open source

Video by H2O.ai via YouTube

How h2oGPTe grounds LLMs in enterprise data using multimodal RAG, hybrid search, and autonomous agent workflows.

LLMs don’t inherently know your internal products, policies, or customer history. h2oGPTe bridges this gap by ingesting 50+ file formats—including documents, audio, and video—using multi-engine OCR and native enterprise connectors for SharePoint, S3, and Azure. Hybrid retrieval combines semantic similarity and BM25 with Reciprocal Rank Fusion and cross-encoder reranking for precise, citation-backed answers. Agentic workflows extend RAG further by enabling autonomous retrieval, reasoning, and tool execution.

Technical Capabilities & Resources

➤ Document Ingestion & Transformation: 50+ format support with multi-engine OCR, table preservation, and enterprise connectors.
🔗 https://docs.h2o.ai/enterprise-h2ogpte/guide/collections/supported-file-types

➤ Built-in & External Vector Storage: Includes Vex embedded vector database plus integrations with external vector providers.
🔗 https://docs.h2o.ai/enterprise-h2ogpte/architecture/vector-database

➤ Advanced Hybrid Search: Combines semantic similarity, BM25, Reciprocal Rank Fusion, and cross-encoder reranking.
🔗 https://docs.h2o.ai/enterprise-h2ogpte/guide/chats/chat-settings#generation-approach

➤ Agentic Workflows: Autonomous agents that iteratively retrieve, reason, and trigger tool execution for complex queries.
🔗 https://docs.h2o.ai/enterprise-h2ogpte/guide/agents

Source

Video by FOSSASIA via YouTube

Logical replication in PostgreSQL powers migrations, upgrades, CDC pipelines, and active/active architectures—but at its core, it is a flexible mechanism for transporting ordered data changes.

This talk explores major PostgreSQL 18 improvements to logical replication conflict handling, including explicit conflict detection, classification, and observability. Through live demos, see how conflicts that were once silent or vague apply failures are now visible, structured, and measurable.

Learn why PostgreSQL intentionally avoids built-in conflict resolution, allowing higher-level tools to implement safe and predictable behavior for blue/green deployments, migrations, and multi-active systems. We’ll also look ahead at the future of PostgreSQL logical replication and conflict management.

FOSSASIA Summit 2026 held in Bangkok, is Asia’s leading Open Source tech conference featuring sessions on #AI, #Cloud, #DevOps, #Open Hardware, #Security, #Web #Mobile Technologies, #Web3, and #Databases. Learn more: http://summit.fossasia.org

Session slides: https://eventyay.com/e/88882f3e/session/10491

#FOSSASIA #FOSSASIASummit #opensource #FOSS

Source

Video by FINOS via YouTube

Vincent Caldeira (Field CTO at Red Hat) explores the urgent need for Sovereign AI in financial services. He explains how open source provides the only viable path to independent control over infrastructure, data, and models, ensuring banks don’t just "rent opaque intelligence".

🇬🇧 Join us in London! Catch the latest on Sovereign AI and Open Source at OSFF London on June 25, 2026: https://hubs.ly/Q041YV9Z0 (Use Code: 26YTOSFFLN20C)

🕒 Timestamps:
0:00 Welcome: Why Sovereign AI Matters in Canada
0:45 The Tipping Point: Board Interest vs. Regulatory Scrutiny
1:15 Defining Sovereign AI in Finance
1:45 Operational Resilience and Data Exposure
2:15 Concentration Risk: The Danger of Single-Vendor Dependency
2:45 Explainability and OSFI Guidelines
3:15 Open Source as the Answer: The Platform Layer
4:15 The Rise of Open Models vs. Frontier Models
5:00 Governance as Proof: The AI Governance Framework
5:30 Three Takeaways: Platform, Supply Chain, and Industry Standards

📊 The Problem: Renting "Opaque Intelligence" When financial institutions rely on closed, proprietary AI vendors, they surrender control over their entire AI stack. This creates significant banking risks: Operational Resilience due to data exposure , Concentration Risk through single-vendor dependency , and Model Risk where decisions cannot be explained to regulators.

🏗️ The Solution: The Sovereign AI Stack
Vincent proposes a three-layer approach to achieving independent control using open technology:
* Open Platform Foundation: Building AI-as-a-Service using open technologies like Kubernetes and vLLM to run independently of specific infrastructure.
* Model Parity: Leveraging open models that have caught up to proprietary ones, allowing banks to tune them with private data within their own firewalls.
* Machine-Readable Governance: Using the FINOS AI Governance Framework to demonstrate control through automated, auditable policies.

⚙️ Why This Matters for Financial Engineering
* Supply Chain Transparency: Understanding where data comes from and how models are trained to mitigate systemic risks.
* Regulatory Proof: Building a governance framework that is truly in line with industry needs and provides "evidence" of compliance.

The takeaway: You must have independent control over your infrastructure, data, and models to truly own your AI future. Vincent Caldeira proves that open source is the essential foundation for Sovereign AI in finance.

🌐 More about FINOS: https://www.finos.org/
📧 Join our newsletter: https://www.finos.org/sign-up
🎙️ Listen to our Open Source in Finance Podcast: https://www.youtube.com/@FINOS/podcasts
LinkedIn: https://www.linkedin.com/company/finosfoundation

#FINOS #OSFFToronto #RedHat #SovereignAI #OpenSource #FinTech #BankingInnovation #AIGovernance #DigitalTransformation

Source

Video by The Late Night Linux Family via YouTube

Support us on Patreon and get an ad-free RSS feed with some early episodes. https://www.patreon.com/LateNightLinux

There’s a new Ubuntu LTS release and quite a lot is new, Canonical’s infrastructure was taken down and we disagree about whether it could have been avoided, two recent examples of irresponsible vulnerability disclosure, and the Steam controller finally arrives with a hefty price tag.

https://latenightlinux.com/late-night-linux-episode-384/

Source

Video by Michael Tunnell via YouTube

Ubuntu 26.04 is one of those LTS releases where the small details say a lot about where Linux desktop is going.

Follow for more #Linux and #tech #news

Full episode at https://thisweekinlinux.com/343

#podcast #technology #opensource

Source

Video by TWiT Tech Podcast Network via YouTube

AirPods Pro offer seamless Apple device switching and excellent noise cancellation. Even with previous versions working fine, the latest generation is a must-have for the ultimate audio experience. #AirPodsPro #Apple #TechReview #Accessory

Source

Video by Rasa via YouTube

We’ve never had this level of user context before.

Soon, brands will be able to personalize every interaction in real time by injecting the right data at the right moment into AI systems.

This is what the future of customer experience looks like:
context-aware, dynamic, LLM-driven interactions.

Insights from Etie Hertz (GM of Conversational Intelligence @Contentsquare)

#conversationalai #LLM #customerexperience #personalization #AI

Source