InfoQ Homepage News
-
Microsoft Introduces CoRAG: Enhancing AI Retrieval with Iterative Reasoning
Microsoft AI has introduced Chain-of-Retrieval Augmented Generation (CoRAG), a new AI framework designed to enhance Retrieval-Augmented Generation (RAG) models. Unlike traditional RAG systems, which rely on a single retrieval step, CoRAG enables iterative search and reasoning, allowing AI models to refine their retrievals dynamically before generating answers.
-
AWS CodeBuild Now Supports Fastlane to Simplify iOS Deployments
CodeBuild, AWS continuous integration service, now provides Fastlane support to manage tasks such as code signing, screenshot generation, beta distribution, and app store submissions for iOS, iPadOS, watchOS, tvOS, and macOS apps.
-
OpenAI Releases Reasoning Model o3-mini, Faster and More Accurate Than o1
OpenAI released OpenAI o3-mini, their latest reasoning LLM. o3-mini is optimized for STEM applications and outperforms the full o1 model on science, math, and coding benchmarks, with lower response latency than o1-mini.
-
Prezi's Journey from Prometheus to VictoriaMetrics
Prezi’s engineering team recently discussed their transition from a Prometheus-based monitoring system to VictoriaMetrics, focusing on cost optimization, performance improvements, and architectural simplicity. This transition reduced the costs by approximately 30%, and speed of completion for heavy queries reduced to 3-7 seconds from 30+ seconds.
-
OpenAI Features New o3-mini Model on Microsoft Azure OpenAI Service
OpenAI has launched the advanced o3-mini model via Microsoft Azure, enhancing AI applications with improved cost efficiency, faster performance, and adjustable reasoning capabilities. Designed for complex tasks, it supports structured outputs and backward compatibility. With widespread access, the o3-mini empowers developers to drive innovation across various industries.
-
Micronaut Framework 4.7.0 Provides Integration with LangChain4j and Graal Languages
The Micronaut Foundation has released Micronaut Framework 4.7.0 in December 2024, four months after the release of version 4.6.0. This version provides LangChain4J support to integrate LLMs into Java applications. Micronaut Graal Languages provides integration with Graal-based dynamic languages such as the Micronaut GraalPy feature to interact with Python.
-
Java News Roundup: LangChain4j 1.0-Beta1, JHipster Lite, GlassFish, Spring Cloud Stream Applications
This week's Java roundup for February 3rd, 2025, features news highlighting: the first beta release of LangChain4j 1.0; versions 1.27.0 and 1.28.0 of JHipster Lite; GlassFish 7.0.22; and versions 2025.0.0 and 2024.0.1 of Spring Cloud Stream Applications.
-
Slack Enhances Accessibility Testing through Automation
Slack recently integrated automated accessibility testing into its software development lifecycle to improve user experience for individuals with disabilities. Slack has internal standards and the company further collaborates with external accessibility testers as well. These standards align with WCAG, an internationally recognized benchmark for web accessibility.
-
FerretDB, an Open-Source Alternative to MongoDB, Releases Version 2.0
FerretDB has announced the first release candidate of version 2.0. Now powered by the recently released DocumentDB, FerretDB serves as an open-source alternative to MongoDB, bringing significant performance improvements, enhanced feature compatibility, vector search capabilities, and replication support.
-
Recent Generations of Apple CPUs Affected by New Side-Channel Vulnerabilities
Researchers at the Georgia Institute of Technology and the Ruhr University Bochum demonstrated two new side channel attacks on recent M and A CPUs from Apple that leak sensitive information when using Chrome and Safari to visit popular sites.
-
How Locking, Saturation and CDN Network Issues Brought down Canva
The Canva engineering team recently published their post-mortem on the outage they experienced last November, detailing the API Gateway failure and the lessons learned during the incident.
-
OpenEuroLLM: Europe’s New Initiative for Open-Source AI Development
A consortium of 20 European research institutions, companies, and EuroHPC centers has launched OpenEuroLLM, an initiative to develop open-source, multilingual large language models (LLMs). Coordinated by Jan Hajič and co-led by Peter Sarlin, the project aims to provide transparent and compliant AI models for commercial and public sector applications.
-
How Data Contracts Support Collaboration between Data Teams
Data contracts define the interface between data providers and consumers, specifying things like data models, quality guarantees, and ownership. They are essential for distributed data ownership in data mesh, ensuring data is discoverable, interoperable, and governed. Data contracts improve communication between teams and enhance the reliability and quality of data products.
-
Amazon EventBridge Event Bus Cross-Account Event Delivery
AWS enhances Amazon EventBridge, enabling direct event delivery across accounts. This feature simplifies architecture, boosts security, and reduces latency, allowing seamless routing of events to AWS services like SQS and Lambda. Leverage fine-grained IAM control for streamlined event sourcing. Discover more about this transformative update on AWS documentation and GitHub.
-
OpenAI Launches Deep Research: Advancing AI-Assisted Investigation
OpenAI has launched Deep Research, a new agent within ChatGPT designed to conduct in-depth, multi-step investigations across the web. Initially available to Pro users, with plans to expand access to Plus and Team users, Deep Research automates time-consuming research by retrieving, analyzing, and synthesizing online information.