- Weaviate Newsletter
- Posts
- Beyond basic RAG at Google Next ‘24, academic paper reviews, DSPy meetups, and more
Beyond basic RAG at Google Next ‘24, academic paper reviews, DSPy meetups, and more
Victoria Slocum
April 25, 2024
Hello Weaviate Community, 🤗
Great to see you here! We’ve got a packed newsletter this week, including great resources from Google Next ‘24 on building AI apps with Gemini and Weaviate and a new paper reviews initiative so you never miss out on academic research and techniques. Also, we have an exciting DSPy meetup with Arize and Cohere on May 1st in San Francisco 🎉
Let’s get into it!
Google Next ‘24 was a blast!
Team Weaviate attended our first Google Cloud Next and we had a blast! We connected with folks from our community, made lots of new friends, and shared our latest product features and trend predictions. Check out the resources below to see more about what went on!
✍️ Highlights from Google Next ‘24 by Ieva Urbaite
Check out Ieva’s blog post on the latest trends from the field, our favorite product announcements, and upcoming events with our friends at Google Cloud.
🎥 From RAG to autonomous apps with Weaviate and Gemini on Google Kubernetes Engine by Bob van Luijt
As generative AI applications mature, retrieval-augmented generation (RAG) has become popular for improving large language model-based apps. Our CEO Bob joined Brian Kaufman, Senior Product Manager from Google Cloud, to talk about moving beyond basic RAG to autonomous agents and generative loops, and how to set up a Weaviate vector database on Google Kubernetes Engine (GKE) and Gemini.
💻 Github Demo showcasing using Weaviate & Google Gemini
This demo application creates a product catalog that is stored in a Weaviate vector database and vectorized for semantic search. It is also integrated with the Gemini Pro Vision API to automatically create product descriptions. The app is built with the NextJS framework.
AI tips, tricks, and tech
How-to
✍️ A Web Developers Guide to Hybrid Search by Daniel Phiri and Ajit Mistry
Learn about hybrid search for curious web developers with the new Weaviate Typescript client and Next.js!
✍️ Your Language Model Deserves Better Prompting by Erika Cardenas and Connor Shorten
One prompt does not fit all language models! Learn how to optimize your prompts using DSPy compilers in this in-depth blog post.
✍️ Unbody: Using Weaviate to Build the Foundation for AI-First App Development by Amir Houieh
Transforming data scattered across various sources into actionable insights, like searching or building chatbots, involves many complex tasks. Unbody - built on Weavaite’s technology - automates it all with just a few clicks and a line of code.
🎥 Zain and JP chat about: Vector embedding models for AI
Selecting the right vector embedding models can be hard, and even overwhelming! Zain Hasan and JP Hwang have a casual conversation filled with actionable tips and simply explained big ideas. Check it out for discussion on what embeddings are, how to go about selecting them, where to find benchmarks, how to read those benchmarks, and even how to do your own model evaluation.
Newest AI & data technology developments
Paper Reviews
The AI landscape changes fast, and staying on top of all the news and updates is hard and time-consuming - especially as most of the knowledge is “hidden” in academic papers and research reports.
But no worries - we’ve got you! With our new paper reviews initiative, we’re sharing 1-2 minute digestible, easy-to-read reviews of important papers.
Podcasts
🎙 RAGKit with Kyle Davis - Weaviate Podcast #93
Conversation with Kyle Davis, the creator of RAGKit! At a high-level, the podcast covers our understanding of RAG systems through 4 key areas: (1) Ingest / ETL, (2) Search, (3) Generate / Agents, and (4) Evaluation. Discussing these lead to all sorts of topics from Knowledge Graph RAG, to Function Calling and Tool Selection, Re-ranking, Quantization, and many more.
🎙 ParlayANN with Magdalen Dobson Manohar - Weaviate Podcast #94
In our 94th Weaviate podcast, Connor talks with Magdalen Dobson Manohar about vector search and her journey developing ParlayANN. The podcast begins with Magdalen’s journey into ANN science, the issue of Lock Contention in HNSW, further detailing HNSW vs. DiskANN vs. HCNNG and pyNNDescent, ParlayIVF, how Parallel Index Construction is achieved, conclusions from experimentation, Filtered Vector Search, Out of Distribution Vector Search, and exciting directions for the future!
Listen to the Weaviate podcast on YouTube, Spotify, or Apple Podcasts. ✨🎧
News
✍️ Weaviate on the Forbes AI 50 List: The most promising AI startups in 2024
Bob van Luijt reflects on Weaviate’s inclusion into the Forbes AI 50 2024, and our growth and direction in the current market.
Upcoming events
Weaviate Office Hours
Our next Office Hours is on Wednesday, May 15th. The Topic (voted by our Slack Community) will be Collections & General Q&A. Join our regular Office Hours to meet the experts and ask all the questions you may have.
Online workshops
Accelerate your journey with Weaviate and get hands-on experience by joining one of our free online workshops! No matter if you’re a beginner or an advanced AI developer, we host workshops for all levels:
Thursday, May 2nd | Getting started with the New Weaviate Typescript Client with Daniel Phiri
Wednesday, May 8th | Intro to Weaviate with JP Hwang
Tuesday, May 14th | Intro to Weaviate with Duda Nogueira
Thursday, May 16th | Multimodality with Zain Hasan (advanced)
Meetups
We love to give everyone around the globe the chance to meet, network, collaborate and learn new things on their journey of building AI applications. So it’s no surprise that May is packed with opportunities:
Wednesday, May 1st | DSPy Meetup in San Francisco
DSPy is a framework that enables you to program and optimize large language model (LLM) systems. We’re excited to co-host this event with Arize and Cohere on May 1st in San Francisco!
Tuesday, May 7th | AI for Developer Love Meetup in Amsterdam
Tuesday, May 14th | Hack Night at GitHub in San Francisco
Thursday, May 16th | AI Meetup NY with AI Camp
NY AI in Prod Roadshow
Our AI [in Prod] roadshow is making its next stop in New York City on May 21st. Join us for tech talks from our CTO Etienne, experts at Google Cloud, and Weaviate's customers. In the afternoon, Sebastian will run a hands-on Intro to Building AI-native Applications course.
Stay connected with us on social media for updates, behind-the-scenes glimpses, and maybe even a surprise or two. You can also find our events on our website!
Check out the provided links for all the details on how to sign up. We can't wait to meet you!
Welcoming new faces
Meet Mariska Tunc, joining as a Finance Operations Specialist.
We’re hiring!
Check out our open roles:
Have a look at our career page for more roles and opportunities! ✨
Thank you for reading
Do you have any questions about Weaviate, vector databases, documentation, or other topics? Say hi at the Community Slack or join our Weaviate Forum, where you can engage in community conversations. Looking forward to your participation over the next two weeks!
Weaviate is almost to 10,000 stars on GitHub! Check out our GitHub repository, and don't forget to star us while you're there ⭐
Till the next one,
Victoria