talk-data.com

Join us together with Zilliz for an exciting meetup where we dive into the power of graphs and vectors for Generative AI! Come on a journey through the world of knowledge graphs in GenAI, revealing their pivotal role in AI models, vector indexes, and knowledge representation. Learn how to build a GraphRAG Agent using Neo4j and Milvus, combining graph databases and vector search for intelligent, accurate query responses!

Whether you're new or experienced, this meetup will expand your understanding of how graphs shape AI innovation.

Session 1: Building a GraphRAG Agent With Neo4j and Milvus - Stephen Batifol\, Developer Advocate at Zilliz

In this talk we will show how to build a GraphRAG Agent with Neo4j and Milvus. We will show how an agent can combine the power of graph databases and vector search to provide accurate and relevant answers to user queries. We will also show how an Agent can use routing, fallback mechanisms, and self-correction.We will use LangGraph, Llama 3.1 8B with Ollama and GPT-4o. Of course, there will be a live demo of how everything works together.

Stephen previously worked as a Machine Learning Engineer at Wolt, where he created and worked on the ML Platform, and previously as a Data Scientist at Brevo. Stephen studied Computer Science and Artificial Intelligence. He is a founding member of the MLOps.community Berlin group, where he organizes Meetups and hackathons. He enjoys boxing and surfing.

Session 2: A Field Guide to Knowledge Graphs used in GenAI - Andreas Kolleger, Lead for GenAI Innovation at Neo4j

Join us for an exhilarating journey into the world of Knowledge Graphs within Generative AI! Graphs are the hidden backbone of GenAI applications, surfacing everywhere from the AI models themselves to intricate vector indexes and, of course, as fundamental tools for knowledge representation. We will uncover graphs' pervasive presence, delve into their diverse forms, and reveal how they weave together to form a vast, interconnected "graph of graphs." Whether you're a seasoned professional or just beginning your adventure in GenAI, this session promises to deepen your understanding and spark new insights into the critical role of knowledge graphs.

Andreas is a technological humanist. Starting at NASA, he designed systems from scratch to support science missions. Then in Zambia, he built medical informatics systems that complement technology with social good. Now with Neo4j, he is democratizing graph databases which elevate understanding by emphasizing relationships.

Welcome to the PyData Berlin August meetup!

Please provide your first and last name, current role and organization name for the registration because this is required for the venue's entry policy. If you cannot attend, please cancel your spot so others are able to join as the space is limited.

Host: Google Cloud is excited to welcome you for this month's version of PyData.

Agenda:

• 6pm - 7pm: Arrival, networking and food & drinks (BBQ)
• 7pm - 9pm: Talks (and lightning talks)
• 9pm - 10pm: Drinks and networking

**************************************************************************

The Lineup for the evening

Talk 1: Multi-agent Systems with Mistral AI, Milvus and Llama-agents Abstract: Agentic systems are on the rise, helping developers create intelligent, autonomous systems. LLMs are becoming more and more capable of following diverse sets of instructions, making them ideal for managing these agents. This advancement opens up numerous possibilities for handling complex tasks with minimal human intervention in so many areas. In this talk, we will see how to build agents using llama-agents. We’ll also explore how combining different LLMs can enable various actions. For simpler tasks, we'll use Mistral Nemo, a smaller and more cost-effective model, and Mistral Large for orchestrating different agents. Speaker: Stephen Batifol Stephen is a Developer Advocate at Zilliz. He previously worked as a Machine Learning Engineer at Wolt, where he created and worked on the ML Platform, and previously as a Data Scientist at Brevo. Stephen studied Computer Science and Artificial Intelligence. He is a founding member of the MLOps.community Berlin group, where he organizes Meetups and hackathons. He enjoys boxing and surfing.

Talk 2: Bayes by Hand Abstract: Discover how powerful Bayesian modelling can be with a pen and paper, or even in your head! Or - Bayes, the good bits! The focus is on Bayes as a thinking tool, rather than on code and algorithms. Think eliciting and updating priors, updating estimates rigorously with incoming data, etc. This approach reacts to the need for more disciplined estimation in business contexts, while wanting to include non-stats and non-dev stakeholders in the process.

Bayes By Hand can be used for sketching out baselines, cross-disciplinary collaborations, improved decision making, and more. Let's get back to the blackboard my friends, and do some modelling by hand! Speaker: Laura Summers Laura is a very technical designer™️. She's the founder of Debias AI, (debias.ai) and the human behind Sweet Summer Child Score (summerchild.dev), Ethics Litmus Tests (ethical-litmus.site), fairXiv (fairxiv.org), the Melbourne Fair ML reading group (groups.io/g/fair-ml). Laura is passionate about feminism, digital rights and designing for privacy. She speaks, writes and runs workshops at the intersection of design and technology.

Lightning talks There will be slots for 2-3 Lightning Talks (3-5 Minutes for each). Kindly let us know if you would like to present something at the start of the meetup :)

*** NumFOCUS Code of Conduct THE SHORT VERSION Be kind to others. Do not insult or put down others. Behave professionally. Remember that harassment and sexist, racist, or exclusionary jokes are not appropriate for NumFOCUS. All communication should be appropriate for a professional audience including people of many different backgrounds. Sexual language and imagery are not appropriate. NumFOCUS is dedicated to providing a harassment-free community for everyone, regardless of gender, sexual orientation, gender identity, and expression, disability, physical appearance, body size, race, or religion. We do not tolerate harassment of community members in any form. Thank you for helping make this a welcoming, friendly community for all. If you haven't yet, please read the detailed version here: https://numfocus.org/code-of-conduct ***

** Important RSVP here. (Due to room capacity and building security, it's required to pre-register at the link for admission).

Welcome to the monthly in-person AI meetup in Berlin, in collaboration with Thoughtworks. Join us for deep dive tech talks on AI, GenAI, LLMs and machine learning, networking with speakers and fellow developers.

Agenda: * 6:00pm\~7:00pm: Checkin and networking * 7:00pm\~9:00pm: Tech talks and Q&A * 9:00pm: Open discussion and Mixer

Tech Talk: AI solution design in an LLM world Speaker: Mirza Rahim Baig (Zalando) Abstract: Are you using LLMs where a simple string match would work? Using multiple agents unnecessarily? Or are you using 4x the tokens you actually need. Identify all the decisions we need to make in designing a solution and learn how to make those decisions. Get some pro-tips in designing LLM based solutions. We start with a poorly created solution and the audience interactively and successively improves the solution.

Tech Talk: Beyond Vanilla RAG - Advanced RAG Strategies Speaker: Stephen Batifol (Zilliz) Abstract: In this talk, we'll explore how we can have Advanced RAG, the key components and innovative strategies. We'll cover how we can divide & conquer complex problems, and how query enhancement can help with query precision. We'll also look at different how we can use different retrievers. We'll touch on Routing, Memory, Planning to create Agentic Strategies.

Speakers/Topics: Stay tuned as we are updating speakers and schedules. If you have a keen interest in speaking to our community, we invite you to submit topics for consideration: Submit Topics

Sponsors: We are actively seeking sponsors to support AI developers community. Whether it is by offering venue spaces, providing food, or cash sponsorship. Sponsors will not only speak at the meetups, receive prominent recognition, but also gain exposure to our extensive membership base of 8,000+ AI developers in Berlin or 350K+ worldwide.

Community on Slack/Discord - Event chat: chat and connect with speakers and attendees - Sharing blogs\, events\, job openings\, projects collaborations

• Join Slack/Discord (link is at the bottom of the page)

*

This Meetup is presented by our friends from AI Camp Berlin. For more information and to help us keep track, please register via the event page of AICamp here ----------------------------- Join us for deep dive tech talks on AI, GenAI, LLMs and machine learning, food/drink, networking with speakers and fellow developers.

On the Agenda: 6:00pm\~7:00pm: Checkin, Food/drink and Networking 7:00pm\~9:00pm: Tech talks and Q&A 9:00pm: Open discussion and Mixer

About the evening

AI solution design in an LLM world by Mirza Rahim Baig

Are you using LLMs where a simple string match would work? Using multiple agents unnecessarily? Or are you using 4x the tokens you actually need. Identify all the decisions we need to make in designing a solution and learn how to make those decisions. Get some pro-tips in designing LLM based solutions. We start with a poorly created solution and the audience interactively and successively improves the solution. https://www.linkedin.com/in/rahim-baig/

Beyond Vanilla RAG - Advanced RAG Strategies by Stephen Batifol from Zilliz

In this talk, we'll explore how we can have Advanced RAG, the key components and innovative strategies. We'll cover how we can divide & conquer complex problems, and how query enhancement can help with query precision. We'll also look at different how we can use different retrievers. We'll touch on Routing, Memory, Planning to create Agentic Strategies. https://www.linkedin.com/in/stephen-batifol/

------

AICamp Community on Slack/Discord - Event chat: chat and connect with speakers and attendees - Sharing blogs\, events\, job openings\, projects collaborations Join Slack (search and join the #berlin channel) \| Join Discord

------ Code of Conduct We adhere to the Berlin Code of Conduct to ensure a welcoming and respectful environment for all participants. The event space operates under largely compatible Thoughtworks Meetups & Events CoC.

Accessibility The Location is accessible for wheelchair users. This includes the entrance (no steps to get into the location), toilets and the stage.

** RSVP here (Due to room capacity and venue security, it is required to pre-register at the link for admission)

Welcome to the monthly AI meetup in Berlin. Join us for deep dive tech talks on AI, GenAI, LLMs and machine learning, networking with speakers and fellow developers.

Agenda: * 6:00pm\~7:00pm: Checkin and networking * 7:00pm\~9:00pm: Tech talks and Q&A * 9:00pm: Open discussion and Mixer

Tech Talk: Building Your First RAG locally with Llama 3 and Milvus Speaker: Stephen Batifol (Zilliz) Abstract: With the rise of Open-Source LLMs like Llama, Mistral, Gemma, and more, it has become apparent that LLMs might also be useful even when run locally. In this talk, we will see how to deploy a Retrieval Augmented Generation (RAG) setup using Llama 3, with Milvus as the vector database on your laptop. That way, you can also avoid being Rate Limited by OpenAI like I have been in the past.

Tech Talk: Lowering comprehension barriers with LLMs Speaker: Anton Burnashev (dltHub) Abstract: Trying to sift through endless documentation can be tedious for our users - what if they could just ask GPT instead? In this talk we will show you how we built a RAG chatbot for our docs using dlt, ChromaDB and OpenAI. We'll also share how we used this to get to know our user base better and how we might improve our docs.

Speakers/Topics: Stay tuned as we are updating speakers and schedules. If you have a keen interest in speaking to our community, we invite you to submit topics for consideration: Submit Topics

Sponsors: We are actively seeking sponsors to support AI developers community. Whether it is by offering venue spaces, providing food, or cash sponsorship. Sponsors will not only speak at the meetups, receive prominent recognition, but also gain exposure to our extensive membership base of 8,000+ AI developers in Berlin or 350K+ worldwide.

Community on Slack/Discord

• Event chat: chat and connect with speakers and attendees
• Sharing blogs, events, job openings, projects collaborations *

** Important RSVP here. (Due to room capacity and building security, it's required to pre-register at the link for admission).

Welcome to the monthly in-person AI meetup in Berlin, in collaboration with Thoughtworks. Join us for deep dive tech talks on AI, GenAI, LLMs and machine learning, networking with speakers and fellow developers.

Agenda: * 6:00pm\~7:00pm: Checkin and networking * 7:00pm\~9:00pm: Tech talks and Q&A * 9:00pm: Open discussion and Mixer

Tech Talk: Building an LLM agent to chat with the Berlin Parliament Speaker: Stephen Batifol (Zilliz) Abstract: Lot of things are happening in the Berlin Parliament and you might not be aware of it. By using LLMs and a Vector DB, I'll show you how you can chat and interact with the data of the Berlin Parliament.

Tech Talk: Improving the Usefulness of LLMs with RAG Speaker: Kristian Aune (Vespa) Abstract: LLMs like GPT can give useful answers to many questions, but there are also well-known issues with their output: The responses may be outdated, inaccurate, or outright hallucinations. And they don’t know anything about you or your organization private data (we hope). RAG can help reduce the problems with “hallucinated” answers, and make the responses more up-to-date, accurate, and personalized - by injecting related knowledge, including non-public data. In this talk, we’ll go through what RAG means, demo some ways you can implement it - and warn of some traps you still have to watch out for.

Tech Talk: Boosting Automation - An AI Engineer’s Open Source Toolbox Speaker: Thomas Kranzkowski (CLOUDETEER) Abstract: TBD

Speakers/Topics: Stay tuned as we are updating speakers and schedules. If you have a keen interest in speaking to our community, we invite you to submit topics for consideration: Submit Topics

Sponsors: We are actively seeking sponsors to support AI developers community. Whether it is by offering venue spaces, providing food, or cash sponsorship. Sponsors will not only speak at the meetups, receive prominent recognition, but also gain exposure to our extensive membership base of 8,000+ AI developers in Berlin or 350K+ worldwide.

Community on Slack/Discord - Event chat: chat and connect with speakers and attendees - Sharing blogs\, events\, job openings\, projects collaborations

• Join Slack/Discord (link is at the bottom of the page) *

This Meetup is presented by our friends from AI Camp Berlin. For more information and to help us keep track, please register via the event page of AICamp here: Link

Welcome to the monthly in-person AI meetup in Berlin! Join us for deep dive tech talks on AI, GenAI, LLMs and machine learning, food/drink, networking with speakers and fellow developers.

On the Agenda: 6:00pm\~7:00pm: Checkin, Food/drink and Networking 7:00pm\~9:00pm: Tech talks and Q&A 9:00pm: Open discussion and Mixer

About the evening

Building an LLM agent to chat with the Berlin Parliament by Stephen Batifol (Zilliz) Lot of things are happening in the Berlin Parliament and you might not be aware of it. By using LLMs and a Vector DB, I'll show you how you can chat and interact with the data of the Berlin Parliament.

Improving the Usefulness of LLMs with RAG by Kristian Aune (Vespa) LLMs like GPT can give useful answers to many questions, but there are also well-known issues with their output: The responses may be outdated, inaccurate, or outright hallucinations. And they don’t know anything about you or your organization private data (we hope). RAG can help reduce the problems with “hallucinated” answers, and make the responses more up-to-date, accurate, and personalized - by injecting related knowledge, including non-public data. In this talk, we’ll go through what RAG means, demo some ways you can implement it - and warn of some traps you still have to watch out for.

Boosting Automation - An AI Engineer’s Open Source Toolbox by Thomas Kranzkowski (CLOUDETEER) The world of data technologies and AI is moving faster and faster, which means that the profile of an AI engineer is constantly changing. Find out which open-source tools and skills you need to keep up with the times in this talk.

------ Important note: To keep the overview we close the registration on this page - please register via the AI Camp page here: Link

------ Speakers/Topics: Stay tuned as we are updating speakers and schedules. If you have a keen interest in speaking to our community, we invite you to submit topics for consideration: Submit Topics

AICamp Community on Slack/Discord - Event chat: chat and connect with speakers and attendees - Sharing blogs\, events\, job openings\, projects collaborations Join Slack (search and join the #berlin channel) \| Join Discord

------ Code of Conduct We adhere to the Berlin Code of Conduct to ensure a welcoming and respectful environment for all participants. The event space operates under largely compatible Thoughtworks Meetups & Events CoC.

Accessibility The Location is accessible for wheelchair users. This includes the entrance (no steps to get into the location), toilets and the stage.