vespa.ai
@vespaengine
Followers
3K
Following
754
Media
27
Statuses
501
https://t.co/abkb8IjPSH - the open source platform for combining data and AI, online. Vectors/tensors, full-text, structured data; ML model inference at scale.
Joined September 2017
The Singaporean government has deployed Vespa to search every word ever said in their Parliament. "A good decision is an informed one [. ] The heart of a good RAG system is a good search engine to retrieve the relevant data chunks for ingestion".Many teams are racing to make use
2
15
87
We have become our own company!.Expect even more features, even faster.
4
14
64
Announcing the open sourcing of Vespa, Yahooโs Big Data Processing and Serving Engine at
3
61
57
Announcing our $31 million raise from Blossom Capital We'll spend it all on features.
1
6
46
Spotify launches semantic search in Podcasts, powered by
Hereโs the problem: you want to search for a podcast, but you canโt remember the name, only what itโs about.๐ Here comes Natural Search ๐ to save the day! .
0
5
43
LangChain Webinar on retrieval for LLMs with @lateinteraction and our very own @jobergum in six hours. Save your spot at
1
6
31
Choosing an algorithm for fast vector search for big data serving. Read if you are interested in combining fast vector search with filters, text, and real-time updates. Or in how professionals choose algorithms from the literature for production usage.
0
12
30
Having trouble keeping up? . Guidebook to the State-of-the-Art Embeddings and Information Retrieval .by @aapo_tanskanen at @thoughworks is out today - a great resource to get up to date.
0
9
26
Search is going through a paradigm shift -.neural methods are outperforming traditional methods by a wide margin. Can you use it real production systems?.[1/4]
1
8
26
What the world need most now is more research on #covid19, faster. We've created to help with that. It lets researchers find research papers by combining text and structured search with exploring by semantic similarity using the scibert-nli model.
The @vespaengine team released based on the CORD-19 dataset released by the @allen_ai. Since everything is open-sourced, you can contribute to the project in multiple ways. ๐. #NLP #NLProc #SearchEngine #COVIDใผ19.
0
14
26
Do you want to work on .- search relevance .- recommendation.- personalization . using .- machine-learning.- embeddings .- vector or hybrid retrieval . but are kinda tired of all the plumbing?. Thread time ๐.
2
7
24
After extensive benchmarking, Marqo migrated their underlying engine from OpenSearch to Vespa: . "For Marqo 2, we looked at a number of open source and proprietary vector databases, including Milvus, Vespa, OpenSearch (AWS managed), Weaviate, Redis, and Qdrant.".
1
1
24
We made it simpler to create semantic search applications on Vespa.- No need to create vectors yourself.- No code needed.- No limits, once you want to grow add features.
3
2
24
We're starting a new series of posts where we provide a complete and scalable Vespa application with a frontend for a popular use case. First out: Shopping sites! .
0
8
19
Follow this guide if you need to build a personal data app which .- costs about 5% of a traditional vector database.- contrary to those, finds all the user's data.- scales to millions (or billions) of users.
Hands-on RAG guide for personal data with @vespaengine and @llama_index ๐ . Featuring LLamaIndex retrievers, Vespa streaming mode for personal data, built-in embedders, multi-index RAG (federation + blend), hybrid search, and rank fusion strategies.
1
4
19
Releasing support for ONNX models (Caffe2, PyTorch). All the same optimizations making it fast as TensorFlow models since we compile into the same execution engine
0
9
19
Announcing support for Maximum Inner Product Search (MIPS) in Vespa. โ
Search efficiently for vectors with the highest dot product, by an innovative extension to HNSW indexes. โ
With full realtime indexing, and no need to normalize vectors.
0
4
19
Announcing approximate nearest neighbor vector search in Vespa - State of the art performance from a native Vespa implementation of HNSW.- Vector search combines efficiently with filters and text search.- Infinitely scalable.- Real-time updates of vectors.
0
12
19
Things we've been up to in May:. ๐LLM integration: Build complete RAG applications on Vespa. ๐ฐEmbed to multiple representations at once: An oom cheaper vector search by creating a small vector for search and a larger for ranking. ๐ฏCombine fuzzy search and prefix match: Ideal.
1
3
18
Recommender systems need to multiply very large sparse matrices. e-commerce platform @farfetch leverages Vespa's support for sparse and dense tensors + vector search to do this online in less then 100 milliseconds. ๐งต.
1
1
19
Have you ever had to index trillions of documents in your vector database?. This is the problem Yahoo Mail is facing, and believe us it can get expensive. Luckily this is personal data, so it's possible to use Vespa's Vector Streaming Search which makes the problem tractable.
1
2
16
The latest Vespa newsletter is here to help you stay up to date on what's happening on the leading edge in RAG, IR and vector search:.- A new SPLADE embedder.- ONNX models with float16.- @cohere embedding model guides.- Support for an array of chunks with ColBERT.- And list of.
0
3
18
Very informative post on choosing Vespa for personalization using vector embeddings
Blog post on how โฆโฆ@vintedโฉ started using โฆ@vespaengineโฉ for recommendations
2
5
15
Seems everybody is migrating their search and recommendation systems from Elastic to Vespa now. Here's the experience of Stanby, Japan's leading job search site:
0
5
15
When you are doing nearest neighbor vector retrieval you are doing *search*, which is computation over data. The llm builders community is currently speedrunning the process of discovering what this takes. If you are reading this, congrats you're likely ahead of the curve :-).
Vector databases are not search engines. Reasoning over metadata is easily achievable with COT + @elastic , @vespaengine , or other search engines.
0
0
15
Vector databases are not suited for personal data: You need complete results and much lower cost. We're announcing vector streaming search to solve this problem: Fully production ready, and open source, of course.
1
5
16
Benchmark results! Scaling TensorFlow model evaluation with Vespa
0
14
15
New blog post: Creating a state of the art question-answering system using
1
12
16
Startups running on Vespa Cloud raised more than $750M during 2024.
1
1
14
What we have been up to in the Vespa HQ in August:. ๐๏ธ 30x faster MaxSim with Hamming distance for multivector documents. ๐งโ๐ปIDE support for VSCode, IntelliJ, PyCharm, WebStorm and neovim. ๐Even more pyVespa improvements.
0
1
14
Vector search is more than ranking by nearest neighbor. Run efficient transformer-based embedding retrieval on your laptop ๐ป.
0
2
14
A good writeup on building a search product end to end "[Vespa] is *the* search engine to use on mutable data sets with modern ranking methods".
0
4
14
Frozen embeddings ๐ฅถ. A guest post on the Vespa blog by Andrii Yurkiv.
1
3
14
New blog post! . Joining real-time click data and content at query time without impacting performance. Impossible? Not with
0
2
14
Vespa continues to empower developers who are building something real with vector embeddings. No custom code required to.- use any embedding model from @huggingface.- do multilingual embedding.- run embedders on GPUs.
1
0
13
Is it possible to do distributed joins in real time without sacrificing performance? It depends - is your use case of the parent-child type, and do you run the latest Vespa?
0
8
11
What we've been up to during summer at the hq. - A multi-lingual embedding sample app using E5.- to_epoch_second in the indexing language.- New pyvespa and Vespa CLI features.- ML model persistence across deployments.- and more.
0
4
13
Announcing support for ANN with multiple vectors per document in
1
1
11
Can machines reliably answer questions in natural language?. It turns out they can, and the best methods from research are public. Seems like a game-changer, so why isn't this more widespread?
1
7
13
How and why Zedge migrated their autosuggest, search and recommendation to Vespa
0
4
12
Why you can't conclude a machine-learned model will scale in production just because it is fast
1
4
12
DONE from our โ๏ธsummerโ๏ธ todo list :.- pyVespa deploy_to_prod. - vespa log CLI command also for self-hosted. - Faster multithreaded hybrid queries. - rank-score-drop-limit in second phase. - Chinese segmentation. and 14 more, covered in our August issue.
2
4
12
Tempted to use a database for your vectors? .Consider why you are using vectors in the first place.
0
3
12
The December Vespa newsletter is out:.- Global-phase ranking with normalizing functions.- Take the Vespa open source survey.- Token access on Vespa Cloud.- Get indexed tokens in results.- and much more.
0
1
12
Vespa improvements released in February: Support for LightGBM machine-learned models, improved matrix multiplication performance, benchmarking guide, a fluent query builder API, and Hadoop integration improvements.
0
6
12
Vespa improvements from January Among other things this includes new tensor functions needed to run BERT models. All of it already released and running in production of course.
1
7
12
Highlights of Vespa features released in June:. - Personal vector search with complete results, at 1/20 of the cost, with streaming.- MIPS/dot product ranking in ANN.- GPU Acceleration of embedding models.- Use any @huggingface embedder directly.
0
4
12
Everybody knows that AI builds on tensors now, but when we started work on them in 2013 it was just a weird thing.
1
3
12
If you are looking for a comparison of Elasticsearch, Solr, and Vespa this is the video to watch.
Find out how our invited speakers compared #Elasticsearch #Solr and @vespaengine at the Haystack LIVE! Meetup - video now available at - thanks so much @anshumgupta @jobergum @joshdevins !.
0
2
11
If you are using vector embeddings, reading this post might be the most profitable ten minutes you'll ever spend.
Matryoshka ๐ค Binary vectors: Slash vector search costs with Vespa. We announce support for combining matryoshka and binary quantization in Vespaโs native hugging-face embedder and discuss how this slashes vector search costs.
0
1
10
Implementing reinforcement learning in production with open source: New Vespa blog post
0
9
11
Gigaom published their Sonar for Vector Databases today, positioning Vespa as a leader. While what we are - and what you need - is much more than a vector database, it is gratifying to be recognized as a leader also on these core features alone.
1
2
11
Finally it is possible to create search systems that can see: Drop document text extraction and let your system see text, figures and layout directly.
0
2
11
It's been a good summer for coding in the north ๐ง๏ธ๐ง๏ธ. We got some new features in Vespa released: BM25 ranking feature, searchable parents, tensor summary features and metric export.
0
4
11
It turns out that when you open source 1.7M lines of code in 150 flat modules people will keep asking for directions. Today we're publishing a map to the code base.
0
3
11
April @vespaengine updates include performance and operability improvements: Top-K hits, smarter data migration and CloudWatch integration. Contributing to Vespa is now easier with the release of a CentOS 7 dev environment. #bigdata.
0
6
11
When GigaOm named Vespa Leader in their Sonar for Vector Databases, one of the categories where we scored Excellent were Embedding Flexibility - why? . Vespa lets you create embeddings in four ways:. - On your own, outside Vespa: Just pass tensors directly in documents and.
1
2
11
๐ฅNew blog post: Improving Zero-Shot Ranking with Vespa Hybrid Search.
1
0
9
When you're working with vectors you're doing search - and you'll need all the features of a search engine. A new blog post which explains why we're no fans of the term 'vector database'.
0
2
10
Semantic search with multiple languages is finally clearing the bar for production. Vespa makes it easy to stand up your own.
0
2
9
We're submitting some Vespa examples to relevance competitions. All of them:.- available as open source sample applications.- production ready, with < 100 ms latency. This first one is a simple WAND+GDBT baseline, beating all the other entries not using deep learning/embeddings.
Welcome @jobergum and @vespaengine to the fray with their first @MSMarcoAI document leaderboard submission! Awesome to see LTR effectiveness creeping up on the muppets.
1
3
10
How would you implement the next Gmail efficiently in open source? New Vespa blog post
0
7
9
Did you know you can now convert text to vector embeddings in documents and queries automatically in Vespa? We provide the wonderful SentencePiece algorithm by Taku@Google for this, but you can also plug in your own.
0
2
10
And how to use a BERT-style transformer model for final ranking while staying within your latency budget
0
2
10
Finally, for all the Elastic developers out there who want to start creating modern search base applications, @atitaarora on understanding Vespa with a Lucene mindset
0
3
9
For those who are running Vespa, information about HTTP/2 Rapid Reset (CVE-2023-44487).
0
1
9
Testing ANN performance on Search a million vectors in 2 ms measured from the client.
From our performance factory page at @vespaengine HQ where we test Vespa performance for every build. This is testing Vespa's approximate nearest neighbor search on SIFT 1M This is an end to end benchmark including HTTP API. Pretty awesome if you ask me.
0
3
9
ColBERT v2 is the state of the art in information retrieval, and with this work you can actually run it economically, at any scale.
Announcing ColBERT in @vespaengine, enjoy!. - A new native Vespa ColBERT v2 embedder.- ColBERT token-level vector compression (32x).- Support for long context via Vespa mixed tensors.- Offload to disk .- Eval. Plus, it boasts the largest FAQ ever!๐
.
0
0
9
October news from ๐. ๐ค๏ธ Enclave: Bring your own cloud to Vespa Cloud, on both AWS and GCP. ๐๏ธMUCH faster fuzzy matching. ๐Lucene linguistics integration. and much more obviously:
0
3
9
This lets you combine vector search with filters and text while staying efficient, and scale to real data sizes with low latency. This is what's needed for production and what can't be achieved by integrating specialist tools for these problems. [3/4].
1
0
8
If you're in Bay Area come meet us at September 26. in San Francisco Thanks to @Amplitude_HQ for hosting!.
0
5
9
If you have it's not too late to make yourself a state of the art and infinitely scalable e-commerce site in time for Black Friday. @jobergum explains how in
0
9
9
For more on how to use reinforcement learning for recommendation see
A breath of fresh air: @vespaengine at #HaystackConf, signal to noise is through the roof! Reinforcement learning for comment ranking.
0
6
6
Announcing a new IN operator in Vespa: .select * from product where id in (10, 20, 30). - Simpler than using a WeightedSet.- Over 10x faster with large thousands of query values.
1
0
8
ANN lets us apply AI in ways that weren't possible before. But to use it in the real world you need a few more things.
0
1
8
Shipped from the Vespa HQ in ๐ October:. - Index tensors with multiple sparse dimensions: tensor(page{}, section{}, chunk{}, x[16]).- Global significance ("tf") models- Metric dashboards in the Vespa Cloud Console.- Even more new PyVespa features. Read the details in our latest.
0
1
7
Want to run on your m1 Mac, on ARM64 nodes in your data centers, or on Vespa Cloud?. We got you! All Vespa images are now multi-architecture.
0
2
7
Scalable realtime blog recommendation using neural nets.Part 3 of 3 of a series showing in detail how to build a big data serving application using Vespa.
0
6
8
An open source sample application for searching images by describing them, based on CLIP
0
3
7
We also provide the same for *your* applications when running on Vespa Cloud.
@vespaengine has one of the best FOSS ci/cd set up I have seen out there. Pretty much everything is automated. This encourages contributors like me to contribute even more because the changes are so instant on prod.
0
0
7
Danswer (YC W24) on why they moved their RAG solution to Vespa. We hear this in so many private conversations right now.
@DanswerAI has been using @vespaengine as our search engine for a long time. In this blog, I outline the key benefits of using Vespa. Thanks @jonbratseth, @kraune and @jobergum for keeping Vespa open source and helping our users with Vespa questions!.
0
0
7
For those who want to contribute to this will be an easy way to get started.
Join us March 21 - 28, for Yahoo Hack Together, a virtual #opensource #hackathon! Learn more & register: #bigdata #design #devops #networksecurity
0
3
7
@farfetch The full post includes a detailed description of how to implement a scalable and low latency recommender system:
0
0
7
Vespa product updates for December:. - 10-150x speedup of computations with sparse tensor dimensions.- ZooKeeper distributed locking available in containers.- PyVespa for machine learning.- ONNX runtime integration.
0
2
7
๐
The official 2024 Advent of Tensors ๐
. Follow this thread to get a challenge a day, win swag and become a tensor computation expert along the way.
Prepare to embark on a festive journey as we bring you the Advent of Tensors with 24 challenges and the chance to win @vespaengine swag! .
0
3
7
This is an unusually good comparison, although it leaves out what we see as most important: Ranking and inference capabilities. It can be solved elsewhere, but only if you don't need to perform at scale . .
Found this comprehensive spreadsheet on the key features of popular Vector Databases used to build out AI chatbot solutions. Spreadsheet: Key takeaways:. - The most well-rounded solutions include @weaviate_io, @vespaengine, and @elastic. - The top
0
0
7