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can give useful answers to many questions, but there are also well-known issues with their output: The responses may be outdated, inaccurate, or outright hallucinations, and it’s hard to know when you can trust them. 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.

In this talk, Louise will share his experience with RAG evaluation and the challenges of scaling the feature with cost efficiency, stability, and speed.

Send us a text Welcome to the cozy corner of the tech world where ones and zeros mingle with casual chit-chat. Datatopics Unplugged is your go-to spot for relaxed discussions around tech, news, data, and society. Dive into conversations that should flow as smoothly as your morning coffee (but don't), where industry insights meet laid-back banter. Whether you're a data aficionado or just someone curious about the digital age, pull up a chair, relax, and let's get into the heart of data, unplugged style!

In this episode, titled, "#46 Debunking Devon, Exploring RAG Frameworks, and Tech for a Better World", our special guest Martin Van Mollekot adds a rich layer of insight to our tech stew, covering everything from 3D-printed humanoids to the harmonious blend of AI and music, all while exploring how tech is cultivating a better world. 3D Printing: Martin discusses building a humanoid using resources from Thingiverse.AI Generated Music: Exploring Udio, an AI that not only composes music but adds vocals to match your taste.Devin Debunked: Unpacking the claims of the "First AI Software Engineer" and why it's not quite time to worry about AI taking coding jobs.GPT-4 Over Humans? A critical look at whether AI could replace junior analysts in the current tech landscape.The Data Science Dilemma: Is Data Science Dead? Discussing the evolution and future relevance of data science, with Zapier highlighted for its accessible toolset.RAG Frameworks Galore:. Discover the evolving buffet of RAG frameworks, making data handling smoother – and whether they're up to the hype: Ragflow, Pine Cone, Verba, and R2R. Tech for a Better World: Martin shares his personal story of how computer vision technology can aid farmers in managing their livestock.Hip-Hop and Generative AI: How generative AI is stirring up the music industry & tips from Bart on reproducing hit tracks.The Low-Code Revolution: Martin shares his insights on the rise of low-code/no-code platforms in data management.

Retrieval Augmented Generation (RAG) is a powerful technique to provide real time, domain-specific context to the LLM to improve accuracy of responses. RAG doesn't require the addition of sensitive data to the model, but still requires application developers to address security and privacy of user and company data. In this session, you will learn about security implications of RAG workloads and how to architect your applications to handle user identity and to control data access.

Click the blue “Learn more” button above to tap into special offers designed to help you implement what you are learning at Google Cloud Next 25.

This in-depth technical session delves into real-world use cases, and design patterns for building generative AI applications using Google Cloud Databases, Vertex AI, and popular open-source orchestration frameworks such as LangChain. We’ll showcase a sample application that leverages the versatility of Google Cloud Databases to implement dynamic grounding using various RAG techniques, giving you valuable insights on implementing enterprise-grade gen AI solutions.

Click the blue “Learn more” button above to tap into special offers designed to help you implement what you are learning at Google Cloud Next 25.

Building an assistant capable of answering complex, company-specific questions and executing workflows requires first building a powerful Retrieval Augmented Generation (RAG) system. Founding engineer Eddie Zhou explains how Glean built its RAG system on Google Cloud— combining a domain-adapted search engine with dynamic prompts to harness the full capabilities of Gemini's reasoning engine. By attending this session, your contact information may be shared with the sponsor for relevant follow up for this event only.

Click the blue “Learn more” button above to tap into special offers designed to help you implement what you are learning at Google Cloud Next 25.

Accessing mission-critical data in a nonintrusive fashion will be critical for enabling operational analytics, and with the evolution of generative AI, enterprises are building RAG-based gen AI applications that require access to operational data. Datastream is a simple, serverless data-streaming platform that organizes the ingesting, processing, and analyzing operational data to support AI/ML and RAG apps. Experts from RocketMoney and Intuit Mailchimp will share how they’re using Datastream to solve for Operational Analytics and beyond.

Click the blue “Learn more” button above to tap into special offers designed to help you implement what you are learning at Google Cloud Next 25.

As generative AI applications mature, retrieval-augmented generation (RAG) has become popular for improving large language model-based apps. We expect teams to move beyond basic RAG to autonomous agents and generative loops. We'll set up a Weaviate vector database on Google Kubernetes Engine (GKE) and Gemini to showcase generative feedback loops.

After this session, a Google Cloud GKE user should be able to: - Deploy Weaviate open source on GKE - Set up a pipeline to ingest data from the Cloud Storage bucket - Query, RAG, and enhance the responses

Click the blue “Learn more” button above to tap into special offers designed to help you implement what you are learning at Google Cloud Next 25.

Following the explosion of ChatGPT onto the market in late 2022, LexisNexis Legal & Professional quickly saw the massive opportunity for large language models (LLMs) to transform how its customers do legal work. Within weeks, the company pivoted to begin innovating, delivering, and now expanding generative AI solutions for its customers. Across legal and tech industries, the company was recognized as a generative AI leader.

LexisNexis EVP & CTO Jeff Reihl will detail how the company rapidly innovated, delivered, and expanded generative AI solutions. Reihl will share insights into how the company considers its customers’ key challenges and its multi-model approach, prioritizing the best LLM to solve each customer use case. He’ll also share how the company integrates its data assets with LLM technology to improve model output and how the company’s Retrieval Augmented Generation (RAG) platform creates flexibility for the company to adopt new LLM technologies as they change. 

Attendees will learn strategies for deploying generative AI in their organizations to impact products, customers, and internal tools. Reihl will share how attendees should think about deploying generative AI in their organization, how to hire for it, and how to organize teams around it.

Startups are setting the bar high for innovation and impact with AI implementations. In this lightning round session, you’ll learn from some groundbreaking startups.

Resemble AI will talk about their cutting-edge text to speech engine integrated with Google's Gemma AI and Gretel.ai will show how they empower developers to create high-quality synthetic data. Learn about Writer AI large language models that are top-ranked on Stanford HELM's leaderboard, as well as their unique graph-based retrieval-augmented generation approach. Join us for a showcase in the latest AI innovation.

Click the blue “Learn more” button above to tap into special offers designed to help you implement what you are learning at Google Cloud Next 25.

In this session, you’ll learn how to deploy a fully-functional Retrieval-Augmented Generation (RAG) application to Google Cloud using open-source tools and models from Ray, HuggingFace, and LangChain. You’ll learn how to augment it with your own data using Ray on Google Kubernetes Engine (GKE) and Cloud SQL’s pgvector extension, deploy any model from HuggingFace to GKE, and rapidly develop your LangChain application on Cloud Run. After the session, you’ll be able to deploy your own RAG application and customize it to your needs.

Click the blue “Learn more” button above to tap into special offers designed to help you implement what you are learning at Google Cloud Next 25.

In this session, Douwe Kiela, the CEO and Co-Founder of Contextual AI and an Adjunct Professor in Symbolic Systems at Stanford University, will talk about how Contextual AI is building the next generation of language models leveraging Google Cloud. He will dive deeper into why retrieval augmented generation (RAG; which he pioneered at Facebook) is the dominant paradigm for large language model (LLM) deployments and the role he believes RAG will play in the future of gen AI.

Click the blue “Learn more” button above to tap into special offers designed to help you implement what you are learning at Google Cloud Next 25.

Natural language is an ideal interface for many real time applications such as inventory tracking, patient journey, field sales, and other on-the-go situations. However, these real time applications also require up to date and accurate information, which necessitates a real time RAG architecture. In this session, we will demonstrate how you can build an accurate and up to date real time generative AI application using a combination of Dataflow and graph databases.

Click the blue “Learn more” button above to tap into special offers designed to help you implement what you are learning at Google Cloud Next 25.

Building an assistant capable of answering complex, company-specific questions and executing workflows requires first building a powerful Retrieval Augmented Generation (RAG) system. Founding engineer Eddie Zhou explains how Glean built its RAG system on Google Cloud— combining a domain-adapted search engine with dynamic prompts to harness the full capabilities of Gemini's reasoning engine. By attending this session, your contact information may be shared with the sponsor for relevant follow up for this event only.

Click the blue “Learn more” button above to tap into special offers designed to help you implement what you are learning at Google Cloud Next 25.

GenAI can look deceptively easy when it comes to showing a cool demo, but can prove incredibly hard to productionalize. This session will cover the challenges behind industrializing GenAI applications in the enterprise, and the approaches engineers are taking to meet these challenges. Attendees will get to take a look under the hood to see how Data Engineering and Integration techniques can help us go from simple demos to production grade applications with consistently high quality results.  

We will explore how Retrieval Augmented Generation (RAG) workflows go from naive to advanced. Techniques discussed will cover a typical GenAI application flow with topics including multiple and hybrid models, refined data processing, data security, getting transparency in results, combining structured and unstructured data, and putting it all together to get high performance and cost effective outcomes. Attendees will leave the session with a framework to understand proposed solutions from their teams and ask the right questions to test if a solution can become industrial-grade.

Unlock the power of retrieval-augmented-generation (RAG) for generative AI apps with Vertex AI app builder platform. Vertex AI Vector Search powers blazingly fast embeddings retrieval for your search, recommendations, ad serving, and other gen AI applications. Multimodal embeddings scale your search across text, images, and other modalities. Customize your RAG pipeline with document understanding capabilities. With comprehensive offerings, Vertex AI makes building robust RAG systems easy.

Click the blue “Learn more” button above to tap into special offers designed to help you implement what you are learning at Google Cloud Next 25.

Explore the transformative power of Generative AI with Databricks on Google Cloud. Learn to integrate and leverage governed, sensitive data for real-world problem-solving, from advanced RAG applications to traditional challenges. With 88% of enterprises investing in Generative AI, discover how to swiftly develop and deploy tailored solutions, which could include Q&A bots and custom models. Gain insights from a customer’s experience and propel your organization into the forefront of AI innovation. By attending this session, your contact information may be shared with the sponsor for relevant follow up for this event only.

Click the blue “Learn more” button above to tap into special offers designed to help you implement what you are learning at Google Cloud Next 25.

In this workshop, you will learn how you can easily create a Retrieval Augmented Generation (RAG) application and how to use it. We will be highlighting AlloyDB Omni (our deploy-anywhere version of AlloyDB) with pgvector's vector search capabilities. You will learn to run an LLM and embedding model locally so that you can run this application anywhere. Creating an app in a secure way with LLMs playing around your data is harder than ever. Come and build with me!

Click the blue “Learn more” button above to tap into special offers designed to help you implement what you are learning at Google Cloud Next 25.