• Weaviate Newsletter
  • Posts
  • Locally Running RAG Pipelines, JavaScript June Recap, and Opportunities to Join Weaviate!

Locally Running RAG Pipelines, JavaScript June Recap, and Opportunities to Join Weaviate!

Author

Femke Plantinga
July 18, 2024

Hello Weaviate Community, 🤗

June was a blast, but July is heating up too! ☀️

We've recapped JavaScript June to give you a glimpse of one of our big June events. Our summer workshops are heating up, so join us from your laptop, whether you're at home or taking a break somewhere sunny. Weaviate is still hiring for several new roles—check them out at the end of the newsletter.

Let's dive in. 🏊

Empowering JavaScript Developers to Build AI-Powered Applications

In June, we celebrated the TypeScript v3 client release with a series of webinars focusing on Angular, React, and Vue.js. These webinars showcased the power of vector databases and multimodal embeddings in AI-native applications. The depth of questions from our sessions highlighted the evolving role of full-stack AI engineers in the JavaScript community. For more details, check out the full blog post here.

AI data tips, tricks, and tech

How-to

Newest AI & data technology developments

Podcasts

Listen to the Weaviate podcast on YouTube, Spotify, or Apple Podcasts. ✨🎧

Weaviate Paper Reviews

Have you read Zain Hasan’s paper reviews?

  • 🗞️ Many-Shot In-Context Learning

    • In this paper, DeepMind explores whether fine-tuning large language models (LLMs) or using relevant examples in the prompt yields better performance.

  • 🗞️ Adaptive Retrieval and Scalable Indexing for k-NN Search with Cross-Encoders

    • The paper from DeepMind introduces Adaptive Cross-Encoder Nearest Neighbor Search, a method that combines the retrieval quality of cross-encoders/re-rankers with the efficiency of bi-encoders by approximating query-document similarities within a bi-encoder framework.

  • 🗞️ RouteLLM: Learning to Route LLMs with Preference Data

    • You don't need a massive model to answer simple queries; a new paper proposes a framework to train a router that directs queries to the most appropriate language model based on difficulty and specialization, optimizing cost and performance across models like Llama-3-70b and GPT-4.

Curious about more Weaviate Paper Reviews? Visit our page here!

Upcoming events

Online events

Learn Advanced RAG Tricks with Zain 💚

We’re excited to announce our ✨new✨ online hands-on session, where we’ll explore the innovative and promising AI use case of Retrieval-Augmented Generation (RAG). 🥳

RAG is one of the most promising AI use cases for companies across various industries, offering advanced capabilities in data retrieval and generation. However, scaling RAG to production presents several challenges:

1️⃣ Data Preparation

2️⃣ Query Optimization

3️⃣ Retrieval Quality

Join our upcoming online hands-on session with Zain Hasan to learn best practices, options, and strategies for indexing data, optimizing retrieval, and enhancing generation to build and scale advanced RAG applications effectively for production.

Remember to check out the provided links for all the details on how to sign up. We can't wait to see you there.

Welcoming new faces

  • Meet Rich Lapham, who is joining the People & Culture team as our Recruiter.

Let’s work together

Check out our open roles:

Internship at Weaviate

Have a look at our career page for more roles and opportunities! ✨

Thank you for reading

Do you have questions about Weaviate, vector databases, or anything else? Join us on Community Slack or the Weaviate Forum. We look forward to hearing from you in the next two weeks!

Weaviate is open source. Check out our GitHub repository, and don't forget to star us while you're there. ⭐

Till the next one,

Femke