Please join us in welcoming these awesome new joiners today!
Faustas Butkus - Software Engineer ๐งโ๐ป
Tobias Christiani - Research Engineer โจ๏ธ
Jacob Heier - Enterprise Account Executive ๐
Kamil Tyborowski - Software Engineer ๐งโ๐ป
We're so excited to have you on the team!
#teamweaviate
Please join us in welcoming three new joiners this week! ๐
Danielle Washington - Technical Documentation Writer โจ๏ธ
Giorgos Kampitakis - Full Stack Engineer ๐จโ๐ป
Mary Ann Casugod - Product Support Engineer ๐ฉโ๐ป
Welcome to the team! ๐ซ
#teamweaviate #newjoiners #techjobs
We've hit an exciting milestone at Weaviate: the 100 people mark! ๐ฅณ
As a fully remote company, our teams span the globe, and it's incredible to see talented people from all corners of the world unite behind our mission. โจ
Check out our open positions at https://weaviate.io/company/careers
Welcome to these new joiners that start today!
Austin Freels - Director of Customer Success Engineering ๐ฅ
Madison Sanders - Enterprise Account Executive ๐
Elisa Seay - Enterprise Account Executive ๐
Nathaniel Ma - Enterprise Account Executive ๐
We're so excited to have you on the team!
๐ Get started here: cloud.google.com/vertex-ai/ge...
๐ Notebook: github.com/GoogleCloudP...
๐ก Soon, many more examples!
Exciting News ๐จ
Weaviate is spotlighted in Googleโs 5-Day GenAI Intensive course hosted by Kaggle!
Explore the whitepaper โEmbeddings & Vector Storesโ by Anant Nawalgaria & Xiaoqi Ren.
Read the full paper here:
www.kaggle.com/whitepaper-embeddings-an...
Start your year off with something newโจ
Combine @inngest.com's workflow engine with Weaviate's vector search capabilities and create powerful agentic applications that practically run themselves! A big step up for anyone working with large-scale RAG systems.
Check out the blog! lnkd.in/gSW-xHVf
We're so excited to welcome this awesome group of people to the team this week! ๐
Dyma - Software Engineer Client Libraries
Ivan - Technical Documentation Writer
Brendan - Enterprise Account Executive
Aaron - Enterprise Account Executive
Sean - Business Development Representative
๐๐ฒ๐ป๐ฒ๐ฟ๐ฎ๐๐ถ๐ผ๐ป ๐๐ผ๐บ๐ฝ๐ผ๐ป๐ฒ๐ป๐:
This focuses on how well generated answers are both accurate and relevant. It also notes the shift from focusing mostly on spotting false information (hallucinations) to other metrics like how reasonable and specific the answers are.
๐ฅ๐ฒ๐๐ฟ๐ถ๐ฒ๐๐ฎ๐น ๐๐ผ๐บ๐ฝ๐ผ๐ป๐ฒ๐ป๐:
This discusses new ways to measure search accuracy using large language models (LLMs) for context precision and recall. It also mentions how human evaluators have traditionally been used to assess recall, precision, and ranking quality (nDCG).
๐๐ป๐ฑ๐ฒ๐
๐ถ๐ป๐ด ๐๐ผ๐บ๐ฝ๐ผ๐ป๐ฒ๐ป๐:
This is about measuring how well the search algorithm finds the closest matches to a query. The main question is: When do mistakes from the approximate search start affecting the overall search results?
You can only improve what you measure.
But how do you measure the performance of a RAG pipeline?
To best identify areas of improvement, it is beneficial to evaluate your RAG pipeline component-wise ๐ฝ
Read more on our blog: https://weaviate.io/blog/rag-evaluation
Read more on our blog: weaviate.io/blog/openais-matryoshka-...
Or check out this video: https://www.youtube.com/watch?v=ZvnKlUtMOkQ
With this training procedure, the first dimensions (8, 16, 32, etc.) end up storing much more information than the later dimensions. This means that MRL can be used as a compression mechanism by shortening the embeddings by removing dimensions from the end of the sequence.
If we call a normal training loss functionย L, the MRL loss function would just be something like: Loss_Total = L(upto 8d) + L(upto 16d) + L(upto 32d) + ... + L(upto 2048d), because of the sum over all nested vectors.
Matryoshka Representation Learning (MRL) is a hierarchical representation learning technique that allows for flexible dimensionality in vector representations by making a key change to the loss function.
Happy New Year from everyone here at Weaviate! ๐
Thank you all for another year full of innovation, community, and great memories. We appreciate each and every one of you, and cannot wait to see what is in store for 2025!
Cheers to another trip around the sun!! ๐๐ฅ
The top Weaviate video of 2024 was.. ๐ฅ
Open Source RAG with Ollama!
Since the video was published, our open source RAG demo, Verba, has had even more updates, features, and tutorials published. You can try it out here: https://verba.weaviate.io
Video: https://www.youtube.com/watch?v=swKKRdLBhas
What does the future of AI look like in 2025?
We canโt wait to find out! Attendees of the Berlin AI Hack Night gave some insightful responses on how they think AI will improve in 2025, and what excites them most about it.
Join our upcoming events here: https://lu.ma/weaviatecommunityevents
Learn how you can use Weaviate and all of these technologies in our Integration Ecosystem page:
https://buff.ly/4fFzAgF
Check out Recipes, our repository where we share end-to-end notebooks on building applications ranging from RAG to Agentic RAG:
https://buff.ly/41Q8uQN
What a year it has been for Weaviate and the AI ecosystem!
Building AI-Native applications requires a variety of tools. Weโve clustered our technology partners into six categories:
1. Cloud hyperscalers
2. Model providers
3. Data platforms
4. Compute infrastructure
5. LLM frameworks
6. Operations
2024 was a massive year for Weaviate and the AI community! ๐
Our global roadshow showcased real-world applications of vector databases, driving innovation across industries.
Relive the action:
https://buff.ly/4gKsWaF
Thereโs more to come in 2025. Keep an eye out for Weaviate in a city near you!
โข What is Agentic RAG: https://buff.ly/3UBxmYf
โข Verba: https://buff.ly/3Td1SWC
โข Late Chunking: https://buff.ly/3zxEzB7
โข Advanced RAG Techniques: https://buff.ly/3ZIMPsg
โข Choosing the Best Embedding Model: https://buff.ly/3AbdV0R
โข Building a Local RAG System: https://buff.ly/3PalZmU
Looking for the most influential AI blogs from this year?
Here's our curated list ๐
(Save for later)
โ๏ธย Happy Holidays from Weaviate!
Whatever youโre celebrating, may it be filled with peace, joy (and maybe a little snow).
As we wrap up 2024, we want to thank our incredible Weaviate Community for making this year so special!
Join us on a journey through this year's highlights and discover why our community continues to inspire us every day.
Read more about the release on our blog: weaviate.io/blog
Try it on Weaviate Cloud: console.weaviate.cloud
Open Source Release: github.com/weaviate/wea...
More community โค๏ธ - Jun Ohtani contributed a Japanese BM25/Hybrid tokenizer to Weaviate!
Since 1.27.0, weโve also added:
โข Weaviate Embeddings - to make vector embedding generation even more seamless!
โข Support for Voyage AI's multimodal embeddings
Under the hood features: our async vector indexing has gotten even more robust and faster. For the adventurous, you can try out the experimental BlockMax WAND indexing for yourself.
The big highlight is our technical preview of ๐ฟ๐ผ๐น๐ฒ-๐ฏ๐ฎ๐๐ฒ๐ฑ ๐ฎ๐ฐ๐ฐ๐ฒ๐๐ ๐ฐ๐ผ๐ป๐๐ฟ๐ผ๐น. This gives you granular control over who can do what! Set permissions at collection, object, and cluster metadata levels with custom roles or use predefined roles.
