deepset

💭 AI applications can get complex. In our latest article with NVIDIA AI, we show how you can visually curate these complex AI applications, making them easier to reason about and iterate over them quickly. In this article, discover how to use deepset Studio – our free AI prototyping platform for Haystack – and NVIDIA NIM together to:  · Design common AI pipelines with Haystack like RAG with full control over each step such as embedding retrieval, LLM, prompt and more.  · Export them as Python code or YAML to run or deploy them yourself. · Do all this while still having the option to use self-hosted models such as NIM that you can deploy yourself. 📚 Read the full article here: https://lnkd.in/g8fAp5Yh ✅ Sign up for deepset Studio here: https://lnkd.in/gy6UJzwW Tuana Çelik Anshul Jindal Meriem Bendris

📣 deepset Studio GA : Build AI Applications Faster with Haystack 📣 We're thrilled to announce the general availability of deepset Studio - our comprehensive toolkit that helps AI engineers build and test custom AI applications with ease. Thanks to feedback from our early beta users, what started as a visual pipeline designer for Haystack has evolved into a complete prototyping and development environment. Now, you can: • Jump start development with a library of common use case templates • Build and edit AI pipelines with drag-and-drop simplicity • Upload your data or use our sample data sets to get started • Access Haystack's full component library or customize your own • Deploy prototypes instantly to collect feedback • Test and debug in an interactive playground • Export to YAML or Python code • Use our native integration with NVIDIA AI NIM and the NVIDIA API catalog 🛠️ Ready to start building? Sign up for free: https://lnkd.in/esbgqPEu 🧩 Want to learn more? Read more about deepset Studio on our blog: https://lnkd.in/dFc-BfDm 💬 Got questions or feedback? Join our Haystack Discord community: https://lnkd.in/eNE9cgpU #AIEngineering #AIApplications #AIOrchestration #Haystack #LLM #MLOps

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 a complimentary copy of the report to see why: https://lnkd.in/gfJMAaZ6 Read more on the blog: https://lnkd.in/gbwzv63S Check out the press release: https://lnkd.in/gGA9AsKz #AI #GenAI #LLMs #RAG #haystack #deepset #Cool

📅 Just a few days to go for our upcoming webinar. [Sign up Link Below] Join deepset's VP Product - Mathis Lucka and CredX CEO, Ralf Krauther on 19th November as they share their strategy for successfully implementing Intelligent Document Processing (IDP) with GenAI in financial services and real estate transactions. You'll learn about: - A practical framework for Intelligent Document Processing of complex and unstructured documents - Moving from prototype to production rapidly - How to engage specialist knowledge workers to develop and team up with virtual deputy analysts‘ https://hubs.li/Q02WZ__70 #aiinfinance #webinar #intelligentdocumentprocessing #llms

Join us for a deep dive into #IntelligentDocumentProcessing in financial services! 🚀 Learn how to implement GenAI-powered IDP, from prototype to production, with insights from deepset VP of Product, Mathis Lucka and credX CEO, Dr. Ralf Kauther. Register today: https://hubs.li/Q02W_2f90

(Part V of our series “Only Custom RAG Is Production-Ready RAG”) ❗ Improve trust in your system by adding verifiable, model-generated references to the LLM’s output ❗ 📝You can use a specialized model to include references to the source documents in an LLM’s answer. 🔀 This model takes the answer generated by the LLM and the previously retrieved documents. 🧠It then predicts for each sentence which documents, if any, it is based on. 🧩Again, modularity reigns supreme. This post concludes our series about the most common custom AI setups. Read this article to understand why customization is the road towards building mission-critical products with generative AI: https://lnkd.in/eJMvxpTc

Don't miss deepset's Bilge Yücel and Jay Wilder as they share the spine-tingling tale of "The Fallback Mechanism: Haunting Errors in RAG" at this Thursday's chilling GenAI NIGHTMARES virtual event with OPEA.

Last Chance Webinar! Customized RAG Solutions - Register today 👉🏽 https://hubs.li/Q02W54tn0 Many AI initiatives struggle to get off the ground, taking on average 8 months to move from prototype to deployment. That’s where the partnership between appliedAI Initiative GmbH and deepset steps in. Together, we’re solving the challenges of GenAI for businesses across Europe by driving reliable, Trustworthy RAG solutions that accelerate AI’s impact. Join our joint webinar to learn more: ✅ Real-world approaches to solving AI challenges with Trustworthy RAG ✅ Best practices for implementing AI with transparency and explainability ✅ Lessons from high-stakes industries like electronics and telecom 🚀 Title: Customized RAG Solutions: Rohde & Schwarz’s Success in Knowledge Management for Manufacturing and Telecom 🎙️Speakers: Dr. Christian Geishauser (appliedAI Initiative GmbH), Laura Luckert (deepset) and Andrew Schaefer (Rohde & Schwarz) as they share firsthand insights and actionable strategies from their work with Rohde & Schwarz. 🗓️ Date: 29th of October 2024 ⌚️Time: 4:30pm (1 hour) 📍Place: https://hubs.li/Q02W54tn0 AI’s true value lies in optimizing processes and driving business growth. This event is your chance to learn how Trustworthy RAG can tackle your AI challenges. #Trustworthy #RAG

🚀 (Part IV of our series “Only Custom RAG Is Production-Ready RAG”) Re-ranking makes RAG cheaper, faster, and more accurate Full article 👉 https://lnkd.in/eJMvxpTc 🥇A ranker component helps narrow down the documents we send to the LLM by more accurately ranking the retrieved documents by relevance. 🥈Rankers can use more powerful models than retrievers — or they can use metadata. 🥉In a typical setup, the retriever sends 40-60 documents to the ranker, which re-ranks them and then sends only the top 20 to the LLM. 🏆This saves cost, cuts latency, and reduces noise in the data received by the LLM, improving its performance. Stay tuned for our next post on the most common custom RAG setups! #rag #AI #llm #aiinproduction

Join us for an upcoming webinar based on our latest customer case study! Customized RAG Solutions: Success in Knowledge Management for Manufacturing and Telecom - https://hubs.li/Q02Vq_g80 In collaboration with appliedAI Initiative GmbH, we implemented Retrieval-Augmented Generation (RAG) at Rohde & Schwarz, a leader in electronic products and solutions. Our approach, featuring a robust vision pipeline and retrieval fine-tuning, improved answer accuracy by 46%! The result is a new enhanced, functional prototype that solves challenges such as multilingual data and complex tabular structures and is based on scalable technology for further implementation. This webinar will outline the case study, share learnings, and leave time for questions. 🚀 Title: Customized RAG Solutions: Rohde & Schwarz’s Success in Knowledge Management for Manufacturing and Telecom 🎙️Speakers: Dr. Christian Geishauser at appliedAI, Laura Luckert at deepset, and Andrew Schaefer at Rohde & Schwarz 🗓️ Date: October 29, 2024 ⌚️Time: 4:30pm CET 📍Place: Save your spot here: https://hubs.li/Q02Vq_g80 #GenAI #TrustworthyRAG #RetrievalAugmentedGeneration #customAI