Haystack 2.0: Composable, Transparent, and Robust AI Applications
Building an AI prototype is easy and quick these days. Building production-grade systems is a different story. How do you keep moving quickly and run robustly?
In this talk, we introduce you to Haystack 2.0 and show how an orchestration framework can truly help you build production-ready AI systems.
We explain key concepts and share our learnings from working with thousands of open source users over the last 4 years.
We touch on compound AI systems, the need for customizability, simple abstractions – and agentic RAG. We wrap up with an outlook into the future and what this means for us developers.
Malte Pietsch
Co-Founder at Deepset
Malte Pietsch is a Co-Founder at deepset, where he crafts custom NLP solutions for diverse clients, such as Siemens, Airbus and Springer Nature. He holds a M.Sc. with honors from TU Munich and conducted research at Carnegie Mellon University. Before founding deepset he worked as a data scientist for multiple startups. He is an active open-source contributor and creator of the NLP package FARM.
