Google Research เปิดตัว TurboQuant อัลกอริทึมบีบอัดเวกเตอร์ ลดขนาดข้อมูล
#ShoperGamer #Google #GoogleResearch #Algorithm #TurboQuant #VectorDB #Feed
Latest posts tagged with #vectorDB on Bluesky
Google Research เปิดตัว TurboQuant อัลกอริทึมบีบอัดเวกเตอร์ ลดขนาดข้อมูล
#ShoperGamer #Google #GoogleResearch #Algorithm #TurboQuant #VectorDB #Feed
PageIndex: not a #VectorDB replacement 📑
Best for hierarchical Table of Content indexing at ingestion
#RAG pattern:
1️⃣ VectorDB → find chunks
2️⃣ Load page
3️⃣ PageIndex → remove unrelated sections
🐍 Python
📜 MIT #OpenSource
#AI #LLM Repost 🔁
🔗 Link in first 💬⤵️
#ChromaDB Context-1: Fast 20B model.
Small Specialized Language Model for fast #agentic search trained to retrieve supporting documents for complex, multi-hop queries. X10 faster than #LLM
#VectorDB #RAG #SLM #Agents
#OpenSource Apache 2.0 lic
github.com/chroma-core/...
@opensearch.org was named a Leader and Fast Mover in the 2025 GigaOm Radar for Vector Databases 🏆
My #OpenSearch report highlights:
✅ Platform play
✅ Search variety
✅ Business criteria
✅ Security
And I'd add - it's OPEN SOURCE @linuxfoundation.org!!
opensearch.org/gigaom-radar...
#gigaom #vectorDB
ICYMI, #OpenSearch 3.5 is here! 🤩
I shared some of my personal highlights in this short clip.
Hope you enjoy the format 👍
#OpenSearchAmbassador @opensearch.org @linuxfoundation.org #observability #analytics #search #vectorDB #kubecon #kubeconEU #o11yDay
My talk from #NDCLondon is now available on YouTube! 🇬🇧
youtube.com/watch?v=N2kn4UybFBI&list=PLPFMHjhoDntsPHFHTN1d4H-U3G8zRlJ-p&index=1&t=9s
@ndcconferences.com @opensearch.org @linuxfoundation.org
#vectorDB #OpenSearch #opensource #search #GenAI #OpenSearchAmbassador
310% throughput increase and 300% latency reduction!
Great work by the AWS #opensearch engineers with bulk SIMD brings these performance gains in @opensearch.org 's vector search 👏
And it's all #opensource under @linuxfoundation.org 🤩
opensearch.org/blog/acceler...
#vectorDB #OpenSearchAmbassador
Google just open‑sourced its Always On Memory Agent—think SQLite powering LLM retrieval instead of a heavy vector DB. Curious how this lean stack changes AI memory? Dive in! #AlwaysOnMemoryAgent #SQLite #VectorDB
🔗 aidailypost.com/news/google-...
Rust-powered vector database that handles billions of embeddings with millisecond search times - the
Rust-powered vector database that handles billions of embeddings with millisecond search times - the infrastructure backbone for modern AI applications that actually need to scale
https://github.com/qdrant/qdrant
#VectorDB #Rust #AIInfrastructure
🚀 Build a RAG server with ollama, Open WebUI and Chroma DB!
Learn to create a headless LLM server that handles document ingestion, vector storage, and intelligent retrieval.
medium.com/@chribonn/ho...
#RAG #ollama #AI #MachineLearning #Python #LLM #VectorDB #DeveloperTools #TTMO
Can't wait to to have a great ride at #JavaLand! 🇩🇪
#OpenSearch sucht nicht mehr nach Wörtern, sondern nach Bedeutungen. 🔍
Join me to learn about #vectorDB search and about the @opensearch.org #opensource Project
See you 11 March @javaland.bsky.social 🎡
👉 meine.doag.org/events/javal...
IBM Docling: turn complex docs into structured data for #RAG & #AI pipelines. Keep tables, lists & layout intact. Feed #LangChain & #LangGraph easily. ⚡📝
#AI #DocumentUnderstanding #OpenSource #VectorDB
Lightning-fast search engine in Rust that makes Elasticsearch look bloated - typo tolerance, AI-powe
Lightning-fast search engine in Rust that makes Elasticsearch look bloated - typo tolerance, AI-powered hybrid search, and vector similarity out of the box with zero configuration.
https://github.com/meilisearch/meilisearch
#Rust #SearchEngine #VectorDB
🌲 Pinecone Serverless réinvente la mémoire IA.
Votre infrastructure vectorielle est-elle prête à passer à l'échelle sans vous ruiner ?
#KingLand #IA #Pinecone #Serverless #RAG #TechTrends #Cloud #Data #VectorDB #Innovation
✨ Fiche Impact :…
MemMachine: long-term #Memory for #AI #Agents 🧠💾
#Graph + vector search → durable context across runs
🧩 Sessions 🗂️ History 👤 Profiles 🔌 APIs
📜 Apache 2.0 lic #OpenSource
#LLM #RAG #GraphRAG #VectorDB Repost 🔁
🔗 Link in first 💬⤵️
I joined InstaBlinks podcast to talk about vector search, difference from lexical search, and how the #OpenSearch Project facilitates both in a hybrid model.
Thanks NetApp Instacluster for having me!
www.youtube.com/watch?v=buKX...
@opensearch.org #vectorSearch #vectorDB #opensource #search
Getting ready to take the stage at @ndcconferences.com London. See you at room 6!
#NDCLondon #VectorDB #VectorSearch #OpenSearch #AI @opensearch.org #OpenSearchAmbassador
2/8 🔍 Vector Databases Evolving: Scalability skyrockets, multimodal support added. Pinecone & Weaviate powering smarter AI apps like search & recs. The AI infra game-changer. #VectorDB
See you in a few days at NDC Conferences London! 🇬🇧
I'll give a talk about Vector Search Made Simple and how the #OpenSearch Project can help you, a-la #OpenSource!
See you 30 January @ndcconferences.com 💂
ndclondon.com/agenda/vecto...
#NDClondon #vectorDB @opensearch.org #opensearchambassador
Imagine NFL‑level AI and Olympic‑scale analytics running on rock‑solid data, not just slick prompts. The secret? A data‑quality creed. Dive into why vector DBs, streaming architecture, and defensive engineering matter. #DataQuality #VectorDB #SportsAnalytics
🔗 aidailypost.com/news/ai-nfl-...
If you’re building AI apps and still sleeping on Chroma 1.0, you’re missing out on an open source vector DB that makes retrieval and semantic search feel effortless.
Learn concepts, use cases, and why devs love it on techglimmer.
🔗 techglimmer.io/what-is-chro...
#Chroma #VectorDB #AI #RAG #trychroma
Not all vector databases are created equal.
With OpenSearch, you get:
🤝 Open source flexibility
⚡ Memory-efficient ANN search at scale
📈 Built-in scalability for real-world workloads
Search smarter with a platform designed for developers.
👉 opensearch.org/platform/vec...
#OpenSearch #VectorDB
NDC London is taking place in 2 weeks! 🇬🇧
I'll give a talk about Vector Search Made Simple and how the #OpenSearch Project can help you, a-la open source!
See you end of January in London 💂
ndclondon.com/agenda/vecto...
#NDClondon #vectorDB @opensearch.org #opensource
NAGS-4: #GrapRAG with #KnowledgeGraph framework with build-in #VectorDB & #GraphDB implemented in Rust.
MIT lic
#OpenSource #RAG #AI #LLM
github.com/YASSERRMD/na...
just pushed a new @nextjs.org starter that builds on the Vercel AI chatbot template with Orchata already integrated. If you're building on RAG, give it a whirl and lemme know what you think 🥛
github.com/orchata-ai/orchata-nextjs-starter
#ai #rag #vectordb #startup #nextjs #vercel #devtools
One month to NDC London! 🇬🇧
I'll give a talk about Vector Search Made Simple and how the #OpenSearch Project can help you, a-la open source!
See you last week of January in London 💂♂️
ndclondon.com/agenda/vecto...
#ndclondon @opensearch.org #opensource #london #vectorDB #search #searchEngine
How Different Databases Store and Retrieve Data
open.substack.com/pub/engineer...
#vectordb #dataengineering #databases
www.tuned.org.uk/posts/010_ga...
#LLM #vectorDB #opensource
Generating some serious signal at #SC25! Building Huge, Affordable Vector Databases -- pliops.com/achieving-hu...
#AI #LightningAI #VectorSearch #LLMinference #VectorDB #AIInfrastructure #Pliops
Wondering how it performs in real-world scenarios? Explore how OpenSearch vector search efficiently handles large-scale queries with impressive speed and accuracy.
See it in action.
👉 opensearch.org/platform/vec...
#OpenSearch #VectorDB #Search