Vector databases: from embeddings to applications, re:Invent 2023, and podcasts on AI, LLMs, and RAG
Hello, Weaviate Community!
November is here, and Weaviate is buzzing with excitement. Before we jump into the latest and greatest, let's recap the highlights from the previous newsletter. Ready for the scoop?
Let's dive in! 🚀
Weaviate takes on re:Invent 2023
Exciting news! Weaviate is heading to AWS re:Invent in Las Vegas from Nov 27 - Dec 1! Swing by our booth for live product demos, exclusive merch, and a chance to win Lego sets and Weaviate plushies. Our team is eager to meet you, answer questions, and discuss the latest tech trends.
Can't wait to connect at the event!
Check out our AWS re:Invent page here.
Vector data tips, tricks, and tech
Learn about the Weaviate 1.22 release highlights. This 5-minute video provides an overview of nested object storage, asynchronous indexing, official gRPC support and the new v4 Python client.
Vector databases are a key part of many LLM applications that need search or data retrieval, for example with Retrieval Augmented Generation (RAG). Learn how they work + how to use them in this new short course, by Sebastian Witalec.
Newest AI & data technology developments
Check out the 75th Weaviate Podcast with Tanmay Chopra! Discover Tanmay's ML journey from TikTok to Neeva and now his startup, Emissary. Get insights on Search AI, including Temporal Queries and Query Recommendation. Tanmay shares the motivation behind Emissary, with nuggets like the GPT-4 analogy to 3D printers.
Featuring Simba Khadder, CEO of FeatureForm! Dive into the world of feature engineering, where Simba sheds light on how features impact machine learning models. From orchestrating transformations to enhancing RAG with advanced features for better context in LLMs, Simba shares valuable insights.
Join the Weaviate Podcast with Charles Packer, lead author of MemGPT at UC Berkeley! Explore the exciting concept of an "Operating System for LLMs," where MemGPT is prompted with its context limits and equipped with memory management tools for adaptive behavior. Join us for a quick dive into the future of language models!
Explore Machine Learning with Tables and Tabular Data with expert Madelon on the Weaviate Podcast. We cover various topics like tabular data and embeddings, searching through tables, semantic joins, advanced Text-to-SQL, and using machine learning for query execution.
Discover RAG and LLM with Vibs Abhishek, CEO of Alltius AI. On the Weaviate Podcast, Vibs breaks down Alltius's pillars: Knowledge, Skills, and Deployment Channels. Learn about the differences between Assistants and Agents, and how Alltius tackles challenges in Enterprise RAG applications.
Mark your calendar
November 10th - 16th, Online: Collaborate with AI enthusiasts worldwide and team up with Coral, Cohere’s Knowledge Agent, to craft innovative solutions. Enroll here: Cohere Coral Hackathon
November 14th, 8 PM CET, Online: Join in to leverage the power of lightning-fast vector search implemented by using vector databases in collaboration with DeepLearningAI: Workshop - Building Multi-Modal Search with Vector Databases
Welcome to the team
Meet Nick Olivetti, joining us from the US in Pennsylvania as our new Enterprise Account Executive.
Thank you for reading
Do you have burning questions about Weaviate, vector databases, docs, or anything else? Dive into the discussion over at the Weaviate Forum and connect with the community. Catch you in the next news updates!