Julian Risch

interesting analysis @hwchase17 - 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 the last year. As the thread here indicates, there are plenty of directions agent frameworks can focus and evolve – how about we get together with @jerryjliu0 @samuelcolvin @MarcKlingen on a live panel to discuss? Would for sure be a panel with many hot takes and those are typically the most interesting ones 😅

Congrats to the winners of @tech_berlin hackathon! Thanks a lot to the participants, the jury and all the sponsors making it possible. Winners: 1. Wingly - Boardy for Dating 2. TradeMind - Dynamic Pricing for Minecraft 3. Healthlink - Streamlining Lab result communication

OMG! full house in @CodeUniversity at the @tech_berlin Hackathon ❤️ We got 100+ hackers building with @weaviate_io @deepset_ai @MistralAI and LMNT 🤯 Luckily, we assembled an unstoppable team with: @Julian_Risch , @nickcarmont , @blwiertz , @JoannaGraiver , Jacob, and me 🫡 Excited to see what everyone is building!

✨ Turn your ideas into reality at the @tech_berlin AI Hackathon this weekend! 👥 Team up with amazing builders 🛠️ Build with cutting-edge tools like @MistralAI, @lmnt_com, @weaviate_io and Haystack 🏆 Showcase your demo to the jury Register now 👇lu.ma/bkevcvsk

🎄 Advent of Haystack continues with Day 3! ☃️ Santa needs a RAG assistant connected to BBC News to learn about the world! 🌍 For this challenge, help Elf David build custom components for multi-query retrieval to boost recall 🎅 Challenge details👇 #challenge" target="_blank" rel="nofollow noopener">haystack.deepset.ai/advent-of-hays…

✨ Advent of Haystack: Day 2 is Here! 🎄 Help the Elves Find What They've Lost 🕵️ Step into the universe of "A Very Weaviate Christmas" and use Haystack + @weaviate_io to solve the mystery: Who is the culprit? More details and hints 👇 #challenge" target="_blank" rel="nofollow noopener">haystack.deepset.ai/advent-of-hays…

Join us for an evening of NLP, LLMs, and retrieval at our meetup, live from @deepset_ai HQ in Berlin or online! 🎙️ Talks: 1️⃣ NLP-as: an NLP analytics system that helps you develop insights into the limitations of your NLP engine by @orenmatar Discover a model-agnostic system to analyze NLP engine weaknesses with robust, LLM-generated test datasets. 2️⃣ Retrieving with Haystack by @DavidSBatista Explore retrieval techniques, from classic IR methods to modern LLM-powered solutions, and learn how to apply them with Haystack. 🍕 Networking & live Q&A included! Register for the in-person event 👉 lu.ma/n7arvjng 🌐 Join us online on Zoom lu.ma/k4payims

🚀 Introducing deepset Studio! 🎉 Say hello to the visual way to build, test, and deploy Haystack pipelines, from simple tasks to complex AI workflows. Here’s what you can do with Studio: 🛠️ Drag & drop components to create pipelines 🚀 Deploy pipelines for FREE on deepset Cloud 📑 Bring your own files or connect other databases 🫂 Collaborate with teammates in your workspace 🧪 Test pipelines in the Playground and share prototypes 💻  Export pipelines as YAML/Python for local use Studio is free and open to everyone - perfect for building RAG and other AI workflows 💡 Read all about it and sign up today 👉 haystack.deepset.ai/blog/announcin…

When it comes to text classification, there are a few ways you can use classification models: 1️⃣ You can use a zero shot model, provide your own labels, and ask the model to classify (label) text based on these labels you defined. 2️⃣ You can get a model trained to classify for predefined labels. For example: classifying text as 'query' or 'statement'. In this new tutorial, you can learn how you can use both text classification techniques in your Haystack AI pipelines, to understand incoming user queries better, as well as to classify text based on topic 👇 haystack.deepset.ai/tutorials/41_q…

Come visit the @Haystack_AI team at booth 225 at @AIconference today! 🎉 We’ve got exciting demos and awesome swag waiting for you! We're right by the coffee bar—grab a coffee and let's chat! ☕️

A huge shoutout to our winners at the Useless Fun AI Build-A-Thon! 🏆🌟 The projects were beyond fun and creative. Special thanks to our amazing judges for their thoughtful insights and for helping select the best of the best 🙌 Congratulations to everyone, and thank you for making this event so amazing! 🚀

Today’s the day! 🎉 Kicking off Useless Fun AI Build-A-Thon with @Cloudflare and @AssemblyAI. Can't wait to see what amazing projects and ideas come out of it 👀

🚀 Thrilled to share that our open source team at deepset has launched a new course with DeepLearning.AI! Learn from @tuanacelik and @AndrewYNg about Building AI Applications with Haystack! Ready to dive in? 🤿 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_ai, and taught by @tuanacelik, who is the developer relations lead for Haystack at deepset. Generative AI technology is changing rapidly and it can be challenging to integrate APIs from different LLMs, vector databases, and various tools such as web search. In this course, you will learn how to use the Haystack framework to make your development process more modular, allowing you to manage complexity and focus more on building your application. In detail, you’ll: - Build a RAG pipeline using Haystack’s main building blocks – components, pipelines, and document stores. - Create custom components in your pipeline by building a Hacker News summarizer that extends your app’s ability to access APIs. - Use conditional routing to create a branching pipeline with a fallback to web search mechanism when the LLM does not have the necessary context to respond to the user's query. - Build a self-reflecting agent for named entity recognition that loops using an output validator custom component. - Create a chat agent using OpenAI's function-calling capabilities which allow you to provide Haystack pipelines as tools to the LLM, enhancing that agent's capabilities. By the end of this course, you will learn a high-level orchestration framework that can help make your applications flexible, extendible, and maintainable, even as the technology stack changes, new user needs arise, and you add new features to your application. Please sign up here: deeplearning.ai/short-courses/…

🌟 Haystack has officially crossed 15.000 stars on GitHub! 🌟 🫶 We're beyond excited to see so many of you joining the journey of building cutting-edge AI applications. This milestone isn't just a number—it's a symbol of the incredible community that's been growing around Haystack 🧩 60+ integrations including @AIatMeta @ollama @langfuse @nvidia 📚 Numerous tutorials, cookbooks, articles 💙 250+ contributors 👾 Over 3.2k members on discord …and more!

🚀 New open-source German/English embedding model by deepset and @mixedbreadai 🚀 ​ Most models today are still geared towards English speaking markets. Today, with Mixedbread, we are jointly announcing our latest contribution towards changing that landscape: A new open-source German/English embedding model deepset-mxbai-embed-de-large-v1 ​ ✅ Supports binary quantization ✅ Supports MRL ​ Learn more: haystack.deepset.ai/blog/announcin…

Last day of @PyConDE today and @bilgeycl is presenting fallback mechanisms for LLM apps using @Haystack_AI in 30min in room A1! 🎉 #PyConDe

@Haystack_AI is at @PyConDE! At 12:15 in Room B09 @SilvanoCerza will explain why we decided to rewrite Haystack, show the new features 2.0 provides, and give a peek into our future roadmap. #PyConDE #PyDataBerlin

Calling the Berlin GenAI community, join us along with @neo4j @qdrant_engine and mixedbread.ai for a meetup on April 25th 🚀 We have 4 great speakers. Our very own @bilgeycl will be joined by: · @atitaarora from Qdrant: RAG Evaluation in Action: Building, Tackling Cold Start Challenges, and Optimizing Your RAG with Qdrant and RAGAS · @mesirii from neo4j: Superpower your GenAI-Applications with GraphRAG using Haystack and Neo4j · @aaxsh18 from mixedbread.ai Register here 👉 lu.ma/berlin-genai-m…

🚀 What an amazing day we had yesterday at our workshop in Berlin! A huge thank you to our amazing friends at @deepset_ai for co-organizing this incredible event with us. And a special shout-out to @Julian_Risch and @LukawskiKacper for a great job breaking down @qdrant_engine and @Haystack_AI, making it all click. To all who joined us, thank you so much! We can't wait to see what awesome things you will do next with what we learned.