elasticmarx's profile picture.

Dimi Marx

@elasticmarx

Dimi Marx reposted

We've reimagined everything with Elastic Cloud Serverless – our fully managed, cloud-native solution. Find out why we built it, how the architecture was approached, and the lessons learned: go.es.io/402b6JJ

elastic's tweet image. We've reimagined everything with Elastic Cloud Serverless – our fully managed, cloud-native solution. Find out why we built it, how the architecture was approached, and the lessons learned: go.es.io/402b6JJ

Dimi Marx reposted

Learn how to use Attack Discovery and AI Assistant for Security to tackle complex threats in this 15-minute hands-on lab. Dive in → go.es.io/4kgPm4q


Dimi Marx reposted

Announcing GA of Elastic Observability LLM integration with @GoogleCloud Vertex AI! This integration provides users with deep insights into the usage, cost and operational performance of Vertex AI models. Read more: go.es.io/4lhcAZt #GoogleCloudNext #VertexAI


Dimi Marx reposted

Justin Trudeau lays out the facts about Russia’s invasions and how Putin cannot be trusted before saying he stands with President Zelenskyy and the people of Ukraine. Thankfully, he does not mention the disgusting display of Trump and Vance.


Dimi Marx reposted

Elasticsearch open inference API adds support for Google AI Studio! Developers can now use Elasticsearch to interact with data, quickly run experiments, and build applications using models available from Google AI Studio. Learn more: go.es.io/3BuQC2I

elastic.co

Elasticsearch open inference API for Google AI Studio - Elasticsearch Labs

Elasticsearch open inference API supports Google AI Studio. Learn how to create a Google AI Studio project, an Elasticsearch inference API endpoint and a chat app.


Dimi Marx reposted

The new LangGraph retrieval agent template from @LangChainAI and Elastic allows developers to build agentic apps with search quickly! Read more about it here: spr.ly/6013onXX7 #ElasticsearchLabs #GenerativeAI


Dimi Marx reposted

Elastic and @MistralAI collaborate to store and automatically chunk mistral-embed vectors into Elasticsearch! Learn more in this blog: go.es.io/3yqilR9 #ElasticSearchLabs #GenAI #VectorDatabase


Dimi Marx reposted

Explore how RAG and RBAC can team up to supercharge AI capabilities while ensuring your data stays under lock and key: go.es.io/4aSMS76 #ElasticSearchLabs #RAG #RBAC #GenAI


Dimi Marx reposted

Explore the simplification of kNN search! k and num_candidates are now optional. But, picking good default values for them was a tricky undertaking. This blog explains how we got there: go.es.io/3RfDBPT #ElasticSearchLabs #kNN

elastic.co

kNN search: Simplifying kNN search in Elasticsearch - Elasticsearch Labs

Elastic's kNN search has evolved. This blog explains the simplification of kNN search, where k and num_candidates are now optional.


Dimi Marx reposted

A Russian woman explains to her fellow Russians who they really are - in no uncertain terms - invaders, terrorists and murderers.


Dimi Marx reposted

Elastic’s Universal Profiling™ agent contribution has been accepted into the @opentelemetry project. Dive into this blog to find out how continuous profiling will impact #observability and help #SRE and developer teams around the globe: go.es.io/3KDSoQl


Dimi Marx reposted

Vector search goes beyond keywords to unlock the meaning behind search queries. Learn how it works and why it’s so critical to powering #AI search apps and #generativeAI experiences in this week's episode of Elastic Snackable Shorts. Watch more: go.es.io/3vafzhk


Dimi Marx reposted

Amazing progress on making Apache Lucene and Elasticsearch a great vector database

searching HNSW in parallel on #lucene 9.10 and then #elasticsearch got a great speedup for all your (dense) vector fields: github.com/apache/lucene/… merging to a single segment will still be faster but the difference is getting much smaller. moar smart optimizations :)

xeraa's tweet image. searching HNSW in parallel on #lucene 9.10 and then #elasticsearch got a great speedup for all your (dense) vector fields: github.com/apache/lucene/…
merging to a single segment will still be faster but the difference is getting much smaller. moar smart optimizations :)


Dimi Marx reposted

**scalar quantization of vectors**: sounds complicated but the idea is simple — reduce the granularity for each dimension from float32 to int8 (so 1 byte instead of 4). while you could always do that yourself, #elasticsearch 8.12's new int8_hnsw index option type does it for you

xeraa's tweet image. **scalar quantization of vectors**: sounds complicated but the idea is simple — reduce the granularity for each dimension from float32 to int8 (so 1 byte instead of 4). while you could always do that yourself, #elasticsearch 8.12's new int8_hnsw index option type does it for you

Dimi Marx reposted

Maximum-inner-product support in Apache Lucene is now available! This paves the way for support for many popular models in Elasticsearch. Read this blog for why (and how) we did it: go.es.io/3R1cd7h #ElasticSearchLabs

elastic.co

Bringing maximum-inner-product into Lucene - Elasticsearch Labs

Explore how we brought maximum-inner-product into Lucene and the investigations undertaken to ensure its support.


Dimi Marx reposted

Thank you to all who attended #ElasticON AI in San Francisco! We had a sold out event with incredible speakers from @huggingface @Cisco @Microsoft @LangChainAI @cohere. If you missed our livestream you can still rewatch the keynotes here: go.es.io/3ru0vcz

elastic's tweet image. Thank you to all who attended #ElasticON AI in San Francisco! We had a sold out event with incredible speakers from @huggingface @Cisco @Microsoft @LangChainAI @cohere.

If you missed our livestream you can still rewatch the keynotes here: go.es.io/3ru0vcz
elastic's tweet image. Thank you to all who attended #ElasticON AI in San Francisco! We had a sold out event with incredible speakers from @huggingface @Cisco @Microsoft @LangChainAI @cohere.

If you missed our livestream you can still rewatch the keynotes here: go.es.io/3ru0vcz
elastic's tweet image. Thank you to all who attended #ElasticON AI in San Francisco! We had a sold out event with incredible speakers from @huggingface @Cisco @Microsoft @LangChainAI @cohere.

If you missed our livestream you can still rewatch the keynotes here: go.es.io/3ru0vcz

Dimi Marx reposted

Elastic unveils the @Elasticsearch Relevance Engine (ESRE), which integrates #AI and #vectorsearch to improve #search relevance and support #generativeAI initiatives. venturebeat.com/ai/elasticsear…


Loading...

Something went wrong.


Something went wrong.