iiinova — where your digital self keeps evolving

leonie @iamleonie.bsky.social · 14/01/2026

I've seen a lot of explanations on similarity measures in vector search but this one by my colleague @dadoonet is by far the most fun! How similar* is Han Solo to: • Princess Leia: very similar • Obi-Wan: meh • Darth Vader: complete opposites Talk slides: david.pilato.fr/talks/2025/2...

211

leonie @iamleonie.bsky.social · 14/05/2025

What's the most underrated embedding technique you've used? Static embeddings -> speed-improvements Binary quantization -> storage-reduction Late interaction -> added granularity I'm curious about lesser-known approaches that worked surprisingly well.

010

leonie @iamleonie.bsky.social · 14/02/2025

Roses are red, violets are blue, A good baseline embedding model is all-MiniLM-L6-v2.

051

leonie @iamleonie.bsky.social · 11/02/2025

Make RAG results more trustworthy with citations. In his latest recipe, @danman966.bsky.social shows you how you can build a RAG pipeline with citations, using: - a @weaviate.bsky.social vector database and - @anthropic.com's Claude 3.5 Sonnet 📌 Code: github.com/weaviate/rec...

130

leonie @iamleonie.bsky.social · 31/01/2025

Normalize not knowing everything in the AI space. It's evolving fast. I’m sure your to-do list is growing as fast as mine. Here are 3 topics, I want to catch up on this quarter: • AI agents • Fine-tuning embedding models • Multimodality • (If time permits: reinforcement learning) What about you?

160

leonie @iamleonie.bsky.social · 28/01/2025

I’m trying to wrap my head around multi-agent system architectures. Here are some patterns I’m seeing so far: 1. Type of collaboration: Network vs. hierarchical 2. Type of information flow: Sequential vs. parallel vs. loop 3. Type of functionality: Routing vs. aggregating What else?

060

leonie @iamleonie.bsky.social · 26/01/2025

Some considerations for choosing a vector dimension: 1. Data complexity 2. Task complexity 3. Dataset size 4. Computational constraints 5. Performance requirements 6. Scalability requirements 7. Latency requirements What else?

020

leonie @iamleonie.bsky.social · 22/01/2025

#1 Rule of RAG Club: Look at your data. With the new explorer tool, looking at your data got a lot easier in Weaviate Cloud. The explorer tool provides a graphical interface to easily: • Browse collections • Inspect objects, metadata, and vectors Check it out now: buff.ly/3KWivSF

010

leonie @iamleonie.bsky.social · 21/01/2025

You can be GPU poor like me and still fine-tune an LLM. Here’s how you can fine-tune Gemma 2 in a Kaggle notebook on a single T4 GPU: • @kaggle.com offers 30 hours/week of GPUs for free • @unsloth.bsky.social uses 60% less memory to fit it on a T4 GPU 🔗Code: buff.ly/4apUUG2

010

leonie @iamleonie.bsky.social · 18/01/2025

Although I know that Vertical scaling: scaling up (to a more powerful machine) Horizontal scaling: scaling out (to multiple smaller machines) I still always have to take a second to think about it. It’s like the left-right-weakness of system design.

000

leonie @iamleonie.bsky.social · 16/01/2025

I talk about RAG so much, I could fill a book. So, we did - and you can download it for free. Together with my colleagues Mary & Prajjwal, we curated an e-book of the most effective advanced RAG techniques. Which ones did we miss? Get it now: weaviate.io/ebooks/advan...

073

leonie @iamleonie.bsky.social · 15/01/2025

Over the holidays, I learned how to fine-tune an LLM. Here’s my entry for the latest @kaggle.com comp. This tutorial shows you: • Fine-tune Gemma 2 • LoRA fine-tuning with @unsloth.bsky.social on T4 GPU • Experiment tracking with @weightsbiases.bsky.social 🔗Code: www.kaggle.com/code/iamleon...

030

leonie @iamleonie.bsky.social · 19/12/2024

Got myself a little early Christmas present. Although this book is from 2017, I heard so many good things about it this year. Can't wait to dig into this over the holidays. And with that being said, I hope you have some nice and relaxing holidays yourself! See you in the new year!

100

leonie @iamleonie.bsky.social · 17/12/2024

It’s time to review the AI space in 2024! Here’s what I got right (and what I missed) in my 2024 predictions: ✅ Evaluation ❌ Multimodal foundation models ❌ Fine-tuning open-weight models and quantization ❌ AI agents ✅ RAG lives on ❌ Knowledge graphs medium.com/towards-data...

100

leonie @iamleonie.bsky.social · 17/12/2024

日本語テキスト向けのハイブリッド検索には日本語テキス用のトークナイザーが必要です。 @weaviate.bsky.socialでは３つのトークナイザーを使用することができます。一つずつのメリットとデメリットはこちら weaviate.io/blog/hybrid-...

010

Reposted by leonie

Weaviate @weaviate.bsky.social · 10/12/2024

Struggling to keep up with new RAG variants? Here’s a cheat sheet of 7 of the most popular RAG architectures. Which variants did we miss?

1143

leonie @iamleonie.bsky.social · 10/12/2024

ハイブリッド検索とは何？ハイブリッド検索は、デンスベクトルとスパースベクトルを統合して、それぞれの検索手法の利点を活かします。この記事では、Weaviateの日本語テキスト向けのハイブリッド検索の説明をします。 - 日本語テキス用のトークナイザーを使用するキーワード検索 - ベクトル検索 - 融合アルゴリズム詳しくはこちら buff.ly/49yMR9K

000

leonie @iamleonie.bsky.social · 04/12/2024

Look what came in the mail today! This is already the 2nd edition of “Developing apps with GPT-4” by Olivier and Marie-Alice I had the pleasure to review. This edition covers the latest advancements in GPT-4, especially regarding its visual capabilities to build multimodal applications.

130

leonie @iamleonie.bsky.social · 30/11/2024

It's been two years since the release of ChatGPT. What cool use cases using Generative AI have you seen in the wild so far?

000

leonie @iamleonie.bsky.social · 28/11/2024

Struggling with RAG over PDF files? You might want to give Docling a try. 𝗪𝗵𝗮𝘁'𝘀 𝗗𝗼𝗰𝗹𝗶𝗻𝗴? • Python package by IBM • OS (MIT license) • PDF, DOCX, PPTX → Markdown, JSON 𝗪𝗵𝘆 𝘂𝘀𝗲 𝗗𝗼𝗰𝗹𝗶𝗻𝗴? • Doesn’t require fancy gear, lots of memory, or cloud services • Works on regular computers or Google Colab Pro

1132

leonie @iamleonie.bsky.social · 26/11/2024

Yes, you don’t need a vector database to do vector search. @victorialslocum.bsky.social shows you how - using just numpy. This article covers: • How does vector search work? • How to do vector search from scratch in Python • and more Learn more: weaviate.io/blog/vector-...

161

leonie @iamleonie.bsky.social · 20/11/2024

Struggling with slow filtered vector search? Here's how Weaviate's researchers 10x'ed query speeds with ACORN:

290

leonie @iamleonie.bsky.social · 20/11/2024

Hi, I am Leonie! (Yes, that's the handle) I do machine learning at Weaviate and write about it on the Internet. medium.com/@iamleonie You might know me for my monochrome technical visuals.

1261