Curated for content, computing, and digital experience professionals

Month: June 2024 (Page 1 of 2)

Elastic introduces Playground to accelerate RAG development with Elasticsearch

Elastic announced Playground, a low-code interface that enables developers to build RAG applications using Elasticsearch in minutes.

While prototyping conversational search, the ability to rapidly iterate on and experiment with key components of a RAG workflow (for example: hybrid search, or adding reranking) are important— to get  accurate and hallucination-free responses from LLMs.

Elasticsearch vector database and the Search AI platform provides developers with a wide range of capabilities such as comprehensive hybrid search, and to use innovation from a growing list of LLM providers. Our approach in our playground experience allows you to use the power of those features, without added complexity.

Playground’s intuitive interface allows you to A/B test different LLMs from model providers (like OpenAI and Anthropic) and refine your retrieval mechanism, to ground answers with your own data indexed into one or more Elasticsearch indices. The playground experience can leverage transformer models directly in Elasticsearch, but is also amplified with the Elasticsearch Open Inference API which integrates with a growing list of inference providers including Cohere and Azure AI Studio.

Franz announces AllegroGraph 8.2

Franz Inc., a supplier of Graph Database technology for Entity-Event Knowledge Graph Solutions, announced AllegroGraph 8.2, a Neuro-Symbolic AI Platform, with enhancements to ChatStream offering users a natural language query interface that provides more accurate and contextually relevant responses. ChatStream’s Graph RAG with Feedback enables more accurate, context-aware, and continuously evolving natural language queries, providing stateful and contextually relevant responses. Additional updates include:

Knowledge Graph-as-a-Service – A new hosted, free version grants users access to AllegroGraph with LLMagic via a web login.

Enhanced Scalability and Performance – AllegroGraph includes enhanced FedShard capabilities making the management of sharding more straightforward and user-friendly, reducing query response time and improving system performance.

New Web Interface – AllegroGraph includes a redesign of its web interface, AGWebView, that provides an intuitive way to interact with the platform, while co-existing with the Classic View.

Advanced Knowledge Graph Visualization – A new version of Franz’s graph visualization software, Gruff v9, is integrated into AllegroGraph. Gruff now includes the ChatStream Natural Language Query feature as a new means to query your Knowledge Graph and is a visualization tool that illustrates RDF-Star (RDF*) annotations, enabling users to add descriptions to edges in a graph – such as scores, weights, temporal aspects and provenance.

Box enhances Box AI for intelligent content management

Box, Inc. announced that end user queries in Box AI for Hubs, Documents, and Notes will be unlimited for customers on its Enterprise Plus plan. Box also unveiled a new set of features in Box AI that includes an integration with GPT-4o, support for image and spreadsheet files, and the Box AI for Metadata API.

  • Integration with GPT-4o: Box plans to support the new GPT-4o model in Box AI. GPT-4o provides advanced capabilities that help Box Hubs deliver higher quality answers and increased support for over 20 additional languages. Box Hubs users will also benefit from enhanced text-related functionalities including multimodal understanding, ethical and sensitive content handling, and task-specific adaptation.
  • Support for additional file types: Box will support natural language queries on image file formats. Users will be able to execute commands for precise data analysis in spreadsheets, simplifying interactions with large structured data sets.
  • All-New Metadata API: Developers will be able to integrate Box AI with custom applications using the new Box AI for Metadata API to automatically extract key information from documents. Customers will be able to automate processes based on file metadata, extract key fields from unstructured content, and save information to external applications such as Salesforce.

RWS launches Trados Studio 2024

RWS, a provider of technology-enabled language, content and intellectual property solutions, announced the launch of Trados Studio 2024. The latest version of the computer-assisted translation (CAT) tool addresses the evolving needs of users on multiple fronts with access to new AI capabilities, enhanced accessibility features and multiple usability improvements:

New AI capabilities: Trados Studio 2024 gives users access to a range of AI features that help them to work smarter and produce higher quality translations. One of these is Trados Copilot – AI Assistant which brings generative translation capabilities to every user, allowing them to harness Large Language Models (LLMs) in a variety of ways to assist translation. 

New accessibility features: With the accessible, feature-rich CAT tool, the ability to complete a project with screen readers, visually impaired users can now create and manage projects, perform translation and generate target files easily. These advancements in accessibility help create equal opportunities for all and also improve usability and productivity across the supply chain. 

Improved cloud and desktop alignment: Along with hundreds of enhancements, RWS has released a new Manager view, providing a more unified way to work with files and projects in a single window with a clean, modern interface.

Graph analytics enhanced by GraphAware & Senzing

Senzing announced a partnership with GraphAware, a provider of connected data analytics platforms built on Neo4j. This partnership integrates Senzing entity resolution capabilities into GraphAware Hume, GraphAware’s graph-based enterprise intelligence platform, offering valuable data insights and competitive advantages.

GraphAware clients include financial institutions, intelligence agencies, law enforcement agencies, cyber defense advisories and diverse research organizations. GraphAware Hume allows both analysts and data scientists to easily visualize and monitor complex relationships, detect patterns of suspicious activities, and perform powerful machine-assisted link analysis.

Senzing provides a purpose-built AI for entity resolution. With Senzing entity resolution incorporated into the Hume data intelligence platform, users can:

  • Better validate identities
  • Mitigate signal-to-noise challenges in their data
  • Map connections between individuals and other legal entities (e.g., to discover and clarify Ultimate Beneficial Ownership UBO relationships)
  • Build comprehensive 360-degree views of entities

GraphAware Hume connects a wide range of siloed data sources, ingesting large amounts of structured and unstructured data to establish a single source of truth: the Entity Resolved Knowledge Graph (ERKG). With powerful graph visualization capabilities and the ability to seamlessly connect to services like geospatial data from OpenStreetMap and other data providers, GraphAware Hume enhances insights and intelligence across many critical applications.

Gilbane Advisor 6-26-24 — Building LLMs, Apple PCC architecture

This week we feature articles from Eugene Yan, Bryan Bischof, Charles Frye, Hamel Husain, Jason Liu & Shreya Shankar, and Patrick Walsh.

Additional reading comes from Mel Richey, Emma Roth, and Scott Brinker.

News comes from Adobe, Argo Translation, Netlify, Acrolinx.

Next issue arrives July 3.

All previous issues are available at

Opinion / Analysis

What we learned from a year of building with LLMs (Part I – tactical)

“This is the first of three pieces. It dives into the tactical nuts and bolts of working with LLMs. We share best practices and common pitfalls around prompting, setting up retrieval-augmented generation, applying flow engineering, and evaluation and monitoring.”

Eugene Yan, Bryan Bischof, Charles Frye, Hamel Husain, Jason Liu and Shreya Shankar are experienced practitioners in a variety of roles and projects that collaborated to create a unique and valuable lessons-learned resource. Links to Parts 2 – operational, and Part 3 – strategic, are included. (30 min)

Analysis of Apple’s new AI Private Compute Cloud

As others have noted, there has been a lot of confusion about Apple’s Private Compute Cloud (PCC) architecture. Patrick Walsh provides an easily readable and balanced analysis – well worth a read. (12 min)

More Reading

All Gilbane Advisor issues

Content technology news

Adobe updates Acrobat with GenAI and chat across document types

Adobe brings Firefly features into Acrobat so customers can generate and edit images directly in PDFs, and multi-document chat to AI Assistant.

Argo Translation launches CMSConnect: Slack

AI technology translates Slack messages in real-time, improving global team and customer support productivity.

Netlify announces Adobe Experience Manager headless integration

AEM users can leverage the Netlify headless CMS to streamline workflows and reduce the touchpoints needed across multi-channel projects.

Acrolinx launches new AI capabilities

Get Suggestions, AI Assistant, and AI Guardrails make content creation easier, faster, and compliant with your enterprise content standards.

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

Argo Translation launches CMSConnect: Slack

Argo Translation, a Chicago-based language services company, announced the launch of CMSConnect: Slack. The tool simplifies multilingual communication for the nearly 35 million users of Slack, a popular cloud-based team communication platform. This launch marks another addition to Argo Translation’s CMSConnect, a suite of translation connectors that includes translation integrations for a multitude of CMS, PIM, CRM, and DAM platforms, including Microsoft SharePoint, WordPress, and Adobe Experience Manager.

With native integration in the Slack platform, CMSConnect: Slack is easy to use. Once a customer has authorized Argo Translation access to their Slack workspace, customers can choose which of the 80+ languages and dialects they want available to their team. Afterward, users simply add the corresponding flag emoji to the text intended for non-English speakers to prompt an AI translation. Additionally, users can generate a voice message from translated text and translate attached documents.

⁠CMSConnect: Slack workflows are customizable, allowing for the display of a quality score with every translated message. Argo Translation can also implement a custom language model to refine the messages for improved tone, clarity, and grammar.

Acrolinx launches new AI capabilities

Acrolinx, experts in SaaS enterprise content governance, launched new generative AI capabilities to maximize productivity benefits while mitigating risks that AI poses. After a successful Beta program with over 20 enterprise customers, Get Suggestions, AI Assistant, and AI Guardrails are publicly available for organizations to use AI confidently and securely. 

Get Suggestions accelerates the writing and editing phase of content creation. With Get Suggestions, most content improvement recommendations have clickable fixes to align content to complex enterprise standards. Get Suggestions saves writers and editors time, as well as improves content quality based on your organization’s own style guide and content compliance needs. 

AI Assistant accelerates the ideation phase of the writing process. With AI Assistant, content is generated that’s already aligned with your company’s writing standards. Writers get a chatbot experience to request the generation of content.

AI Guardrails for your content makes sure that AI-generated writing is compliant with standards in private deployments of LLMs. AI Guardrails for content standards ensures only high-quality content is used for fine-tuning LLMs, checks the quality of AI-generated content before it’s presented to writers, stops low-quality content from getting published, and checks the quality of content already published.

« Older posts

© 2024 The Gilbane Advisor

Theme by Anders NorenUp ↑