Output safety isn't enough for deleted data in vector indexes—graph traversal can still score removed embeddings, and a new audit framework flags this in Faiss and hnswlib.

#AIprivacy #VectorSearch #MachineLearning
https://arxiv.org/abs/2609.19456

Most RAG problems are retrieval problems wearing an LLM costume.

BGE-M3 gives dense and sparse vectors from one pass; Qdrant fuses both with RRF.

#rag #vectorsearch #llm
abchaudary.me/blog/qdrant-...

✍️ New blog post by Ajay kumar

I Tested Amazon S3 Vectors' New Pre-Filtering Against Exact Ground Truth

#aws #vectorsearch #rag #machinelearning

В последнее время довольно много работаю над agent-memory-cpp.

Это C++ библиотека для быстрой, компактной и встраиваемой памяти AI-агентов: хранить embeddings локально и искать по ним без отдельного vector DB сервиса.

#cpp #VectorSearch #VectorDatabase #Embeddings #ANN #AI

#PostgreSQL #in-process with #vectorsearch extensions directly #embedded in your #Python app. #OpenSource Apache 2.0 lic

- Similarly search: #pgvector + #pgvectorscale, high-performance storage
- #FullText search: #pg_textsearch, #BM25 and #ranking
#AI #LLM #Embeddings #Agents #RAG

https://lckhd.eu/qIZK6J

#S3Vectors #VectorSearch #RAG

If your vector index has tenant-specific data and you run a tenant-scoped query asking for 10 results, you may have only gotten 1 or 2 back. In this case, the filter was applied during the similarity search. A tenant with little data in a

S3 Vectors now filters metadata before the similarity search, so you get higher recall on narrow queries.

Each vector carries 2 KB of filterable metadata. No re-ingestion, no cost.

#VectorSearch #AWS

ift.tt/IJKT9Rh

Vector similarity search is getting closer to the database.

Percona Server for MySQL 9.7.2-2 adds DISTANCE() and VECTOR_DISTANCE(), so developers can score, rank and filter embeddings directly in SQL.

https://bit.ly/3TnSCTK

#MySQL #VectorSearch #AI #SQL #OpenSource

Building a Vector Search Engine — Phase 1
Phase 1: built Euclidean distance, Cosine similarity, random vector generation, brute-force search,
Top-K retrieval, and benchmarking.
1M vectors → ~303ms

Next: IVF & HNSW

GitHub: github.com/Sidhu714/vec...

#Go #VectorSearch #Databases #LearningInPublic

Tired of deploying heavy search clusters for RAG? ⚡
Introducing the Luxir Output Connector in OpenCrawling! 🚀

✔ 1024-dim dense vector kNN + BM25 hybrid ranking
✔ Zero client dependencies
✔ OIS deletion tombstones & Zero-Trust ACLs

opencrawling.org/blog/introdu...

#AI #RAG #Search #VectorSearch

Every sports organization is sitting on a fan product it hasn't built yet. Vector search makes decades of archive footage reachable by meaning instead of exact keywords, which is the requirement for conversational fan experiences.

🔗 https://ow.ly/t4pL50ZQyr0
#AI #VectorSearch #DigitalStrategy

🚀 SeekStorm has a new home! ‒ Take a look 👉 seekstorm.com

We’ve just relaunched our website — with a fresh new look and a clearer way to explore what we’re building.

#OpenSource #Rust #Search #VectorSearch #DevTools

A big thanks to Kamatchi Manoharan for the insightful webinar with great demo on 'Scaling Semantic Search in Sitecore AI with Solr Dense Vectors and RAG' on 11 Sep'26.

Watch the recording here: youtu.be/P3Yc6H1GCMs

#sitecore #semanticsearch #solr #rag #sugchennai #sugchn #SitecoreAI #vectorsearch

How Vector Search Grounds an LLM: How does vector search ground an LLM? Data becomes vector embeddings as it's ingested; a user's prompt becomes a vector too, and the database returns the closest matches — so the model answers from your… MSFTMechanics #VectorSearch #GenerativeAI #MachineLearning

"Agentic AI powered by vector search is changing the game for intelligent agents. AWS offers a range of solutions like OpenSearch, S3 Vectors, DynamoDB, and more to optimize performance, scale, and cost. #AWS #AI #VectorSearch 🚀💡"