If you have NLP pipelines running in production, you likely need to maintain them. If you need to detect the sources of problems, having a good way to see each step of execution, and even more, identifying the pipeline with issues (when you have more than one running) is quite important. ✨ Queue the tracing support we introduced in @Haystack_AI 2.0 ✨ Out of the box, Haystack supports @opentelemetry and @datadoghq But we've also added a uniform Tracer interface that allows you to extend Haystack to support other platforms too 🙌 See how to connect your own tracers here 👉 docs.haystack.deepset.ai/doc… We've also included instructions on how you can set up a lightweight local tracing backend with a visualizer using @JaegerTracing in our guide too 🚀

Wir haben keinen einzigen #COVID19 Patienten mehr auf der Intensivstation. Nur das im Herbst nicht alle wieder überrascht sind - ausreichend Pflegekräfte haben wir auch immer noch nicht.

Rasa 3.0 is here! 🎉 Join our livestream launch event to get all the details on what's new & improved (and what it means for you as a developer). And don't worry if you miss it: the recording will be available immediately at the same link. hubs.ly/H0_X_3b0

Drum roll, please! The Rasa Open Source 3.0 is finally out with a bunch of new features and improvements. Let’s meet next week for a series of live events where we will focus on all things Rasa Open Source 3.0! Detailed schedule: hubs.ly/H0_Mx2w0