Welcome and hello to our amazing end of the year special!

It’s time to close out the Year and celebrate - together with friends!

For this occasion Weaviate is teaming up with AICamp and ML6

So we invite everyone who is interested in learning more about building data and AI applications as well as search and open-source vector databases in general.

Join AI developers, ML engineers, Data scientists and practitioners to celebrate all your hard work this year.

Here is what you can expect:
* Tech Talks: Immerse yourself in enlightening tech talks, exploring the latest advancements and trends in the dynamic field of AI, GenAI, LLMs.
* Networking / Happy Hour Mixer: Unwind and celebrate the successes of the year in a relaxed happy hour setting. Enjoy drinks, nibbles, and continue networking in a festive atmosphere.
* Holiday Gifts: 'Tis the season of giving! Enjoy the festive spirit with surprises and holiday gifts to add an extra dash of joy to your AI journey.

Agenda:
* 6.00PM - Open Doors
* 6.15 PM - Welcome and Networking
* 6:30 PM - Tech Talks and Q&A
* 8:00 PM - More food, networking & celebration

Tech Talk: Bring your AI application from Prototype to Production
Speaker: Philip Vollet, Edward Schmuhl, Victoria Slocum @Weaviate
Abstract: In today's evolving AI landscape, bringing your concept from a prototype to a real and production-ready application is a challenge many face. In this meetup, we will give you insights on how to build ai-native applications with the power of Large Language Models (LLMs) at scale. Based on a real-life example we will cover:
- Core concepts and aspects of (long context) Retrieval Augmented Generation
- The role of vector databases in RAG
- Easy integration with leading players in the AI open-source ecosystem
- Choosing various deployment methods
- What to keep in mind for production-ready applications (e.g scalability, multi-tenancy and more)

Tech Talk: Speeding up RAG evaluation with Fondant
Speaker: Robbe Sneyders, Principal Engineer @ML6
Abstract: Tuning your RAG system to get optimal performance takes time. You need to define evaluation metrics, load your data, run the evaluation, and somehow tune your parameters (chunk size, embedding model, ...) based on the outcome. In this talk, We will code a live demo showing how you can speed up this evaluation step with Fondant using the RAG tools you already know: Weaviate, LlamaIndex, LangChain, and Ragas.

Tech Talk: Decoupling code changes from Generative AI test and release cycles
Speaker: Sohrab Hosseini @Orquesta
Abstract: How can product teams starting with Generative AI set themselves up for success? We will explore how teams can focus on their specific use cases while improving collaboration, observability and innovation speed. We explore how decoupling Generative AI updates from code changes can enable this.

Venue:
B.1 Johan Huizingalaan 763a 1066 VH Amsterdam

Slack Community
For events chat, speakers office hours , learning resources, and projects collaboration & networking. Join Slack