Evaluation for RAG pipelines - it is essential to properly evaluate before going to production. Challenging, but solvable. Watch Tuana‘s video on this topic.

🚀 Build and Scale Gen AI Applications with Haystack and NVIDIA NIM 🚀 NVIDIA NIM is now globally available! Learn to deploy Haystack RAG pipelines with NIMs in the cloud, on-premise or even in air-gapped environments. haystack.deepset.ai/blog/haystack-…

We're incredibly happy to be a launch partner for NVIDIA NIMs, a collection of brand new containerized microservices designed for optimized inference of state-of-the-art AI models. ​ Haystack provides components that allow you to use both embedding and generative LLM NIMs. ​ To

Haystack and NVIDIA NIMs - a fully controllable RAG stack. Learn more in our article.

Explore a quick guide on deploying #NVIDIANIM with Docker for easier integration of NIM microservices APIs with top #generativeAI frameworks – like Haystack, LangChain and @Llama_index. ➡️ nvda.ws/3wYaE3Z ✨

New projects for Haystack and the AI community coming soon! Thank you to Andrew Ng and DeepLearning.AI for the hospitality last week. And I’m looking forward to sharing our work with everyone 🎸

Last year it was hard to believe, but looking at what is happening now with new models like Llama 3.1 coming out makes it undeniable that AI's future is "multi-model".

🚨 Upcoming livestream alert 🚨 Join Tuana from deepset, makers of Haystack and Aamir Shakir from Mixedbread on August 7th to learn about our jointly released embedding model: deepset-mxbai-embed-de-large-v1 We will discuss binary quantization, MRL, and how you can start using this model

Retrieval is key to RAG and here you will learn a lot about how to bring it to the next level

We have some great news 🚀 We're launching a short course in collaboration with DeepLearning.AI very soon: Building AI Applications with Haystack Sign up for the waitlist 👇 deeplearning.ai/short-courses/…

Build and customize complex AI applications with a flexible framework in this new short course, Building AI Applications with Haystack. Created in collaboration with deepset, and taught by Tuana, who is the developer relations lead for Haystack at deepset. Generative

🎉 New AI course alert! 🎉 Building AI Applications with Haystack, made in collab with DeepLearning.AI & Andrew Ng , is live. Learn to build flexible, maintainable AI apps with Haystack from our very own Tuana: deeplearning.ai/short-courses/…

Excited to share that deepset has been recognized as a 2024 Gartner® Cool Vendor in AI Engineering. We believe this recognition validates our innovative AI approach and work empowering enterprise AI adoption. Get the report: hubs.li/Q02YfTv50

We're thrilled to be featured in TechCrunch - x.com/TechCrunch -! Discover how our open-source inference optimization framework is making AI more accessible and sustainable. Read more: techcrunch.com/2025/03/20/pru…

Haystack has 20k⭐️ on Github!! 🎉 I remember us celebrating 7k stars at deepset, makers of Haystack , what a journey!

Harrison Chase interesting analysis Harrison Chase - though you've forgotten your friends at Haystack 😉 We seem to share the view that blending "AI workflows" with "agentic" capabilities gives best results right now, and we extended Haystack with many carefully chosen agentic capabilities over

Who's interested in this panel :-) ?

Is OCR quality the silent killer of your RAG performance? 🧵👇 Our deep dive into 8500+ enterprise documents reveals how OCR errors create a "hidden ceiling" for RAG, and how multimodal approaches offer a path forward.

Today, we’re opening up access to the beta version of Mixedbread Search. Mixedbread Search is the first system that lets you experience search over your own documents the way it should be: fast, accurate, multilingual, and truly multimodal. Available immediately.