Perhaps the biggest complaint about generative AI is hallucination. If the text you want to generate involves facts, for example, a chatbot that answers questions, then hallucination is a problem. The solution to this is to make use of a technique called retrieval augmented generation, where you store facts in a vector database and retrieve the most appropriate ones to send to the large language model to help it give accurate responses. So, what goes into building vector databases and how do they improve LLM performance so much? Ram Sriharsha is currently the CTO at Pinecone. Before this role, he was the Director of Engineering at Pinecone and previously served as Vice President of Engineering at Splunk. He also worked as a Product Manager at Databricks. With a long history in the software development industry, Ram has held positions as an architect, lead product developer, and senior software engineer at various companies. Ram is also a long time contributor to Apache Spark.  In the episode, Richie and Ram explore common use-cases for vector databases, RAG in chatbots, steps to create a chatbot, static vs dynamic data, testing chatbot success, handling dynamic data, choosing language models, knowledge graphs, implementing vector databases, innovations in vector data bases, the future of LLMs and much more.  Links Mentioned in the Show: PineconeWebinar - Charting the Path: What the Future Holds for Generative AICourse - Vector Databases for Embeddings with PineconeRelated Episode: The Power of Vector Databases and Semantic Search with Elan Dekel, VP of Product at PineconeRewatch sessions from RADAR: AI Edition New to DataCamp? Learn on the go using the DataCamp mobile app Empower your business with world-class data and AI skills with DataCamp for business

Generative AI is here to stay, fundamentally altering our relationship with technology. But what does its future hold? In this session, Tom Tunguz, General Partner at Theory Ventures, Edo Liberty, CEO at Pinecone, and Nick Elprin, CEO at Domino Data Lab, explore how generative AI tools & technologies will evolve in the months and years to come. They navigate through emerging trends, potential breakthrough applications, and the strategic implications for businesses poised to capitalize on this technological wave.  Links Mentioned in the Show: Rewatch Session from RADAR: AI Edition New to DataCamp? Learn on the go using the DataCamp mobile appEmpower your business with world-class data and AI skills with DataCamp for business

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.

Generative AI is fantastic but has a major problem: sometimes it "hallucinates", meaning it makes things up. In a business product like a chatbot, this can be disastrous. Vector databases like Pinecone are one of the solutions to mitigating the problem. Vector databases are a key component to any AI application, as well as things like enterprise search and document search. They have become an essential tool for every business, and with the rise in interest in AI in the last couple of years, the space is moving quickly. In this episode, you'll find out how to make use of vector databases, and find out about the latest developments at Pinecone. Elan Dekel is the VP of Product at Pinecone, where he oversees the development of the Pinecone vector database. He was previously Product Lead for Core Data Serving at Google, where he led teams working on the indexing systems to serve data for Google search, YouTube search, and Google Maps. Before that, he was Founder and CEO of Medico, which was acquired by Everyday Health. In the episode, RIchie and Elan explore LLMs, hallucination in generative models, vector databases and the best use-cases for them, semantic search, business applications of vector databases and semantic search, the tech stack for AI applications, cost considerations when investing in AI projects, emerging roles within the AI space, the future of vector databases and AI, and much more.   Links Mentioned in the Show: Pinecone CanopyPinecone ServerlessLlamaIndexLangchain[Code Along] Semantic Search with PineconeRelated Episode: Expanding the Scope of Generative AI in the Enterprise with Bal Heroor, CEO and Principal at MactoresSign up to RADAR: The Analytics Edition New to DataCamp? Learn on the go using the DataCamp mobile appEmpower your business with world-class data and AI skills with DataCamp for business

An interactive workshop exploring the infrastructure and service architecture you need to scale AI applications in production, including infrastructure as code basics, provisioning AWS resources (ECS clusters, networking, messaging queues, and Amazon RDS Postgres), and managing Pinecone indexes.

What does it take to go from an idea in a notebook to an application handling real-world traffic? The Pinecone and Pulumi teams will explore the infrastructure and service architecture you need in order to scale AI apps in production. We will delve into deploying high-volume AI systems through scalable microservices, efficient data processing, and seamless synchronization between user interfaces and databases. We will examine the nuances of containerization for enhanced portability and Infrastructure as Code (IaC) for streamlined cloud deployments. The workshop will also discuss industry best practices in scalability and security for production-grade AI systems in a cloud-native landscape. This workshop is designed to help developers and engineers gain valuable insights and practical strategies for evolving AI applications into resilient and efficient cloud-native solutions.

Michel Tricot (CEO of Airbyte) joins me to chat about the impact of AI on the modern data stack, ETL for AI, the challenges of moving from open source to a paid product, and much more.

Airbyte & Pinecone - https://airbyte.com/tutorials/chat-with-your-data-using-openai-pinecone-airbyte-and-langchain

Note from Joe - I had audio issues cuz he got a new computer and didn't use the correct mic :(

The production and management of large-scale vector embeddings can be a challenging problem. The integration of Databricks, Hugging Face and Pinecone offers a powerful solution. Vector embeddings have become an essential tool in the development of AI powered applications. Embeddings are representations of data learned by machine models. High quality embeddings are unlocking use cases like semantic search, recommendation engines, and anomaly detection. Databricks' Apache Spark™ ecosystem together with Hugging Face's Transformers library enable large-scale vector embeddings production using GPU processing, Pinecone's vector database provides ultra-low latency querying and upserting of billions of embeddings, allowing for high-quality embeddings at scale for real-time AI apps.

In this session, we will present a concrete use case of this integration in the context of a natural language processing application. We will demonstrate how Pinecone's vector database can be integrated with Databricks and Hugging Face to produce large-scale vector embeddings of text data and how these embeddings can be used to improve the performance of various AI applications. You will see the benefits of this integration in terms of speed, scalability, and cost efficiency. By leveraging the GPU processing capabilities of Databricks and the ultra low-latency querying capabilities of Pinecone, we can significantly improve the performance of NLP tasks while reducing the cost and complexity of managing large-scale vector embeddings. You will learn about the technical details of this integration and how it can be implemented in your own AI projects, and gain insights into the speed, scalability, and cost efficiency benefits of using this solution.

Talk by: Roie Schwaber-Cohen

Connect with us: Website: https://databricks.com Twitter: https://twitter.com/databricks LinkedIn: https://www.linkedin.com/company/databricks Instagram: https://www.instagram.com/databricksinc Facebook: https://www.facebook.com/databricksinc

Vector databases such as ElasticSearch and Pinecone offer fast ingestion and querying on vector embeddings with ANNs. However, they typically do not decouple compute and storage, making them hard to integrate in production data stacks. Because data storage in these databases is expensive and not easily accessible, data teams typically maintain ETL pipelines to offload historical embedding data to blob stores. When that data needs to be queried, they get loaded back into the vector database in another ETL process. This is reminiscent of loading data from OLTP database to cloud storage, then loading said data into an OLAP warehouse for offline analytics.

Recently, “lakehouse” offerings allow direct OLAP querying on cloud storage, removing the need for the second ETL step. The same could be done for embedding data. While embedding storage in blob stores cannot satisfy the high TPS requirements in online settings, we argue it’s sufficient for offline analytics use cases like slicing and dicing data based on embedding clusters. Instead of loading the embedding data back into the vector database for offline analytics, we propose direct processing on embeddings stored in Parquet files in Delta Lake. You will see that offline embedding workloads typically touch a large portion of the stored embeddings without the need for random access.

As a result, the workload is entirely bound by network throughput instead of latency, making it quite suitable for blob storage backends. On a test one billion vector dataset, ETL into cloud storage takes around one hour on a dedicated GPU instance, while batched nearest neighbor search can be done in under one minute with four CPU instances. We believe future “lakehouses” will ship with native support for these embedding workloads.

Talk by: Tony Wang and Chang She

Here’s more to explore: State of Data + AI Report: https://dbricks.co/44i2HBp Databricks named a Leader in 2022 Gartner® Magic QuadrantTM CDBMS: https://dbricks.co/3phw20d

Connect with us: Website: https://databricks.com Twitter: https://twitter.com/databricks LinkedIn: https://www.linkedin.com/company/databricks Instagram: https://www.instagram.com/databricksinc Facebook: https://www.facebook.com/databricksinc

Summary

Data has been one of the most substantial drivers of business and economic value for the past few decades. Bob Muglia has had a front-row seat to many of the major shifts driven by technology over his career. In his recent book "Datapreneurs" he reflects on the people and businesses that he has known and worked with and how they relied on data to deliver valuable services and drive meaningful change.

Announcements

Hello and welcome to the Data Engineering Podcast, the show about modern data management Introducing RudderStack Profiles. RudderStack Profiles takes the SaaS guesswork and SQL grunt work out of building complete customer profiles so you can quickly ship actionable, enriched data to every downstream team. You specify the customer traits, then Profiles runs the joins and computations for you to create complete customer profiles. Get all of the details and try the new product today at dataengineeringpodcast.com/rudderstack Your host is Tobias Macey and today I'm interviewing Bob Muglia about his recent book about the idea of "Datapreneurs" and the role of data in the modern economy

Interview

Introduction How did you get involved in the area of data management? Can you describe what your concept of a "Datapreneur" is?

How is this distinct from the common idea of an entreprenur?

What do you see as the key inflection points in data technologies and their impacts on business capabilities over the past ~30 years? In your role as the CEO of Snowflake you had a first-row seat for the rise of the "modern data stack". What do you see as the main positive and negative impacts of that paradigm?

What are the key issues that are yet to be solved in that ecosmnjjystem?

For technologists who are thinking about launching new ventures, what are the key pieces of advice that you would like to share? What do you see as the short/medium/long-term impact of AI on the technical, business, and societal arenas? What are the most interesting, innovative, or unexpected ways that you have seen business leaders use data to drive their vision? What are the most interesting, unexpected, or challenging lessons that you have learned while working on the Datapreneurs book? What are your key predictions for the future impact of data on the technical/economic/business landscapes?

Contact Info

LinkedIn

Parting Question

From your perspective, what is the biggest gap in the tooling or technology for data management today?

Closing Announcements

Thank you for listening! Don't forget to check out our other shows. Podcast.init covers the Python language, its community, and the innovative ways it is being used. The Machine Learning Podcast helps you go from idea to production with machine learning. Visit the site to subscribe to the show, sign up for the mailing list, and read the show notes. If you've learned something or tried out a project from the show then tell us about it! Email [email protected]) with your story. To help other people find the show please leave a review on Apple Podcasts and tell your friends and co-workers

Links

Datapreneurs Book SQL Server Snowflake Z80 Processor Navigational Database System R Redshift Microsoft Fabric Databricks Looker Fivetran

Podcast Episode

Databricks Unity Catalog RelationalAI 6th Normal Form Pinecone Vector DB

Podcast Episode

Perplexity AI

The intro and outro music is from The Hug by The Freak Fandango Orchestra / CC BY-SA Sponsored By: Rudderstack:

Introducing RudderStack Profiles. RudderStack Profiles takes the SaaS guesswork and SQL grunt work out of building complete customer profiles so you can quickly ship actionable, enriched data to every downstream team. You specify the customer traits, then Profiles runs the joins and computations for you to create complete customer profiles. Get all of the details and try the new product today at dataengineeringpodcast.com/rudderstackSupport Data Engineering Podcast

Summary The vast majority of data tools and platforms that you hear about are designed for working with structured, text-based data. What do you do when you need to manage unstructured information, or build a computer vision model? Activeloop was created for exactly that purpose. In this episode Davit Buniatyan, founder and CEO of Activeloop, explains why he is spending his time and energy on building a platform to simplify the work of getting your unstructured data ready for machine learning. He discusses the inefficiencies that teams run into from having to reprocess data multiple times, his work on the open source Hub library to solve this problem for everyone, and his thoughts on the vast potential that exists for using computer vision to solve hard and meaningful problems.

Announcements

Hello and welcome to the Data Engineering Podcast, the show about modern data management When you’re ready to build your next pipeline, or want to test out the projects you hear about on the show, you’ll need somewhere to deploy it, so check out our friends at Linode. With their managed Kubernetes platform it’s now even easier to deploy and scale your workflows, or try out the latest Helm charts from tools like Pulsar and Pachyderm. With simple pricing, fast networking, object storage, and worldwide data centers, you’ve got everything you need to run a bulletproof data platform. Go to dataengineeringpodcast.com/linode today and get a $100 credit to try out a Kubernetes cluster of your own. And don’t forget to thank them for their continued support of this show! Are you bored with writing scripts to move data into SaaS tools like Salesforce, Marketo, or Facebook Ads? Hightouch is the easiest way to sync data into the platforms that your business teams rely on. The data you’re looking for is already in your data warehouse and BI tools. Connect your warehouse to Hightouch, paste a SQL query, and use their visual mapper to specify how data should appear in your SaaS systems. No more scripts, just SQL. Supercharge your business teams with customer data using Hightouch for Reverse ETL today. Get started for free at dataengineeringpodcast.com/hightouch. Have you ever had to develop ad-hoc solutions for security, privacy, and compliance requirements? Are you spending too much of your engineering resources on creating database views, configuring database permissions, and manually granting and revoking access to sensitive data? Satori has built the first DataSecOps Platform that streamlines data access and security. Satori’s DataSecOps automates data access controls, permissions, and masking for all major data platforms such as Snowflake, Redshift and SQL Server and even delegates data access management to business users, helping you move your organization from default data access to need-to-know access. Go to dataengineeringpodcast.com/satori today and get a $5K credit for your next Satori subscription. Your host is Tobias Macey and today I’m interviewing Davit Buniatyan about Activeloop, a platform for hosting and delivering datasets optimized for machine learning

Interview

Introduction How did you get involved in the area of data management? Can you describe what Activeloop is and the story behind it? How does the form and function of data storage introduce friction in the development and deployment of machine learning projects? How does the work that you are doing at Activeloop compare to vector databases such as Pinecone? You have a focus on image oriented data and computer vision projects. How does the specific applications of ML/DL influence the format and interactions with the data? Can you describe how the Activeloop platform is architected?

How have the design and goals of the system changed or evolved since you began working on it?

What are the feature and performance tradeoffs between self-managed storage locations (e.g. S3, GCS) and the Activeloop platform? What is the process for sourcing, processing, and storing

Summary Machine learning models use vectors as the natural mechanism for representing their internal state. The problem is that in order for the models to integrate with external systems their internal state has to be translated into a lower dimension. To eliminate this impedance mismatch Edo Liberty founded Pinecone to build database that works natively with vectors. In this episode he explains how this technology will allow teams to accelerate the speed of innovation, how vectors make it possible to build more advanced search functionality, and how Pinecone is architected. This is an interesting conversation about how reconsidering the architecture of your systems can unlock impressive new capabilities.

Announcements

Hello and welcome to the Data Engineering Podcast, the show about modern data management When you’re ready to build your next pipeline, or want to test out the projects you hear about on the show, you’ll need somewhere to deploy it, so check out our friends at Linode. With their managed Kubernetes platform it’s now even easier to deploy and scale your workflows, or try out the latest Helm charts from tools like Pulsar and Pachyderm. With simple pricing, fast networking, object storage, and worldwide data centers, you’ve got everything you need to run a bulletproof data platform. Go to dataengineeringpodcast.com/linode today and get a $100 credit to try out a Kubernetes cluster of your own. And don’t forget to thank them for their continued support of this show! RudderStack’s smart customer data pipeline is warehouse-first. It builds your customer data warehouse and your identity graph on your data warehouse, with support for Snowflake, Google BigQuery, Amazon Redshift, and more. Their SDKs and plugins make event streaming easy, and their integrations with cloud applications like Salesforce and ZenDesk help you go beyond event streaming. With RudderStack you can use all of your customer data to answer more difficult questions and then send those insights to your whole customer data stack. Sign up free at dataengineeringpodcast.com/rudder today. When it comes to serving data for AI and ML projects, do you feel like you have to rebuild the plane while you’re flying it across the ocean? Molecula is an enterprise feature store that operationalizes advanced analytics and AI in a format designed for massive machine-scale projects without having to manage endless one-off information requests. With Molecula, data engineers manage one single feature store that serves the entire organization with millisecond query performance whether in the cloud or at your data center. And since it is implemented as an overlay, Molecula doesn’t disrupt legacy systems. High-growth startups use Molecula’s feature store because of its unprecedented speed, cost savings, and simplified access to all enterprise data. From feature extraction to model training to production, the Molecula feature store provides continuously updated feature access, reuse, and sharing without the need to pre-process data. If you need to deliver unprecedented speed, cost savings, and simplified access to large scale, real-time data, visit dataengineeringpodcast.com/molecula and request a demo. Mention that you’re a Data Engineering Podcast listener, and they’ll send you a free t-shirt. Your host is Tobias Macey and today I’m interviewing Edo Liberty about Pinecone, a vector database for powering machine learning and similarity search

Interview

Introduction How did you get involved in the area of data management? Can you start by describing what Pinecone is and the story behind it? What are some of the contexts where someone would want to perform a similarity search?

What are the considerations that someone should be aware of when deciding between Pinecone and Solr/Lucene for a search oriented use case?

What are some of the other use cases that Pinecone enables? In the absence of Pinecone, what kinds of systems and solutions are people b