analysis of the AI market focused on Meta’s strategy of making LLMs a commodity with Llama, and OpenAi, representing current LLM leadership. 

OpenAI’s Monday announcement of GPT-4o keeps the pressure on Google, Anthropic, et al. Some the impressive GPT-4o demos were on phones and suggest what we might see if Apple and OpenAI finalize an agreement. (7 min)

https://www.thealgorithmicbridge.com/p/openai-rules-the-changes-but-meta

More Reading

All Gilbane Advisor issues


Content technology news

Adobe launches Acrobat AI Assistant for the enterprise

Acrobat AI Assistant can be deployed in minutes with enterprise controls, increasing productivity for knowledge workers on desktop, web and mobile.
https://blog.adobe.com/en/publish/2024/05/08/adobe-acrobat-ai-assistant-enterprise-our-commitment-data-governance-security

SoundHound AI and Perplexity partner

Perplexity’s capabilities added to SoundHound Chat AI will respond to questions conversationally with real-time knowledge from the web.
https://www.soundhound.com/newsroom/press-releases/soundhound-ai-and-perplexity-partner-to-bring-online-llms-to-its-next-gen-voice-assistants-across-cars-and-iot-devices/■ https://www.perplexity.ai

Apple Final Cut Pro 2 on iPad and Mac get new AI features

Final Cut Pro 2 transforms video creation with Live Multicam on the new iPad Pro and new AI features on iPad Pro and Final Cut Pro Mac 10.8.
https://www.apple.com/newsroom/2024/05/final-cut-pro-transforms-video-creation-with-live-multicam-on-ipad-and-new-ai-features-on-mac/

Acquia supports latest W3C content accessibility guidelines

With the Accessibility Module in Monsido, customers can scan their websites, obtain an accessibility score, and get recommendations to improve accessibility.
https://www.acquia.com/products/monsido

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

Flatfile unveils new AI-powered data transformation features 

Flatfile, a data exchange platform, announced their Spring 2024 release with new AI-powered data transformation and data migration capabilities for business users, data analysts and systems integration teams as well as improved tooling and extensions for data exchange solution developers. The Flatfile Data Exchange Platform provides software development teams with an efficient and easy way to build exactly the data collection, transformation and migration solution their users need. Spring 2024 release highlights:

  • With AI Transform, business users can overcome the challenges of manually editing large data sets. This tool allows users to describe in natural language how they’d like to change their data and preview all potential changes in a convenient before-and-after view. This new co-pilot significantly simplifies and accelerates the cleanup and validation of enterprise data.
  • The new “Shared Views” feature, powered by the advanced filtering and querying capabilities of Flatfile workbooks, allows data migration teams to collaborate on the same data set while dynamically sharing precise data slices with relevant team members.
  • The new dashboard introduces a selection of pre-built apps, offering developers a streamlined approach to customizing their Flatfile experience. These apps support common use cases, such as embedded data importers or collaborative data onboarding projects.

https://flatfile.com/news/flatfile-unveils-ai-powered-data-transformation

SoundHound AI and Perplexity partner

SoundHound AI, Inc., a voice artificial intelligence vendor, announced it has partnered with Perplexity, the conversational AI-powered answer engine. Together they will bring Perplexity’s online LLM capabilities to SoundHound Chat AI – a voice assistant that utilizes hundreds of real-time domains, as well as generative AI responses. The SoundHound Chat AI assistant will leverage Perplexity to provide accurate, up-to-date responses to web-based queries that static LLMs cannot currently answer – expanding the type and complexity of the questions the assistant is able to handle.

For example, a user can ask a question like: “How does the price of gas this week compare to last week?” and the response will combine accurate, live information on gas prices with a comprehensive generative AI-style explanation that provides further context. The user can then follow-up with, “Navigate to the nearest gas station,” which uses SoundHound’s technology to seamlessly incorporate data from the appropriate sources and integrate with the navigation software of a device such as a car or a phone.

The assistant also utilizes a specially developed arbitration technology that uses a combination of software engineering and machine learning to intelligently select the more appropriate response, helping to minimize harmful “AI hallucinations.”

https://www.soundhound.com/newsroom/press-releases/soundhound-ai-and-perplexity-partner-to-bring-online-llms-to-its-next-gen-voice-assistants-across-cars-and-iot-devices/https://www.perplexity.ai

Adobe launches Acrobat AI Assistant for the enterprise

Snippets from the Adobe blog…

Today, we announced the general availability of Adobe Acrobat AI Assistant for enterprise customers. Acrobat AI Assistant allows you to interact with your documents in Acrobat for quick answers and one-click summaries to create impactful content and improve productivity. It brings together our deep knowledge of PDF documents with our proprietary technology for document processing.

  • For Adobe Acrobat’s generative AI features, we currently leverage Microsoft’s Azure OpenAI Service, which is contractually prohibited from manually reviewing or training its LLM on Adobe customer data.
  • We leverage Microsoft Azure OpenAI’s content filtering service to moderate hate, sexual, violent, and self-harm content.
  • The Acrobat AI Assistant only looks at the information presented in the document and no other external sources such as the web, email or stored content in other locations are referenced.
  • Adobe’s custom attribution engine and proprietary AI generates citations so users can easily verify the source of answers from within the user-provided documents.
  • The AI Assistant responses are for individual consumption only. Even responses on shared documents on web are only accessible to that user.
  • User content, prompts, and responses are encrypted in transit. At rest, data stored by the Acrobat Generative AI Service is encrypted using SHA-256.

https://blog.adobe.com/en/publish/2024/05/08/adobe-acrobat-ai-assistant-enterprise-our-commitment-data-governance-security

« Older posts

© 2024 The Gilbane Advisor

Theme by Anders NorenUp ↑