#rag

Samsung’s memory chip employees negotiated $340,000 bonuses this year

Details have emerged about a tentative deal struck between Samsung and semiconductor employees who had threatened to str…

The Enhanced Games fit right in with the rest of 2026’s longevity vibes

The Enhanced Games fit right in with the rest of 2026’s longevity vibes We’re evidently in our enhancement era. This Sun…

Build AI agents for business intelligence with Amazon Bedrock AgentCore

Artificial Intelligence Build AI agents for business intelligence with Amazon Bedrock AgentCore OPLOG, a technology-driv…

Simulate real-world places with Project Genie and Street View

Simulate real-world places with Project Genie and Street View Genie is our general-purpose world model capable of genera…

GDS weighs in on the NHS's decision to retreat from Open Source

17th May 2026 - Link Blog GDS weighs in on the NHS's decision to retreat from Open Source. Terence Eden continues his co…

The Download: China’s AI drama factory and the WHO’s missing health targets

The Download: China’s AI drama factory and the WHO’s missing health targets Plus: as their trial goes to the jury, Musk …

How Chinese short dramas became AI content machines

How Chinese short dramas became AI content machines The viral short dramas are increasingly being created entirely with …

Trump’s Tech Posse in China, Who’s Winning in Musk v. Altman, and Hantavirus Conspiracy Theories

This week on Uncanny Valley, the team dives into Trump’s selected entourage for his high-stakes visit to China, ranging …

Gen Z Is Pioneering a New Understanding of Truth

The polar bear video has millions of views. Set to a haunting piano score that's become ubiquitous on TikTok, it shows a…

Desperate Trump taps "Tim Apple," Jensen Huang, Elon Musk to attend Xi summit

Donald Trump has very little leverage heading into two days of meetings with China’s leader, Xi Jinping, in Beijing this…

Everyone at the Musk v. Altman Trial Is Using Fancy Butt Cushions

The final stragglers testified on Wednesday in the Musk v. Altman trial. The witnesses generated few waves, aside from t…

mimalloc: A new, high-performance, scalable memory allocator for the modern era

At a glance - Today’s critical services and applications are often highly concurrent, using hundreds of threads. They al…

Parents say ChatGPT got their son killed with bad advice on party drugs

The family of a 19-year-old college student is suing OpenAI over claims that his conversations with ChatGPT led to an ac…

Using LLM in the shebang line of a script

11th May 2026 Kim_Bruning on Hacker News: But seriously, you can put a shebang on an english text file now (if you're su…

Building Blocks for Foundation Model Training and Inference on AWS

Building Blocks for Foundation Model Training and Inference on AWS Figure: Adapted from "AI's Three Scaling Laws, Explai…

Fostering breakthrough AI innovation through customer-back engineering

Sponsored Fostering breakthrough AI innovation through customer-back engineering Agentic AI is helping organizations com…

Chrome's 4GB AI model isn't new, but you're not wrong for being confused

All of Google’s products have been getting more AI features, including Chrome, which now offers split-screen Gemini chat…

Advanced RAG: Data Cleaning and Retrieval Techniques

Retrieval-augmented generation (RAG) makes queries smarter, arming them with proprietary data and contextualized knowled…

Vibe coding and agentic engineering are getting closer than I'd like

Vibe coding and agentic engineering are getting closer than I’d like 6th May 2026 I recently talked with Joseph Ruscio a…

Google's Gemma 4 AI models get 3x speed boost by predicting future tokens

Google launched its Gemma 4 open models this spring, promising a new level of power and performance for local AI. Google…

Chrome’s AI features may be hogging 4GB of your computer storage

Google Chrome may be taking up more of your storage than expected thanks to a large on-device AI model file that, in som…

A blueprint for using AI to strengthen democracy

A blueprint for using AI to strengthen democracy AI is changing what it means to be a democratic citizen. Here’s how we …

The Zig project's rationale for their firm anti-AI contribution policy

30th April 2026 Zig has one of the most stringent anti-LLM policies of any major open source project: No LLMs for issues…

Unleashing Agentic AI Analytics on Amazon SageMaker with Amazon Athena and Amazon Quick

Artificial Intelligence Unleashing Agentic AI Analytics on Amazon SageMaker with Amazon Athena and Amazon Quick Modern e…

The Download: storing nuclear waste and orchestrating agents

The Download: storing nuclear waste and orchestrating agents Plus: Elon Musk says Sam Altman “stole a charity” at the Op…

Elon Musk appeared more petty than prepared

Today the first witness was sworn in in Musk v. Altman: Elon Musk. I was surprised by how flat he seemed. Elon Musk appe…

Choco automates food distribution with AI agents

Choco automates food distribution with AI agents Using OpenAI APIs, Choco processes millions of orders, reducing manual …

OpenAI available at FedRAMP Moderate

OpenAI has achieved FedRAMP 20x Moderate authorization(opens in a new window) for ChatGPT Enterprise and API Platform, m…

The AI-designed car is taking shape

The auto design world is full of advanced 3D visualization tools and VR sculpting platforms, but your average new car st…

How Popsa used Amazon Nova to inspire customers with personalised title suggestions

Artificial Intelligence How Popsa used Amazon Nova to inspire customers with personalised title suggestions This post wa…

Build and deploy an automatic sync solution for Amazon Bedrock Knowledge Bases

Artificial Intelligence Build and deploy an automatic sync solution for Amazon Bedrock Knowledge Bases With Amazon Bedro…

AutoAdapt: Automated domain adaptation for large language models

At a glance - Problem: Adapting large language models to specialized, high-stakes domains is slow, expensive, and hard t…

Cost-effective multilingual audio transcription at scale with Parakeet-TDT and AWS Batch

Artificial Intelligence Cost-effective multilingual audio transcription at scale with Parakeet-TDT and AWS Batch Many or…

CyberAgent moves faster with ChatGPT Enterprise and Codex

CyberAgent moves faster with ChatGPT Enterprise and Codex CyberAgent uses ChatGPT Enterprise and Codex to help teams wor…

Cut Checkpoint Costs with About 30 Lines of Python and NVIDIA nvCOMP

Training LLMs requires periodic checkpoints. These full snapshots of model weights, optimizer states, and gradients are …

Integrate Physical AI Capabilities into Existing Apps with NVIDIA Omniverse Libraries

Physical AI—AI systems that perceive, reason, and act in physically grounded simulated environments—is changing how team…

RAG System Architecture: Components, How To Implement, Challenges, and Best Practices

A simple retrieval augmented generation architecture (RAG) setup usually works fine with a few documents and a basic ret…

Any Custom Frontend with Gradio's Backend

gradio.Server: Any Custom Frontend with Gradio's Backend gr.HTML : building rich, interactive frontends entirely inside …

Building NVIDIA Nemotron 3 Agents for Reasoning, Multimodal RAG, Voice, and Safety

Agentic AI is an ecosystem where specialized models work together to handle planning, reasoning, retrieval, and safety g…

Design, Simulate, and Scale AI Factory Infrastructure with NVIDIA DSX Air

Building AI factories is complex and requires efficient integration across compute, networking, security, and storage sy…

Introducing NVIDIA BlueField-4-Powered CMX Context Memory Storage Platform for the Next Frontier of AI

AI‑native organizations increasingly face scaling challenges as agentic AI workflows drive context windows to millions o…

Introducing Storage Buckets on the Hugging Face Hub

Introducing Storage Buckets on the Hugging Face Hub Storage Buckets are built exactly for this: mutable, S3-like object …

Build Multi-Domain RAG Systems with Specialized Knowledge Bases

This Verified Node Spotlight was written by Jenna Pederson, Staff Developer Advocate for Pinecone. Imagine you manage mu…

How Axios uses AI to help deliver high-impact local journalism

How Axios uses AI to help deliver high-impact local journalism A conversation with Allison Murphy, Chief Operating Offic…

Building Telco Reasoning Models for Autonomous Networks with NVIDIA NeMo

Autonomous networks are quickly becoming one of the top priorities in telecommunications. According to the latest NVIDIA…

Awakening Sleeping Beauties at The Met

Collaborating with The Met to Awaken “Sleeping Beauties” with AI At OpenAI, we believe AI can enrich our lives by making…

Genmab launches “AI Everywhere”

Genmab launches “AI Everywhere” Genmab(opens in a new window), a leading global biotechnology company, is pioneering nex…

IBM and UC Berkeley Diagnose Why Enterprise Agents Fail Using IT-Bench and MAST

IBM and UC Berkeley Diagnose Why Enterprise Agents Fail Using IT-Bench and MAST ITBench HF Space ITBench HF Dataset MAST…

Build AI-Ready Knowledge Systems Using 5 Essential Multimodal RAG Capabilities

Enterprise data is inherently complex: real-world documents are multimodal, spanning text, tables, charts and graphs, im…

DeepSeek-V3.2 on GB300: Performance Breakthrough Feb 13, 2026 · 12 min read DeepSeek-V3.2 (NVFP4 + TP2)has been successfully and smoothly run on GB300 (SM103 - Blackwell Ultra). Leveraging FP4 quantization, it achieves a single-GPU throughput of 7360 TGS (tokens / GPU /...

DeepSeek-V3.2 on GB300: Performance Breakthrough Summary DeepSeek-V3.2 (NVFP4 + TP2)has been successfully and smoothly r…

Harness engineering: leveraging Codex in an agent-first world

Harness engineering: leveraging Codex in an agent-first world By Ryan Lopopolo, Member of the Technical Staff Over the p…

Testing ads in ChatGPT

Update on March 26, 2026: Our ads pilot is focused on supporting broader access to ChatGPT while preserving consumer tru…

Transformers.js v4: Now Available on NPM!

Transformers.js v4: Now Available on NPM! npm i @huggingface/transformers Performance & Runtime Improvements The biggest…

How to Build a Document Processing Pipeline for RAG with Nemotron

What if your AI agent could instantly parse complex PDFs, extract nested tables, and “see” data within charts as easily …

Establishing a Scalable Sparse Ecosystem with the Universal Sparse Tensor

Sparse tensors are vectors, matrices, and higher-dimensional generalizations with many zeros. They are crucial in variou…

Import AI 442: Winners and losers in the AI economy; math proof automation; and industrialization of cyber espionage

Import AI 442: Winners and losers in the AI economy; math proof automation; and industrialization of cyber espionage Is …

How countries can end the capability overhang

How countries can end the capability overhang By George Osborne, Head of OpenAI for Countries AI is advancing at extraor…

NVIDIA DLSS 4.5 Delivers Super Resolution Upgrades and New Dynamic Multi Frame Generation

NVIDIA DLSS 4 with Multi Frame Generation has become the fastest-adopted NVIDIA gaming technology ever. Over 250 games a…

Zenken boosts a lean sales team with ChatGPT Enterprise

Zenken boosts a lean sales team with ChatGPT Enterprise Zenken is rethinking sales with AI—cutting preparation time, imp…

OpenAI and SoftBank Group partner with SB Energy

OpenAI and SoftBank Group partner with SB Energy - SoftBank Group and OpenAI invest $1 billion in SB Energy to support i…

Retrieval RAG Evaluation Rita Fernandes Neves Senior Solution Architect - AI at NVIDIA Bilge Yücel DevRel Engineer Optimize RAG Applications with Document Reranking Using Haystack With NVIDIA NeMo Retriever March 20, 2025

Optimize RAG Applications with Document Reranking Using Haystack With NVIDIA NeMo Retriever In retrieval-augmented gener…

12/15/2025 NVIDIA Nemotron 3 Nano on Fireworks: The Engine for Next-Generation AI Agents

We're excited to launch Day-0 support on Fireworks for the latest model in the NVIDIA Nemotron family, NVIDIA Nemotron 3…

Our approach to mental health-related litigation

Our approach to mental health-related litigation Cases involving mental health are tragic and complex, and they involve …

OpenAI and Target team up on new AI-powered experiences

OpenAI and Target partner to bring new AI-powered experiences across retail Key takeaways: - With the Target app in Chat…

Intuit and OpenAI join forces on new AI-powered experiences

Intuit and OpenAI join forces on new AI-powered experiences Key takeaways: - Multi-year strategic partnership will soon …

Neuro drives national retail wins with ChatGPT Business

Neuro drives national retail wins with ChatGPT Business Neuro uses ChatGPT Business to move faster across sales and oper…

Build to Last

Note from Jeremy: We’re teaching a course starting Nov 3rd on how to build towards software mastery and craftsmanship wh…

User Story Bilge Yücel DevRel Engineer Nils Hilgers Lead AI Engineer @LHIND Lufthansa Industry Solutions Uses Haystack to Power Enterprise RAG Learn how Lufthansa Industry Solutions (LHIND) built an enterprise-grade, compliant AI knowledge assistant October 24, 2025

Lufthansa Industry Solutions Uses Haystack to Power Enterprise RAG Learn how Lufthansa Industry Solutions (LHIND) built …

Unlock the power of images with AI Sheets

Unlock the power of images with AI Sheets 🧭TL;DR: Hugging Face AI Sheets is an open-source tool for supercharging datas…

7/10/2025 Using Model-as-a-Judge for Reward in Reinforcement Fine Tuning

In domains that are inherently challenging to quantify, such as creative writing, we demonstrate that leveraging a super…

Building OpenAI with OpenAI

Chief Commercial Officer, Giancarlo ‘GC’ Lionetti, kicks off our series sharing internal examples of how OpenAI is using…

Which image editing model should I use?

Which image editing model should I use? Replicate Playground In the past few weeks, nearly every major AI lab has releas…

SafetyKit scales risk agents with OpenAI’s most capable models

SafetyKit scales risk agents with OpenAI’s most capable models From prototyping with early vision model previews to scal…

mmBERT: ModernBERT goes Multilingual

mmBERT: ModernBERT goes Multilingual TL;DR This blog post introduces mmBERT, a state-of-the-art massively multilingual e…

Welcome EmbeddingGemma, Google's new efficient embedding model

Welcome EmbeddingGemma, Google's new efficient embedding model TL;DR Today, Google releases EmbeddingGemma, a state-of-t…

4/9/2025 Building Enterprise-Scale RAG Systems with Fireworks AI and MongoDB Atlas

In the fast-paced world of enterprise data, extracting actionable insights from vast amounts of unstructured information…

Scaling domain expertise in complex, regulated domains

Blue J’s approach for scaling fast in complex, regulated domains Blue J scaled its AI-powered tax research system to thr…

Day Zero Support for OpenAI Open Models

Day Zero Support for OpenAI Open Models Fast and Affordable AI Inference For the World’s Most Popular Models We're excit…

Parquet Content-Defined Chunking

Parquet Content-Defined Chunking TL;DR: Parquet Content-Defined Chunking (CDC) is now available in PyArrow and Pandas, e…

AI as the greatest source of empowerment for all

AI as the greatest source of empowerment for all Fidji Simo In a few weeks, I’ll be joining OpenAI as CEO of Application…

Accelerate a World of LLMs on Hugging Face with NVIDIA NIM

Accelerate a World of LLMs on Hugging Face with NVIDIA NIM NVIDIA AI customers and ecosystem partners leverage NVIDIA NI…

Working with 400,000 teachers to shape the future of AI in schools

Working with 400,000 teachers to shape the future of AI in schools OpenAI joins the American Federation of Teachers to l…

STARFlow-V: End-to-End Video Generative Modeling with Normalizing Flows

STARFlow-V: End-to-End Video Generative Modeling with Normalizing Flows AuthorsJiatao Gu†, Ying Shen‡**, Tianrong Chen, …

LLM RAG Daniel Fleischer Research Engineer at Intel Labs Summarize Hacker News Posts with Haystack & OPEA Build a RAG pipeline to fetch live Hacker News posts and summarize them with a local LLM endpoint June 10, 2025

Summarize Hacker News Posts with Haystack & OPEA Build a RAG pipeline to fetch live Hacker News posts and summarize them…

5/28/2025 FireAttention V4: Industry-Leading Latency and Cost Efficiency with FP4

Today, we’re announcing we've achieved industry-leading speeds of >250 tokens/second on NVIDIA B200 GPUs using our lates…

The Transformers Library: standardizing model definitions

The Transformers Library: standardizing model definitions Transformers was created in 2019, shortly following the releas…

Vision Language Models (Better, faster, stronger)

Vision Language Models (Better, faster, stronger) Motivation Vision Language Models (VLMs) are the talk of the town. In …

Lowe’s leverages AI to power home improvement retail

Lowe’s leverages AI to power home improvement retail A conversation with Chandhu Nair, Senior Vice President of Data, AI…

Arabic Leaderboards: Introducing Arabic Instruction Following, Updating AraGen, and More

Arabic Leaderboards: Introducing Arabic Instruction Following, Updating AraGen, and More As part of our ongoing efforts,…

Canva enables creativity with AI

Canva enables creativity with AI A conversation with Cameron Adams, Chief Product Officer and Co-founder of Canva. Our E…

AI Policy @🤗: Response to the White House AI Action Plan RFI

AI Policy @🤗: Response to the White House AI Action Plan RFI Context: Don't Sleep on (Strongly) Open Models' Capabiliti…

Xet is on the Hub

Xet is on the Hub Over the past few weeks, Hugging Face’s Xet Team took a major step forward by migrating the first Mode…

Product 11/3/2025 40X Faster, and Smarter Outputs: How Vercel Turbocharged their Code Fixing Model with Open Models, Speculative Decoding and Reinforcement Fine Tuning on Fireworks

Vercel, a leading platform provider for full-stack web applications, partnered with Fireworks to solve a critical challe…

Nubank elevates customer experiences with OpenAI

Nubank elevates customer experiences with OpenAI Since its founding in 2013, Nubank—one of the world’s largest digital f…

HuggingFace, IISc partner to supercharge model building on India's diverse languages

HuggingFace, IISc partner to supercharge model building on India's diverse languages Partnership The partnership between…

Build awesome datasets for video generation

Build awesome datasets for video generation hlky and Sayak) Tooling for image generation datasets is well established, w…

Understanding Reasoning LLMs

Understanding Reasoning LLMs Methods and Strategies for Building and Refining Reasoning Models This article describes th…

Strengthening America’s AI leadership with the U.S. National Laboratories

Strengthening America’s AI leadership with the U.S. National Laboratories OpenAI’s latest line of reasoning models will …

Welcome to Inference Providers on the Hub 🔥

Welcome to Inference Providers on the Hub 🔥 We’ve been hosting a serverless Inference API on the Hub for a long time (w…

Supporting sellers with enhanced product listings

Mercari enhances product listings and better supports sellers with GPT‑4o mini Mercari, one of Japan’s leading online ma…