Building Production-ready GenAI Apps with RAG (Weaviate/deepset/Unstructured)

Join us for a fun evening with snacks, drinks, and lots of knowledge to unlock the true potential of AI! Integrate your vast internal knowledge base, build production-ready RAG (Retrieval Augmented Generation) pipelines, and guide your model to produce accurate results.

• Ever felt like your LLM daydreams its own alternative facts?
• Ever hit a knowledge wall because your AI's memory just isn't expansive enough or its wisdom doesn't stretch far enough?
• Tired of digging deep into your pockets just to keep that model finely tuned?

Talks:

Customizing LLM Applications with Haystack
Every LLM application comes with a unique set of requirements, use cases and restrictions. Let's see how we can make use of open-source tools and frameworks to design around our custom needs.

Build bulletproof generative AI applications with Weaviate and LLMs
Building AI applications for production is challenging. Your users don't like to wait. If you deliver the right results in milliseconds instead of seconds, you can win them over. Production-grade pipelines also need to prevent the LLM from making up false facts. We'll show you how to solve this with live demos and ready-to-fork open-source GitHub projects using Weaviate, your most beloved open-source vector database.

Speakers:

Philip Vollet
Head of Developer Growth at weaviate.io

Tuana Çelik
Lead Developer Advocate at deepset.ai

Ronny Hoesada
DevRel Engineer at unstructured.io