Agents are ditching RAG for pure vector search—because memory frameworks already store embeddings. Find out why similarity search is becoming the go‑to retrieval infra for LLM agents. #VectorSearch #AIMemory #AgentSystems

🔗 aidailypost.com/news/agents-...

Building a Vector Search System End-to-End - Part I

Peeling the Onion of Vector Search : From FAISS to from the Scratch Algorithmic Implementation

#vectorsearch

⏰Real-time AI needs real-time data

Guy Shtub shows how modern #database architectures support AI workloads at scale

You'll learn:
🔺 Feature Stores
🔺 #VectorSearch
🔺 Low-latency #AI systems

#webinalewebweek |📍BER | 📅 June 8 – 12, 26

👀About the session: https://tinyurl.com/yc6wn6pz

#webinale

How AI Search Engines Rank Content: Reverse Engineering Ranking Signals Learn how AI search engines rank content by analyzing retrieval signals, semantic ranking, entity authority, and GEO strategies.

Learn how AI search engines rank content by analyzing retrieval signals, semantic ranking, entity authority, and GEO strategies.

blog.applabx.com/how-ai-searc...

#AISearch, #AISearchEngines, #AISearchRanking, #AISEO, #GenerativeEngineOptimization, #GEO, #SemanticSearch, #VectorSearch,

Kinetica is the only vector database built for real-time operational data at GPU speed.

For RAG on live operational data — financial signals, telemetry, sensor feeds — the gap between data arrival and search availability isn't a minor inconvenience.

It's the difference between AI that knows what's happening now vs. what happened hours ago.

#VectorSearch #RealTimeAI

Optimizing Vector Search Author Introduction: I am Mansi Tibude, an electronics and communication engineer. I have worked in...

Optimizing Vector Search Author Introduction : I am Mansi Tibude, an electronics and communication engineer. I have worked in the IT industry for about 3 years as a Systems Engineer in a previous o...

#vectorsearch #elasticsearch #vectorwithelastic

Origin | Interest | Match

The Modern, Unified GenAI Data Stack | TiDB Optimize GenAI apps with the right database. Learn vector search, RAG, and more in this engineer’s guide to GenAI data infrastructure.

When SQL, vector search, and sync pipelines live in separate systems, context becomes stale and ops get painful. A modern unified GenAI data stack simplifies this by bringing transactions + vectors together.

https://ow.ly/fOa750YlLEV

#GenAI #DataStack #VectorSearch

Oracle Vector Search: Distance Metrics There are several ways you can calculate distances to determine how similar, or not, two vectors are. I'll introduce you each metric available in Oracle 26ai. Euclidean and Euclidean Squared Distances Computed using straight-line distance between two vectors. This is calculated using the Pythagorean theorem (SQRT(SUM((xi-yi)2))). Euclidean Squared avoid the square-root calculation, so, it's faster to compute. Cosine Similarity Measures the cosine of the angle between two vectors.

There are several ways you can calculate distances to determine how similar, or not, two vectors are. I'll introduce you each metric available in Oracle 26ai. #oracle #ai #oracleai #oracle26ai #vectorsearch #oracleace

Blue promotional graphic for Azure DocumentDB featuring the title “DocumentDB Vector Search for TypeScript.” The image includes a database icon with curly braces, a magnifying glass over a network graph representing vector search, and a banner reading “Azure DocumentDB Code Sample” on a blue gradient background.

Explore vector search in TypeScript with Azure DocumentDB. This hands-on sample shows how to store embeddings, configure vector indexes, and run similarity queries in a Node.js app.

msft.it/63325QpWp1

#AzureDocumentDB #VectorSearch

SurrealDB 3.0 just merged agent memory, business logic, and multimodal data into a single engine. Think RAG, graph queries, vector search—all powered by Rust. Curious how this reshapes AI pipelines? Dive in. #SurrealDB #VectorSearch #AgentMemory

🔗 aidailypost.com/news/surreal...

🔍 La biblioteca open source USearch potencia la búsqueda vectorial de ScyllaDB

ScyllaDB integra búsqueda vectorial con USearch, acelerando aplicaciones de IA.

thenewstack.io/open-source-usearch-libr...

#VectorSearch #ScyllaDB #OpenSource #RoxsRoss

PostgreSQL on Azure supercharged for AI | Microsoft Azure Blog Find out why PostgreSQL is the most-loved database among developers, and with Azure’s latest innovations, it’s now more intelligent.

PostgreSQL on Azure is being repositioned as AI infrastructure, not just a managed DB.

Vector search, AI-ready performance, and enterprise controls signal a shift:
your database is now part of the AI system design.

azure.microsoft.com/en-us/blog/p...

#Azure #PostgreSQL #AIInfra #VectorSearch

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

Demystifying Vector Databases: OpenSearch for Semantic Search Ready to unlock the true potential of your data? We're diving deep into the world of Vector Search with special guest Dotan Horovitz, Senior Developer Advocate at AWS and OpenSearch Ambassador. We break down complex tech into simple, actionable insights for developers and data enthusiasts alike. Dotan guides us through the essentials of vector versus lexical search, revealing why "hybrid search" might be the winning strategy you're looking for. We also explore the cutting edge of multimodal search (searching across images, video, and text) and how to deploy powerful AI agents directly within OpenSearch. Whether you are building the next big GenAI application or just want to understand the mechanics behind semantic search, this conversation is packed with value. Watch the full episode to future-proof your search strategy! LEARN MORE ABOUT INSTACLUSTR MANAGED OPENSEARCH: https://www.instaclustr.com/platform/managed-opensearch/ LOOKING FOR EMERGENCY SUPPORT: https://www.instaclustr.com/contact-us/ Don't forget to Like and Subscribe to the channel for more expert insights on AI and cloud technology!

#OpenSearchAmbassador Dotan Horovits cuts through the hype, explaining why hybrid search works best and how OpenSearch powers smarter AI and RAG—in the latest InstaBlinks episode, hosted by member company @NetApp Instaclustr.

Watch now 👇
bit.ly/4pSp4YM

#OpenSearch #VectorSearch #AI #RAG

Release 26.1.1 · ArcadeData/arcadedb ArcadeDB 26.1.1 Release Notes We're excited to announce ArcadeDB 26.1.1, a significant release that brings 92 closed issues and introduces major new capabilities to the platform. This release marks...

ArcadeDB v26.1.1 is out! New Native OpenCypher Engine, huge LSM Vector updates (Quantization, PQ and much more), 92 total issues resolved (!)

github.com/ArcadeData/a...

#ArcadeDB #GraphDB #OpenCypher #VectorSearch #Database #OpenSource

Recherche vectorielle : MongoDB entend unifier sa pile technologique | LeMagIT Le spécialiste du NoSQL poursuit ses efforts en matière de recherche vectorielle et d’IA générative. Lors de son événement Local du 15 janvier à San Francisco, MongoDB a présenté plusieurs ajouts en c...

Vous déployez un RAG ? MongoDB lance Voyage 3.5 multimodal et Voyage 4 (32k tokens, 256–2048 dim), vectorisation auto et préfiltres pour réduire les coûts. 🔎⚙️ #vectorsearch https://bit.ly/4qvzIG2

Why does AI understand some questions and miss others?

Searching is easy. Understanding intent is hard.
Here’s Nischith Girish sharing a perspective worth hearing👇

𝗙𝘂𝗹𝗹 𝘀𝘁𝗼𝗿𝘆 → antt.me/tqp5guLA
𝗦𝘂𝗯𝘀𝗰𝗿𝗶𝗯𝗲 → antt.me/-PCkoRRa

#AI #VectorSearch

Vector search for modern applications 🤖
OpenSearch continues to improve performance and predictability for AI-powered search.
👉 Read about vector search in OpenSearch: opensearch.org/platform/vec...

#OpenSearch #VectorSearch

Secure and Intelligent: Queryable Encryption and Vector Search in MongoDB EF Core Provider - .NET Blog The MongoDB EF Core provider now supports Queryable Encryption and Vector Search. Learn how to encrypt sensitive data while querying it and build AI-powered semantic search applications directly with EF Core.

Secure and Intelligent: Queryable Encryption and Vector Search in MongoDB EF Core Provider The MongoDB EF Core provider now supports Queryable Encryption and Vector Search. Learn how to encrypt sen...

#.NET #Entity #Framework #efcore #mongodb #rag #vectorsearch

Origin | Interest | Match

Secure and Intelligent: Queryable Encryption and Vector Search in MongoDB EF Core Provider - .NET Blog The MongoDB EF Core provider now supports Queryable Encryption and Vector Search. Learn how to encrypt sensitive data while querying it and build AI-powered semantic search applications directly with EF Core.

Secure and Intelligent: Queryable Encryption and Vector Search in MongoDB EF Core Provider The MongoDB EF Core provider now supports Queryable Encryption and Vector Search. Learn how to encrypt sen...

#.NET #Entity #Framework #efcore #mongodb #rag #vectorsearch

Origin | Interest | Match

Keyword Search: Combining Lexical and Vector Search #shorts See how combining lexical keyword matching with vector search gives you the best of both worlds. Match specific keywords like product names while also getting conceptual mapping. #keywordmatching #vectorsearch #AI #searchalgorithms

FYI: Keyword Search: Combining Lexical and Vector Search #shorts: See how combining lexical keyword matching with vector search gives you the best of both worlds. Match specific keywords like product names while also getting conceptual mapping. #keywordmatching #vectorsearch #AI #searchalgorithms

⏰ Reminder: Qdrant Office Hours - in 2 days!
🗓️ 18th December
⏰ 9:30 PM IST | 9:00 AM PST | 5:00 PM CET

Speakers:
- Kumar Shivendu - Qdrant v1.16 update
- Clelia Astra Bertelli - StudyLlama updates

Link to the event: discord.com/events/90756...

#Qdrant #VectorSearch #Discord #AIInfrastructure #LLM

Revolutionize Your Search with Hybrid Techniques: A Hands-On Guide

Hybrid Search, a state-of-the-art modern technique that delivers the best of both worlds.  Hybrid Search includes the precision of keyword matching and the cont #vectorsearch

Imagine a shopper searching for “red running shoes.” Traditional search might miss their style preferences. With vector search, OpenSearch can recommend the perfect pair — similar in style, color, and fit!

Semantic search just got smarter. 🚀 opensearch.org/platform/vec...
#OpenSearch #VectorSearch

Stop Relying on Vector Search Alone: Build a Hybrid RAG System with Knowledge Graphs and Local LLMs Standard RAG pipelines are hitting a wall. Here is how to break through by combining Vector Search with Knowledge Graphs. If you have built a

Stop Relying on Vector Search Alone: Build a Hybrid RAG System with Knowledge Graphs and Local LLMs #Technology #EmergingTechnologies #ArtificialIntelligence #VectorSearch #HybridRAG #AI

Implementing Vector Search in Your Application with SQL Server 2025 | Data Exposed: MVP Edition Going a level deeper than a basic semantic search talk, we’ll explore semantic search, how to implement it in your app, and how to ingest data at scale to support your application’s AI needs. ✅ Chapters: 0:00 Introduction 3:50 Demo ✅ Resources: https://learn.microsoft.com/en-us/sql/t-sql/functions/vector-search-transact-sql?view=sql-server-ver17 https://learn.microsoft.com/en-us/sql/sql-server/ai/vectors?view=sql-server-ver17 https://github.com/Azure-Samples/azure-sql-db-vector-search About Joseph D'Antoni: Joseph D'Antoni is an Principal Consultant at Denny Cherry and Associates Consulting. He is recognized as a VMWare vExpert and a Microsoft Data Platform MVP, and has over 20 years of experience working in both Fortune 500 and smaller firms. He has worked extensively on database platforms and cloud technologies and has specific expertise in performance tuning, infrastructure, and disaster recovery. About MVPs: Microsoft Most Valuable Professionals, or MVPs, are technology experts who passionately share their knowledge with the community. They are always on the "bleeding edge" and have an unstoppable urge to get their hands on new, exciting technologies. They have very deep knowledge of Microsoft products and services, while also being able to bring together diverse platforms, products and solutions, to solve real world problems. MVPs make up a global community of over 4,000 technical experts and community leaders across 90 countries/regions and are driven by their passion, community spirit, and quest for knowledge. Above all and in addition to their amazing technical abilities, MVPs are always willing to help others - that's what sets them apart. Learn more: https://aka.ms/mvpprogram 📌 Let's connect: Twitter: Anna Hoffman, https://twitter.com/AnalyticAnna Twitter: AzureSQL, https://aka.ms/azuresqltw 🔴 To watch other MVP Edition episodes, see our playlist: https://aka.ms/dataexposedmvps To check out even more Data Exposed episodes, see our playlist: https://aka.ms/dataexposedyt 🔔 Subscribe to our channels for even more SQL tips: Microsoft Azure SQL: https://aka.ms/msazuresqlyt Microsoft SQL Server: https://aka.ms/mssqlserveryt Microsoft Developer: https://aka.ms/microsoftdeveloperyt #AzureSQL #SQLServer

Channel9 Implementing Vector Search in Your Application with SQL Server 2025 | Data Exposed: MVP Edition: Going a level deeper than a basic semantic search talk, we’ll explore semantic search, how to implement it in your app, and how to ingest data at scale to… #VectorSearch #SQLServer #DataExposed

💡 Compressing vectors saves memory but can hurt recall. Using asymmetric distance computation (ADC), you can search compressed indexes with uncompressed queries — achieving up to 32 fold compression with better recall.

📚 Read more: opensearch.org/blog/asymmet...

#OpenSearch #VectorSearch

Unlocking AI Search in Drupal: A Practical Guide to Vector Database Modules Explore how Drupal developers can harness the power of vector databases to enhance AI Search and RAG capabilities. This guide breaks down five VDB Provider modules—Milvus, Pinecone, Postgres, SQLite, and Azure AI Search—comparing their setup, perform...

🧠 Want smarter search in Drupal?

Grzegorz Bartman at Droptica reviews 5 vector DB modules powering AI Search & RAG.

Stable option: SQLite. Leader in flexibility: Milvus.
https://bit.ly/48yIRpw

#DrupalAI #VectorSearch #DrupalModules #AIDevelopment

Vector Sharks

NEW ON AMAZONWEBSHARK: I explore how Amazon S3 Vectors works in practice, create an unstructured data Bedrock Knowledge Base using it and review its storage layout, performance and cost 🦈 Link in comments!

#AWS #S3Vectors #DataEngineering #RAG #VectorSearch #GenerativeAI