leonie
@iamleonie.bsky.social
I do Machine Learning at Weaviate and write about it on the internet.
Pinned
leonie
@iamleonie.bsky.social
· Nov 20
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.
(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.
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.
Static embeddings -> speed-improvements
Binary quantization -> storage-reduction
Late interaction -> added granularity
I'm curious about lesser-known approaches that worked surprisingly well.
May 14, 2025 at 12:31 PM
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.
Static embeddings -> speed-improvements
Binary quantization -> storage-reduction
Late interaction -> added granularity
I'm curious about lesser-known approaches that worked surprisingly well.
Roses are red,
violets are blue,
A good baseline embedding model
is all-MiniLM-L6-v2.
violets are blue,
A good baseline embedding model
is all-MiniLM-L6-v2.
February 14, 2025 at 8:41 AM
Roses are red,
violets are blue,
A good baseline embedding model
is all-MiniLM-L6-v2.
violets are blue,
A good baseline embedding model
is all-MiniLM-L6-v2.
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...
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...
February 11, 2025 at 3:48 PM
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...
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...
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?
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?
January 31, 2025 at 9:15 AM
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?
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?
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?
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?
January 28, 2025 at 5:00 PM
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?
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?
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?
1. Data complexity
2. Task complexity
3. Dataset size
4. Computational constraints
5. Performance requirements
6. Scalability requirements
7. Latency requirements
What else?
January 26, 2025 at 1:03 PM
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?
1. Data complexity
2. Task complexity
3. Dataset size
4. Computational constraints
5. Performance requirements
6. Scalability requirements
7. Latency requirements
What else?
#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: https://buff.ly/3KWivSF
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: https://buff.ly/3KWivSF
January 22, 2025 at 4:01 PM
#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: https://buff.ly/3KWivSF
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: https://buff.ly/3KWivSF
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: https://buff.ly/4apUUG2
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: https://buff.ly/4apUUG2
January 21, 2025 at 4:00 PM
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: https://buff.ly/4apUUG2
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: https://buff.ly/4apUUG2
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.
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.
January 18, 2025 at 10:03 AM
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.
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.
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...
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...
January 16, 2025 at 12:46 PM
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...
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...
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...
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...
January 15, 2025 at 12:50 PM
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...
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...
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!
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!
December 19, 2024 at 3:55 PM
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!
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!
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...
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...
December 17, 2024 at 6:31 PM
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...
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...
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-...
@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-...
December 17, 2024 at 2:41 PM
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-...
@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-...
Reposted by leonie
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?
Here’s a cheat sheet of 7 of the most popular RAG architectures.
Which variants did we miss?
December 10, 2024 at 5:00 PM
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?
Here’s a cheat sheet of 7 of the most popular RAG architectures.
Which variants did we miss?
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
https://buff.ly/49yMR9K
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
https://buff.ly/49yMR9K
December 10, 2024 at 11:02 PM
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
https://buff.ly/49yMR9K
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
https://buff.ly/49yMR9K
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.
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.
December 4, 2024 at 5:03 PM
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.
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.
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?
What cool use cases using Generative AI have you seen in the wild so far?
November 30, 2024 at 4:00 PM
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?
What cool use cases using Generative AI have you seen in the wild so far?
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
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
November 28, 2024 at 1:34 PM
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
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
Reposted by leonie
🇯🇵日本初のWeaviateミートアップのお知らせ🇯🇵
本イベントでは、Weaviateの特徴や活用事例を学び、Weaviate CEO @bobvanluijt.bsky.socialとグローバル パートナーシップ責任者 @jobig630.bsky.social やWeaviate Kagome コントリビューター Jun Ohtaniと交流できる場を提供します。
マルチモーダル検索や検索拡張世代（RAG）によるAIのユースケースのお話楽しみにしてます。
本イベントでは、Weaviateの特徴や活用事例を学び、Weaviate CEO @bobvanluijt.bsky.socialとグローバル パートナーシップ責任者 @jobig630.bsky.social やWeaviate Kagome コントリビューター Jun Ohtaniと交流できる場を提供します。
マルチモーダル検索や検索拡張世代（RAG）によるAIのユースケースのお話楽しみにしてます。
新世代のソフトウェアのためのAIネイティブベクトルデータベース Weaviate 日本イベント初開催 (2024/12/11 14:30〜)
この度、日本初のWeaviate主催 プロダクトアップデートイベントを開催します。 Weaviateは、AIネイティブなオープンソースベクトルデータベースとして世界で最も注目を集めるグローバルリーダーです。 世界の先進企業がどのように生成AIをプロトタイプから本番へとスケールアップさせているのか学んでいただくチャンスです。 最先端のマルチモーダル検索や検索拡張世代（RAG）によるAIのユースケ...
connpass.com
November 28, 2024 at 9:09 AM
🇯🇵日本初のWeaviateミートアップのお知らせ🇯🇵
本イベントでは、Weaviateの特徴や活用事例を学び、Weaviate CEO @bobvanluijt.bsky.socialとグローバル パートナーシップ責任者 @jobig630.bsky.social やWeaviate Kagome コントリビューター Jun Ohtaniと交流できる場を提供します。
マルチモーダル検索や検索拡張世代（RAG）によるAIのユースケースのお話楽しみにしてます。
本イベントでは、Weaviateの特徴や活用事例を学び、Weaviate CEO @bobvanluijt.bsky.socialとグローバル パートナーシップ責任者 @jobig630.bsky.social やWeaviate Kagome コントリビューター Jun Ohtaniと交流できる場を提供します。
マルチモーダル検索や検索拡張世代（RAG）によるAIのユースケースのお話楽しみにしてます。
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-...
@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-...
November 26, 2024 at 4:13 PM
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-...
@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-...
Struggling with slow filtered vector search?
Here's how Weaviate's researchers 10x'ed query speeds with ACORN:
Here's how Weaviate's researchers 10x'ed query speeds with ACORN:
November 20, 2024 at 10:00 AM
Struggling with slow filtered vector search?
Here's how Weaviate's researchers 10x'ed query speeds with ACORN:
Here's how Weaviate's researchers 10x'ed query speeds with ACORN:
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.
(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.
November 20, 2024 at 9:10 AM
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.
(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.