#vectordb search results
Search is moving towards semantic understanding. With vector technology, OpenSearch is laying the foundation for AI-driven applications that truly ‘get’ user intent. 🚀 Be part of this journey: hubs.la/Q03RpF3D0 #OpenSearch #VectorDB #Search
🤔Is there a Vector DB where you can use plain SQL to: - Insert data - Create Index with embeddings - Query semantic search No ML knowledge needed! Just write SQL like: #Database #AI #VectorDB #SQL
That face when you realize you’ve been storing embeddings in CSVs instead of a vector DB. 🤦♂️ subscribe to our YouTube channel 👉 youtube.com/@neurlcreators for more bite-sized breakdowns. Pinecone, Weaviate, Qdrant, Milvus, Chroma = your upgrade path. #VectorDB #RAG #AIinfra
Today I learned Vector DB by @rohit_negi9 Unlike traditional DBs store text or nums, Vector DBs store embeddings — high-Dim vectors representing meaning. This enables semantic search, recommendations. Internally, they use like HNSW, IVF for ultra-fast matching #AI #VectorDB
Worried your #GenAI application will fail in production because your #vectordb may not be able to keep up? 🔥 #Redis8 just benchmarked: ◼️ 1 BILLION vectors (not a typo!) ◼️ 90% precision @ 200ms latency ◼️ 66K vectors/sec ingestion ➡️ Read more here: redis.io/blog/searching…
How to Modernizing your DB to Handle Massive & Streaming AI Data mltblog.com/3N1woAa #graphdb #vectordb #mariadb In this session, we will discuss the following, with an emphasis on AI applications: ➡️ Advanced features to optimize performance, security, and scalability.…
Vector databases are on the verge of irrelevance. Not because they’re bad tech — but because vector search **alone** solves almost nothing. The future isn’t “vector search.” It is “contextual retrieval”. #VectorDB #RAG #AI 🧵👇
I just created an in memory #VectorDB that runs completely in the browser🎉.. ... in less than 100 lines of JavaScript😎. It uses #TransformersJS and the all-MiniLM-L6-v2 model for the embeddings and runs a cosine similarity search for a given query.
🚀 WeChat (1.4B daily users!) using custom @ClickHouseDB for vector search Their modified version helps handle massive user scale 🌐 #WeChat #VectorDB #BigTech
Shape the future of #databases by participating in DZone's in-house research. Our goal is to uncover how developers, architects, and data leaders are adopting + modernizing databases 👇 survey.alchemer.com/s3/8483827/dzl… #sql #vectordb #postgresql
SQL = reliable. VectorDB = shiny. Both = the future. But which one do you trust?🤔 Vote here 👉 survey.alchemer.com/s3/8483827/dzx2 #Databases #SQL #VectorDB
.@JoshuaJerinn and Shahnawaz Mohammed are at @HyderabadPUG today - in fact, Shahnawaz just delivered his talk introducing Tembo Stacks and our #vectorDB capabilities. Make sure to meet them at the social tonight!
Vector databases are the backbone of modern AI. They power: 🔹 Semantic search 🔹 RAG (retrieval-augmented generation) 🔹 Embeddings for LLMs That’s why VectorDBs.com is a premium hub for the future of AI infrastructure. #AI #VectorDB #LLM #DomainsForSale
RAG in prod? Cool. 6 weeks later your recall tanks & the model hallucinates. 👻 Root cause = embedding drift; vectors move when you re-fine-tune, re-index or add new docs. Miss it & search ≠ semantics. 🧵👇 #RAG #VectorDB
Wikidata Vector Database to combat closed #AI systems, making #GenAI apps more reliable: wd-vectordb.wmcloud.org ... Learn more about it in this webinar: wikidata.org/wiki/Event:Emb… #VectorDB #RAG #Context #ML
🚀ObjectBox 4.0 brings vector search. We’re effectively releasing the very first on-device vector database today. Check it out 👉 objectbox.io/the-first-on-d… #mobiledev #ai #vectordb #RAG #android #database #edgeAI
Vector stores are now an api call. @OpenAI this was long due, the assistant api v2 🚀. #vectordb #api #openai
Search is moving towards semantic understanding. With vector technology, OpenSearch is laying the foundation for AI-driven applications that truly ‘get’ user intent. 🚀 Be part of this journey: hubs.la/Q03RpF3D0 #OpenSearch #VectorDB #Search
Secure vector databases are essential for RAG, providing the trusted foundation necessary for sensitive data handling. vektaris.com #VectorDB #RAG #Embeddings #DataSecurity #OnPremAI
Bigger isn't always better! Vektaris demonstrates that targeted retrieval can yield enterprise-level results without the complexity. vektaris.com #VectorDB #RAG #Embeddings #DataSecurity #OnPremAI
Vector DBs aren't dead; fast-forward to 2025, and yeah, the "grift" vibe faded as everyone from Postgres (pgvector 0.7's HNSW) to Supabase bolted on vectors like it was an afterthought. Who's stacking what for agentic memory in 2025 #VectorDB #RAGEngineering
Vector databases are on the verge of irrelevance. Not because they’re bad tech — but because vector search **alone** solves almost nothing. The future isn’t “vector search.” It is “contextual retrieval”. #VectorDB #RAG #AI 🧵👇
Did Supabase just add Vectors and Analytics to their Storage? Just noticed these new sections in the Storage UI. Anyone know when this shipped or who announced it? @supabase when did this drop? #Supabase #Database #VectorDB
This blog illustrates how to set up and interact with ChatPDFDoc on your local machine. A personal data answering RAG (Retrieval Augmented Generation) tool for chatting with your PDF documents. ayotomiwasalau.com/posts/chatpdfd… #LLM #RAG #VectorDB
Now I get why devs love open protocol software 😅 🚀 Built a Smart Customer Support Agent using NVIDIA Embeddings + Qdrant Vector DB 💻 github.com/Yash-Kavaiya/N… 🎯 devpost.com/software/ai-ag… #NVIDIA #AI #VectorDB #Qdrant #AWS #EKS #OpenSource #Hackathon #RetailAI
TL;DR: Stop managing indexes manually. Let Pinecone handle the infrastructure so you can build intelligent systems that actually ship. #AI #VectorDB #RAG #LLMs #MachineLearning #Engineering
Today I learned Vector DB by @rohit_negi9 Unlike traditional DBs store text or nums, Vector DBs store embeddings — high-Dim vectors representing meaning. This enables semantic search, recommendations. Internally, they use like HNSW, IVF for ultra-fast matching #AI #VectorDB
Struggling with compliance around data residency and PII? Vektaris offers a secure, scalable vector search that keeps your sensitive data safely within your perimeter. vektaris.com #VectorDB #RAG #Embeddings #DataSecurity #OnPremAI
🚀 CFP: LLM + Vector Data @ ICDE 2026 (Agentic RAG Edition) 📍 Montréal, May 4 🔗 llmvdb2.github.io 📝 Submit by Jan 15, 2026 → cmt3.research.microsoft.com/LLMVectorDB2026 Explore LLM × Vector DB × Agents — RAG, multimodal, benchmarking & beyond! #ICDE2026 #LLM #VectorDB #RAG #AIagents
I think @StackOverflow should just connect their entire DB to #vectordb, #RAG workflow and put a #GenAI chatbot on top and done with this debate 😎
When the connection drops, Vektaris ensures your operations never skip a beat. vektaris.com #VectorDB #RAG #Embeddings #DataSecurity #OnPremAI
"Pinecone / FAISS: Facebook AI Similarity Search🔎" Semantic search works instantly #VectorDB #AI #MLOps
🤖【テックブログ】ベクトルインデックスのすゝめを公開! IVFFLATとHNSWを徹底比較!構築コストや検索精度、パラメータ調整のベストプラクティスを実験から導出✨ 高速化だけじゃない、賢い選び方を解説します👇 zenn.dev/exwzd/articles… #VectorDB #生成AI #HNSW #IVFFLAT #エクサウィザーズ
When the connection drops, Vektaris ensures your operations stay seamless. Our secure, scalable vector search and retrieval capabilities operate offline, maintaining data integrity and accessibility. vektaris.com. #VectorDB #RAG #Embeddings #DataSecurity #OnPremAI
🤔Is there a Vector DB where you can use plain SQL to: - Insert data - Create Index with embeddings - Query semantic search No ML knowledge needed! Just write SQL like: #Database #AI #VectorDB #SQL
Search is moving towards semantic understanding. With vector technology, OpenSearch is laying the foundation for AI-driven applications that truly ‘get’ user intent. 🚀 Be part of this journey: hubs.la/Q03RpF3D0 #OpenSearch #VectorDB #Search
How to Modernizing your DB to Handle Massive & Streaming AI Data mltblog.com/3N1woAa #graphdb #vectordb #mariadb In this session, we will discuss the following, with an emphasis on AI applications: ➡️ Advanced features to optimize performance, security, and scalability.…
🚀ObjectBox 4.0 brings vector search. We’re effectively releasing the very first on-device vector database today. Check it out 👉 objectbox.io/the-first-on-d… #mobiledev #ai #vectordb #RAG #android #database #edgeAI
🚀 WeChat (1.4B daily users!) using custom @ClickHouseDB for vector search Their modified version helps handle massive user scale 🌐 #WeChat #VectorDB #BigTech
Aggregata will have the best AI vectorDB for AI engineers. On-chain vectorDB are the next big thing in data assets! #Aggregata #AIData #vectorDB
🔥Thrilled to announce an integration partnership with @openfabricai 🤖Openfabric AI is a planetary-scale network for building & connecting AI applications⚡️ 🤝Teaming up to build full-stack decentralization powered by Glacier #VectorDB and #Openfabricai
What's state for #prodmgmt for #AI. so much to learn, b2b B2C saas PMs (if not prepped already) have to jump a long one From web1 to soap/rest api to now #vectordb and #LLMs, how shd PMs ramp up? Who's guiding/teaching ai for PM? Can collab if someone's up for it
Today I learned Vector DB by @rohit_negi9 Unlike traditional DBs store text or nums, Vector DBs store embeddings — high-Dim vectors representing meaning. This enables semantic search, recommendations. Internally, they use like HNSW, IVF for ultra-fast matching #AI #VectorDB
Top 10 Vector Databases for RAG Applications blog.qualitypointtech.com/2025/09/top-10… #AI #RAG #VectorDB
High-level understanding of historical, lexical search context and evaluation methodology softwaredoug.com/blog/2024/06/2… #search #vectordb #GenAI #LLM #AI
.@JoshuaJerinn and Shahnawaz Mohammed are at @HyderabadPUG today - in fact, Shahnawaz just delivered his talk introducing Tembo Stacks and our #vectorDB capabilities. Make sure to meet them at the social tonight!
Vector stores are now an api call. @OpenAI this was long due, the assistant api v2 🚀. #vectordb #api #openai
🎉 Jeudi soir, si vous êtes sur Paris, je vous invite à me rejoindre au @aicampai pour discuter #MachineLearning et #LLMs. 👉 Au programme, #VectorDB, #Cassandra, #PaLM, #Java, #GenerativeAI !!! aicamp.ai/event/eventdet…
RAG in prod? Cool. 6 weeks later your recall tanks & the model hallucinates. 👻 Root cause = embedding drift; vectors move when you re-fine-tune, re-index or add new docs. Miss it & search ≠ semantics. 🧵👇 #RAG #VectorDB
Shape the future of #databases by participating in DZone's in-house research. Our goal is to uncover how developers, architects, and data leaders are adopting + modernizing databases 👇 survey.alchemer.com/s3/8483827/dzl… #sql #vectordb #postgresql
SQL = reliable. VectorDB = shiny. Both = the future. But which one do you trust?🤔 Vote here 👉 survey.alchemer.com/s3/8483827/dzx2 #Databases #SQL #VectorDB
Smart AI agents need more than text—they need a brain. 🧠 They need unified, multimodal memory—text, images, audio, embeddings, all linked. That's what @ApertureDB delivers. 👇 New blog: ow.ly/aUss50Wat1z #AI #MultimodalAI #VectorDB #AIAgents #GraphDatabases #ApertureDB
Something went wrong.
Something went wrong.
United States Trends
- 1. Marshawn Kneeland 10.4K posts
- 2. Nancy Pelosi 15.5K posts
- 3. #MichaelMovie 22K posts
- 4. ESPN Bet 1,905 posts
- 5. Gremlins 3 1,959 posts
- 6. Good Thursday 33.8K posts
- 7. #NO1ShinesLikeHongjoong 16.3K posts
- 8. Jaafar 6,355 posts
- 9. Madam Speaker N/A
- 10. #영원한_넘버원캡틴쭝_생일 16.1K posts
- 11. #thursdayvibes 2,678 posts
- 12. Happy Friday Eve N/A
- 13. Joe Dante N/A
- 14. Mega Chimecho 3,135 posts
- 15. Penn 8,897 posts
- 16. #BrightStar_THE8Day 24.3K posts
- 17. Baxcalibur 2,660 posts
- 18. Chris Columbus 1,822 posts
- 19. Korrina 2,771 posts
- 20. Diantha N/A