@OpenSearchProj was named a Leader and Fast Mover in the 2025 GigaOm Radar for Vector Databases ๐Ÿ†

My #OpenSearch report highlights:
โœ… Platform play
โœ… Search variety
โœ… Business criteria
โœ… Security
And I'd add - it's OPEN SOURCE @linuxfoundation !!
https://opensearch.org/gigaom-radar-vector-report-2025/

#gigaom #vectorDB

ICYMI, #OpenSearch 3.5 is here! ๐Ÿคฉ
I shared some of my personal highlights in this short clip.
Hope you enjoy the format ๐Ÿ‘
#OpenSearchAmbassador @OpenSearchProject @linuxfoundation #observability #analytics #search #vectorDB #kubecon #kubeconEU #o11yDay
Vector Search Made Simple: Getting Started with OpenSearch for AI Applications - Dotan Horovits

YouTube

Stoked seeing the OpenSearch Project featured by Jensen Huang on #NVIDIA #GTC keynote! ๐Ÿ˜

One of the innovations in #OpenSearch V3 has been adding GPU acceleration based on NVIDIA's cuVS. Our #VectorSearch benchmarks, using CAGRA algorithm integrated through Facebook's Faiss library, showed:
โœ… 9.3x faster index builds
โœ… 3.75x lower cost
โœ… 2x higher throughput
โœ… 2.5x lower CPU usage

https://www.linkedin.com/feed/update/urn:li:activity:7439600547852189697/

#OpenSearchAmbassador #opensource #gtc2026 #gtc26 #cuvs #vectordb

#gtc #opensearch #nvidia #opensource #opensearchambassador #vectorsearch | Dotan Horovits

Stoked seeing the OpenSearch Project featured by Jensen Huang on NVIDIA #GTC keynote! ๐Ÿ˜ One of the innovations in #OpenSearch V3 has been adding GPU acceleration based on #NVIDIA's cuVS. Our benchmarks, using CAGRA algorithm integrated through Facebook's Faiss library, showed: โœ… 9.3x faster index builds โœ… 3.75x lower cost โœ… 2x higher throughput โœ… 2.5x lower CPU usage That's the power of bringing the best of #opensource in vector search together. Check out the comments for the full benchmark setup and results, and more details on the architecture, as well as the RFC on GitHub. Well done to Navneet Verma Corey Nolet Kshitiz G. Dylan Tong Nathan Stephens Vamshi Vijay Nakkirtha and all involved! #OpenSearchAmbassador #VectorSearch

LinkedIn
310% throughput increase and 300% latency reduction!
Great work by the AWS #opensearch engineers with bulk SIMD brings these performance gains in @OpenSearchProject 's vector search ๐Ÿ‘
And it's all #opensource under @linuxfoundation ๐Ÿคฉ
https://opensearch.org/blog/accelerating-fp16-vector-search-performance-using-bulk-simd-in-opensearch-3-5/
#vectorDB #search #OpenSearchAmbassador

Chunking: an essential concept to understand for Retrieval-Augmented Generation (#RAG). It is the process of dividing large documents into smaller, manageable segments called โ€œchunks.โ€ Effective chunking preserves semantic meaning while ensuring content fits within model context limits.

Proper chunking is essential, as it directly affects retrieval quality. Well-structured chunks improve precision and support more accurate responses.

โ€จโ€จ#OpenSource #devops #vectordb #programming #vector #search

Can't wait to to have a great ride at #JavaLand ! ๐Ÿ‡ฉ๐Ÿ‡ช

#OpenSearch sucht nicht mehr nach Wรถrtern, sondern nach Bedeutungen. ๐Ÿ”

If you're there and want to learn about #vectorDB search and about the @OpenSearchProject, check out my talk ๐Ÿ™‚

See you 11th March in @JavaLandConf ๐ŸŽก

๐Ÿ”ธAgenda: https://meine.doag.org/events/javaland/2026/agenda/#agendaId.6918

๐Ÿ”ธTickets: https://www.javaland.eu/

Exploring IBM Docling: the new open-source toolkit for turning complex documents into structured data ready for #RAG and AI workflows. ๐Ÿ“โšก
Forget messy OCRโ€”preserve tables, lists, formulas & layout, feeding #LangChain, #LangGraph, and other vector pipelines.
#AI #DocumentUnderstanding #OpenSource #VectorDB #DataEngineering #MachineLearning #LLM

Abhishek Yadav (@abhishek__AI)

์•Œ๋ฆฌ๋ฐ”๋ฐ”(Alibaba)๊ฐ€ ๋ฐœํ‘œํ•œ Zvec๋ผ๋Š” ์ž„๋ฒ ๋””๋“œ ๋ฒกํ„ฐ DB ์†Œ๊ฐœ ํŠธ์œ—์ž…๋‹ˆ๋‹ค. ์„œ๋ฒ„ ๋ฐฐํฌ ๋ถˆํ•„์š”, ์ˆ˜์‹ญ์–ต ๋ฒกํ„ฐ๋ฅผ ๋ฐ€๋ฆฌ์ดˆ ๋‹จ์œ„๋กœ ์ฒ˜๋ฆฌ, dense/sparse/hybrid ์ง€์›, ๋…ธํŠธ๋ถยท์„œ๋ฒ„ยท์—ฃ์ง€์—์„œ ์‹คํ–‰ ๊ฐ€๋Šฅํ•˜๊ณ  RAG(๊ฒ€์ƒ‰ ๊ธฐ๋ฐ˜ ์ƒ์„ฑ) ์šด์˜์— ์ ํ•ฉํ•˜๋ฉฐ 100% ์˜คํ”ˆ์†Œ์Šค๋กœ ์ œ๊ณต๋œ๋‹ค๊ณ  ์„ค๋ช…ํ•ฉ๋‹ˆ๋‹ค.

https://x.com/abhishek__AI/status/2023237938864381970

#zvec #vectordb #rag #opensource

Abhishek Yadav (@abhishek__AI) on X

This might be the cleanest way to ship RAG in production Zvec by alibaba, a lightning fast embedded Vector DB that runs wherever your code runs. โ†’ No server deployment โ†’ Billions of vectors in ms โ†’ Dense + sparse + hybrid โ†’ Runs on laptop, server, edge 100% Open source ๐Ÿ‘‡

X (formerly Twitter)

Unwind AI (@unwind_ai_)

์ค‘๊ตญ์˜ ์•Œ๋ฆฌ๋ฐ”๋ฐ”๊ฐ€ ๋ฒกํ„ฐ ๋ฐ์ดํ„ฐ๋ฒ ์ด์Šค์˜ 'SQLite'๋ผ๊ณ  ๋ถˆ๋ฆฐ zvec์„ ์˜คํ”ˆ์†Œ์Šค๋กœ ๊ณต๊ฐœํ–ˆ์Šต๋‹ˆ๋‹ค. zvec์€ ์•ฑ ๋‚ด๋ถ€์—์„œ ๋ผ์ด๋ธŒ๋Ÿฌ๋ฆฌ๋กœ ๋™์ž‘ํ•˜๋ฉฐ ์˜จ๋””๋ฐ”์ด์Šค RAG๋ฅผ ๋ชฉํ‘œ๋กœ ์™ธ๋ถ€ ์„œ๋ฒ„๋‚˜ PineconeยทQdrant ์ธ์Šคํ„ด์Šค ์—†์ด ์ž‘๋™ํ•˜๋„๋ก ์„ค๊ณ„๋˜์—ˆ๊ณ , 100% ์˜คํ”ˆ์†Œ์Šค์ž…๋‹ˆ๋‹ค.

https://x.com/unwind_ai_/status/2022923156185567458

#opensource #vectordb #rag #ondevice #alibaba

Unwind AI (@unwind_ai_) on X

China's Alibaba just opensourced the SQLite of vector databases. zvec runs as a library inside your app and is built for on-device RAG no external server. no pinecone. no qdrant instance. 100% opensource.

X (formerly Twitter)