talk-data.com
Activities & events
| Title & Speakers | Event |
|---|---|
|
Tailoring Foundation Models for Generative AI Applications
2024-09-19 · 21:30
Suman Debnath
– Principal AI/ML Advocate
@ Amazon Web Services
In this session, we will focus on fine-tuning, continuous pretraining, and retrieval-augmented generation (RAG) to customize foundation models using Amazon Bedrock. Attendees will explore and compare strategies such as prompt engineering, which reformulates tasks into natural language prompts, and fine-tuning, which involves updating the model's parameters based on new tasks and use cases. The session will also highlight the trade-offs between usability and resource requirements for each approach. Participants will gain insights into leveraging the full potential of large models and learn about future advancements aimed at enhancing their adaptability. |
|
|
Unstructured Data and Vector Databases
2024-09-19 · 21:30
In this session, I will discuss the unstructured data and the world of vector databases, we will see how they different from traditional databases. In which cases you need one and in which you probably don’t. I will also go over Similarity Search, where do you get vectors from and an example of a Vector Database Architecture. Wrapping up with an overview of Milvus. |
|
|
AI Meetup (September): AI, GenAI and LLMs
2024-09-19 · 21:30
** Important RSVP here (Due to room capacity and building security, you must pre-register at the link for admission.) Description: Welcome to our in-person AI meetup in New York. Join us for deep dive tech talks on AI, GenAI, LLMs and ML, hands-on workshops, food/drink, networking with speakers and fellow developers. Tech Talk: Unstructured Data and Vector Databases Speaker: Tim Spann (Zilliz) Abstract: In this session, I will discuss the unstructured data and the world of vector databases, we will see how they different from traditional databases. In which cases you need one and in which you probably don’t. I will also go over Similarity Search, where do you get vectors from and an example of a Vector Database Architecture. Wrapping up with an overview of Milvus. Tech Talk: Tailoring Foundation Models for Generative AI Applications Speaker: Suman Debnath (AWS) Abstract: In this session, we will focus on fine-tuning, continuous pretraining, and retrieval-augmented generation (RAG) to customize foundation models using Amazon Bedrock. Attendees will explore and compare strategies such as prompt engineering, which reformulates tasks into natural language prompts, and fine-tuning, which involves updating the model's parameters based on new tasks and use cases. The session will also highlight the trade-offs between usability and resource requirements for each approach. Participants will gain insights into leveraging the full potential of large models and learn about future advancements aimed at enhancing their adaptability. 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 our community. Whether it is by offering venue spaces, providing food/drink, or cash sponsor. Sponsors will not only speak at the meetups, receive prominent recognition, but also gain exposure to our extensive membership base of 20,000+ AI developers in New York or 400K+ worldwide. Community on Slack/Discord
|
AI Meetup (September): AI, GenAI and LLMs
|
|
AI Meetup (September): A deep-dive in the RAG
2024-09-19 · 16:00
** 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, in collaboration with Publicis Sapient. 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: RAG Architecture – Arguments for it, and some key considerations Speaker: Samuel Clampitt (Publicis Sapient) Abstract: In the context of LLMs, everyone is talking about it – but what is Retrieval-Augmented-Architecture (RAG), and why and when does it make sense to use it? The talk will attempt to answer these questions, as well as present a practical case study. The talk will also include some key implementation considerations to the constituent parts of a RAG-using system and close with an outlook. Tech Talk: Iterative RAG with LLM Tool Use: Enhancing AI's Capabilities Speaker: Joon-Pil Hwang (Weaviate) Abstract: Generative AI models now incorporate 'tool use' capabilities to interact with external functions, enhancing their power while maintaining important safeguards. In this talk, JP will explore the intersection of tool use with Retrieval-Augmented Generation (RAG) using Weaviate, a vector database. He'll share his experiences implementing this approach, discuss his key findings, and compare it to traditional RAG methods. Attendees will get first-hand impressions of his experience with this approach. 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 10,000+ AI developers in Berlin or 400K+ worldwide. Community on Slack/Discord
|
AI Meetup (September): A deep-dive in the RAG
|
|
AI Meetup (September): AI, GenAI and ML
2024-09-05 · 17:00
** Important RSVP HERE (Due to room capacity and venue security, it is required to pre-register at the link for admission) Welcome to the AI meetup in London. Join us for deep dive tech talks on AI, GenAI, LLMs and machine learning, food/drink, networking with speakers and fellow developers. Tech Talk: Iterative RAG with LLM Tool Use: Enhancing AI's Capabilities Speaker: Joon-Pil Hwang (Weaviate) Abstract: Generative AI models now incorporate 'tool use' capabilities to interact with external functions, enhancing their power while maintaining important safeguards. In this talk, JP will explore the intersection of tool use with Retrieval-Augmented Generation (RAG) using Weaviate, a vector database. He'll share his experiences implementing this approach, discuss his key findings, and compare it to traditional RAG methods. Attendees will get first-hand impressions of his experience with this approach. Tech Talk: Building Agentic Workflows for Engineers Speaker: Shekhar Patnaik (GitLab) Abstract: In this talk, I will cover a product that we've been working on called Duo Workflows. It helps to automate a number of code and development tasks helping make developers more productive. It uses AI Agents and workflows written in LangGraph and is open source. 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 10,000+ AI developers in London or 400K+ worldwide. Community on Slack/Discord
|
AI Meetup (September): AI, GenAI and ML
|
|
GenAI Berlin August Meetup
2023-08-08 · 17:00
This event is brought to you in collaboration with the Berlin Practical GenAI Meetup ========================================== Welcome to the GenAI Berlin end of Summer meetup, co-hosted by your friendly GDG Berlin organizers. If you'd like to give a talk at a future meetup of GenAI Berlin, please fill out this form: https://forms.gle/d52kaHGTCSj7Gjym6 We're looking for hosts! If your company is interested - please DM♥ AGENDA
Generative AI has come a long way in the past few months. We all have seen chatbots doing things we couldn't have dreamt of a few years back. Generative AI is today able to process text, images, code and even speech in ways that can help users be more efficient and creative. For Users, it can access a vast source of information to guide them at work and get more done faster. For Developers, it can explain code snippets, fix your code, help you navigate a new code base or even write tests! The possibilities are endless. In this talk, you are going to learn about Google's new Generative AI platform Vertex AI, the latest tools (Generative AI Studio) and APIs to foundational models (PaLM2, Imagen, Codey and Chirp), just so you can start building AI-enabled Applications and powerful chatbots. AI's current progress and future is truly exciting!
Have you ever seen futuristic films or TV series where humans speak or interact with business intelligence systems using natural language input or even hand gestures? It may have sounded like a dream until 2017 when Google released Cloud Speech-to-Text v1. This opened up a lot of possibilities for building augmented analytics in production. When I worked in consultancy, I built several commercial projects related to this. However, these systems were, to a large extent, rule-based. Recent advances in Large Language Models (LLMs) have opened up a new era of augmented analytics. We not only know how to convert speech to text, but we can now convert text to code on a contextual level, and it actually works! In this talk, I would like to elaborate more on the topic of augmented analytics, present a brief history of developments in this field's technical capabilities, share several projects I implemented in this area, and discuss how LLMs revolutionised this field
ABOUT OUR SPEAKERS Gerard Sans | twitter.com/gerardsans Gerard helps Developers succeed in Artificial Intelligence and Web3. Awarded Google Developer Expert for his community contributions at the GDE Summit 2023 celebrated in Berlin and the Community Connect Europe 2021. He loves running Web3 London, GraphQL London, GraphQL San Francisco, mentoring and giving back to the community. Paul Egorov | Lead Data Scientist at N26 I am a curious researcher and an enthusiastic leader with a diverse skill set and 9 years of experience in system analytics, entrepreneurship, advanced analytics and deep learning. I have completed more than 15 data science projects in banks / fintech / industry and have been building and managing performant, resilient and learning-oriented teams for 3 years. ABOUT THE GENAI BERLIN COMMUNITY We are a community of GenAI enthusiasts. Join the conference in September: heyai.dev And follow us on Twitter: twitter.com/heyai_dev Agenda Speakers Gerard Sans Gerard loves helping Developers to succeed using Web, Cloud, AI and Web3 technologies. He is very excited about the future of the Web and JavaScript. Always happy Computer Science Engineer and humble GDE. He loves to share his learnings by giving talks, training and writing about cool technologies. He loves running Web3 London, GraphQL London, GraphQL San Francisco, mentoring students and givi… Paul Egorov - N26 (Lead Data Scientist) I am a curious researcher and an enthusiastic leader with a diverse skill set and 9 years of experience in system analytics, entrepreneurship, advanced analytics and deep learning. I have completed more than 15 data science projects in banks / fintech / industry and have been building and managing performant, resilient and learning-oriented teams for 3 years. Host Natalie Pistunovic Complete your event RSVP here: https://gdg.community.dev/events/details/google-gdg-berlin-presents-genai-berlin-august-meetup/. |
GenAI Berlin August Meetup
|