$ timeahead_
all sourcesAhead of AI (Sebastian Raschka)Anthropic NewsApple Machine Learning ResearchArs Technica AIAWS Machine Learning BlogCerebras BlogCohere BlogCrewAI BlogDeepSeek BlogDistill.pubfast.ai BlogFireworks AI BlogGoogle AI BlogGoogle Cloud AI BlogGoogle DeepMind BlogGroq BlogHaystack (deepset) BlogHugging Face BlogImport AI (Jack Clark)LangChain BlogLangFuse BlogLil'Log (Lilian Weng)LlamaIndex BlogMeta AI BlogMicrosoft AutoGen BlogMicrosoft Research BlogMistral AI NewsMIT Technology ReviewModal Blogn8n BlogNathan Lambert (RLHF)NVIDIA Developer BlogOllama BlogOpenAI BlogPerplexity AI BlogPyTorch BlogReplicate BlogSimon Willison BlogTensorFlow BlogThe Batch (DeepLearning.AI)The GradientThe Verge AITogether AI BlogVentureBeat AIvLLM BlogWeights & Biases BlogWired AIxAI (Grok) Blog
allapiagentsframeworkshardwareinframodelopen sourcereleaseresearchtutorial
★ TOP STORY[ H(B ]Tutorial·5d ago

Latest Agent LLM Prompting Context Engineering Kacper Łukawski Lead DevRel at Deepset Context Engineering for Agentic Systems: What Goes Into Your Agent's Mind A practical introduction to context engineering - what fills the LLM context window in agentic systems, why it matters, and how to keep it under control. April 20, 2026

Context Engineering for Agentic Systems: What Goes Into Your Agent's Mind A practical introduction to context engineering - what fills the LLM context window in agentic systems, why it matters, and how to keep it under control. April 20, 2026Every new generation of Large Language Models arrives with a bigger context window - and the temptation to use it fully. If the model can read a million tokens, why not feed it everything? In practice, more context doesn’t reliably mean better answers: it often means higher costs, slower responses, and a model that loses track of what actually matters. Context engineering is the discipline of deciding not just what to put in the context window, but how much, in what form, and when to leave things out - and it’s quickly becoming one of the most important skills in building…

Haystack (deepset) Blogread →
▲ trending · last 48hview all →
[H(B]Haystack (deepset) Blog· 9 articlesvisit →
46d ago
Multimodality Embeddings Bilge Yücel DevRel Engineer Stefano Fiorucci AI/Software Engineer Multimodal Search with Gemini Embedding 2 in Haystack Build multimodal search systems in Haystack using Gemini Embedding 2 to embed text, images, video, audio, and PDFs in a shared vector space. March 10, 2026
Multimodal Search with Gemini Embedding 2 in Haystack Build multimodal search systems in Haystack using Gemini Embedding 2 to embed text, images, video, audio, and PDFs in a shared vector space. March 10, 2026Embeddings are the backbone of modern AI applications, from semantic search and recommendation systems to Retrieval-Augmented Generation (RAG). However, most embedding models operate in a single modality, typically focusing only on textual data. Google has introduced Gemini Embedding 2, a fully multimodal embedding model that maps text, images, video, audio, and PDFs into a shared vector space. This means you can search across different types of data using a single embedding model: gemini-embedding-2-preview . Even better, Haystack supports Gemini Embedding 2 from Day 0. Through the Google GenAI x Haystack integration, you can immediately start using the model in your Haystack applications for both text and multimodal…
114d ago
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 generation (RAG) applications, the quality of the retrieved documents plays a critical role in delivering accurate and meaningful responses. But what happens when embedding similarity is not enough to get an accurate ordering of the reference documents? This is where reranking comes into play. What’s Reranking? Reranking refers to assigning a relevance score to each document based on how well it matches the query. Reranking reorders the retrieved documents to ensure the most contextually relevant results are at the top. This is important because while the retrieval stage focuses on recall, considering relevance broadly, reranking “fine-tunes” the results for increased precision. Examples of Reranking Consider a query like, “What are the best practices for securing a REST API?” The retrieval model might return a ranked list…
114dResearch#rag#agents#gpu
127d ago
Community Bilge Yücel DevRel Engineer Haystack Ecosystem: One Name, One Product Family, One Look One unified Haystack ecosystem, from open source to enterprise-scale AI systems. December 19, 2025
Haystack Ecosystem: One Name, One Product Family, One Look One unified Haystack ecosystem, from open source to enterprise-scale AI systems. December 19, 2025We’re making some naming and visual updates at deepset to better reflect the role Haystack already plays as a framework, a community, and the foundation of our enterprise platform. If you’re already building with Haystack, nothing is changing in how you build or run applications. This update is about clarity, making the Haystack ecosystem easier to understand, easier to navigate, and centered around a single open foundation. The Open Source to Enterprise Story of Haystack Haystack began as an open-source framework for building NLP pipelines, created to give developers precise control over how AI systems are composed, debugged, and run in production. From the start, it was designed for real-world use, not just experimentation. Over time, the framework…
127dFrameworks#open-source
183d ago
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 an enterprise-grade, compliant AI knowledge assistant October 24, 2025When you think of Lufthansa, you might picture planes, airports, or global travel, but Lufthansa Industry Solutions (LHIND) is making an impact in a different way: as a full-service IT company delivering digital solutions for clients both inside and outside the Lufthansa Group. At LHIND, a subsidiary of the Lufthansa Group, teams work on a wide range of projects that span cloud infrastructure, AI, and enterprise data systems to custom software development, process automation, and digital transformation initiatives. Among them is SmartAssistantAI, an enterprise AI chatbot implementation to make company knowledge accessible to everyone, instantly and securely. Behind the product is Nils Hilgers, Lead AI Engineer at LHIND and his team of engineers and product builders.…
183dTutorial#rag
201d ago
User Story Bilge Yücel DevRel Engineer Kelsey Sorrels Data Scientist at Telus AG How TAC Built an Agentic Chatbot with Haystack to Transform Trade Promotions Workflows See how TELUS Agriculture & Consumer Goods (TAC) gives users unprecedented access to their data with safety in mind October 6, 2025
How TAC Built an Agentic Chatbot with Haystack to Transform Trade Promotions Workflows See how TELUS Agriculture & Consumer Goods (TAC) gives users unprecedented access to their data with safety in mind October 6, 2025When a leading company like TELUS Agriculture & Consumer Goods (TAC), with a strong presence in agriculture and consumer goods, turns to AI to streamline complex processes, it’s worth taking a closer look. TELUS Agriculture & Consumer Goods helps businesses optimize everything from supply chains to retail operations. One of their latest innovations: an agentic chatbot powered by Haystack that simplifies how users interact with their trade promotions platform. We sat down with the team behind this project to learn how they built it, why they chose Haystack, and what advice they have for other teams looking to implement Retrieval-Augmented Generation (RAG) and agent-based AI solutions…
201dAgents#agents#safety
267d ago
Community Bilge Yücel DevRel Engineer Announcing Haystack Enterprise Starter: Best Practices and Support A Faster Way to Build and Scale Production-Grade AI Apps August 1, 2025
Announcing Haystack Enterprise Starter: Best Practices and Support A Faster Way to Build and Scale Production-Grade AI Apps August 1, 2025💙 Thanks to you and all of our amazing community members, the Haystack open source framework has grown into a thriving developer ecosystem, now used by thousands of organizations to power everything from simple Q&A bots to advanced enterprise agents. As more teams run Haystack in production, one thing has become increasingly clear: building reliable AI systems is hard and scaling them securely is even harder. We’ve had a front-row seat to these challenges. Across GitHub threads, meetups, community calls, and production deployments, developers have consistently asked for engineering support and hands-on guidance to build for their use case, accelerate deployment, improve observability, and scale infrastructure with confidence. These aren’t just feature requests; they reflect the real-world friction points of…
267dFrameworks
319d ago
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 with a local LLM endpoint June 10, 2025Welcome to this step-by-step tutorial where we’ll build a simple Retrieval-Augmented Generation (RAG) pipeline using Haystack and OPEA. We’ll fetch the newest Hacker News posts, feed them to a lightweight LLM endpoint (OPEAGenerator ), and generate concise one-sentence summaries (based on this notebook). Let’s dive in! 🎉 1. Introduction & Motivation In modern GenAI applications, having a flexible, performant, and scalable platform is essential. OPEA (Open Platform for Enterprise AI) is an open, model-agnostic framework for building and operating composable GenAI solutions. It provides: - A library of microservices (LLMs, data stores, prompt engines) and higher-order megaservices for end-to-end workflows - HTTP-based inference with multi-model support (open- and closed-source) - Advanced features…
348d ago
Hayhooks Deployment Isabelle Nguyen Technical Content Writer Michele Pangrazzi Senior Software Engineeer Deploy AI Pipelines Faster with Hayhooks Turn Haystack pipelines into production-ready REST APIs or expose them as MCP tools with full customization and minimal code May 12, 2025
Deploy AI Pipelines Faster with Hayhooks Turn Haystack pipelines into production-ready REST APIs or expose them as MCP tools with full customization and minimal code May 12, 2025Haystack is an AI orchestration framework that enables developers to effortlessly build custom AI pipelines using a modular, building-block approach. However, when it’s time to take those pipelines from your development environment to production, you’re often left with a tough decision: write custom server code, or rely on proprietary tools that may not offer the flexibility you need. We’re excited to announce Hayhooks, an open source package designed to simplify deployment. It lets you focus on developing meaningful AI systems rather than worrying about the underlying infrastructure. With Hayhooks, you can deploy Haystack pipelines with custom logic, expose OpenAI-compatible chat endpoints, stream responses in real time, and customize your server—all with minimal code…
348dInfra#coding
451d ago
Next
Blog Articles about Haystack, LLMs, Agents, and latest AI technologies. All articles Use DeepSeek-R1 with Haystack: Demo and Tutorial Compare DeepSeek-R1 and OpenAI's o1 in the deepset demo and explore their reasoning capabilities January 29, 2025Build an Agentic RAG Pipeline in deepset Studio Use deepset Studio to build an agentic Haystack pipeline with a fallback mechanism for dynamic web search January 14, 2025Announcing Advent of Haystack 2024 🎄 Join the Festive AI Fun! December 2, 2024Create a Swarm of Agents Easy creation of multi-agent systems November 26, 2024Announcing Studio: Your Development Environment for Haystack Build, deploy, and test Haystack pipelines with ease November 20, 2024Building a Multimodal Nutrition Agent Use fastRAG and Haystack to build an agent that can process text and image data November 7, 2024Design Haystack AI Applications Visually in deepset Studio with NVIDIA NIM November 1, 2024Advanced…
451dFrameworks#open-source