#vector-search
Are vector databases still needed? RAG, AI agents & search -> youtu.be/rXFV1ivDe6c
Are Vector Databases Still Needed? RAG, AI Agents & Search
YouTube video by IBM Technology
youtu.be
November 15, 2026 at 7:30 PM
Amazon S3 Vectors now supports hybrid search combining vector and full text for more relevant search results

Amazon S3 Vectors now supports hybrid search, combining vector similarity and full-text search in one query for better RAG and search results with sub-second latency.
November 16, 2026 at 11:03 PM
qdrant: Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/ ★35566 https://github.com/qdrant/qdrant
qdrant / qdrant
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
github.com
November 15, 2026 at 6:47 PM
Store the embedding model name and version next to every vector. The day you switch models, every old vector stops matching new queries. Without that column you cannot tell which rows need re-embedding, and you will find out from bad search results.
November 19, 2026 at 2:02 AM
Amazon S3 Vectors now supports hybrid search combining vector and full text for more relevant search results

Amazon S3 Vectors now supports hybrid search that combines vector similarity search with full-text search within a single query. By combining semantic meaning and exact te...

#AWS #AmazonS3
Amazon S3 Vectors now supports hybrid search combining vector and full text for more relevant search results
Amazon S3 Vectors now supports hybrid search that combines vector similarity search with full-text search within a single query. By combining semantic meaning and exact term matching into a single ranked list of results, hybrid search captures both intent and precise terms for retrieval-augmented generation (RAG), agent memory, and search applications. This can deliver more relevant ranked results than either method alone. Hybrid search works with the same S3 Vectors APIs and maintains subsecond latency for infrequent queries and latency around 100 milliseconds or less for frequent queries. S3 Vectors is designed to provide the same elasticity, durability, and availability as Amazon S3, and it reduces the total costs of storing and querying vectors by up to 90% compared to alternative vector solutions. With hybrid search, customers can now store the data that they want to make full-text searchable alongside the vectors. Customers write data with the PutVectors API as they do today and include the searchable text as another metadata field. S3 Vectors then automatically indexes that field for full-text search with BM25 relevance scoring. By default, S3 Vectors uses a language-agnostic text analyzer to index this data which works across most languages, and customers can optionally select a language-specific analyzer for more accurate language-aware matching. To perform a hybrid query, customers send their query text strings alongside their query vector in a single QueryVectors call; S3 Vectors runs both a vector search and a full-text search, fuses the two with Reciprocal Rank Fusion (RRF), and returns a single ranked list of the top K requested results. Customers can also run full-text and vector queries separately to apply own ranking logic, search across multiple text fields in a single query, and enable full-text search on existing data in place. Hybrid search is available today in all commercial AWS Regions where Amazon S3 Vectors is available, and in the AWS China Regions. To get started, use the AWS CLI, AWS SDKs, or the Amazon S3 console. To learn more, visit the Amazon S3 Vectors https://docs.aws.amazon.com/AmazonS3/latest/userguide/s3-vectors-hybrid-search.html, and the Amazon S3 https://aws.amazon.com/s3/pricing/ for pricing.
aws.amazon.com
November 16, 2026 at 11:05 PM
ICYMI: @dbtrends covered the launch of Percona Search for MongoDB.

It brings full-text, vector and hybrid search to self-managed MongoDB, with local embeddings and operator-managed deployment.

Read: https://bit.ly/4eCrl7z

#MongoDB #VectorSearch #OpenSource
Percona Launches Percona Search for MongoDB
Percona has announced the general availability of Percona Search for MongoDB, an offering that allows organizations to run full-text, vector, and hybrid search within their own infrastructure. It comb...
bit.ly
November 18, 2026 at 9:51 PM
Brought to you by:

• turbopuffer – a vector and full-text search engine built on object storage. It’s fast, cheap, and extremely scalable. turbopuffer.com/pragmatic

• Linear – the product development system for teams and agents. linear.app/pragmatic
turbopuffer x Pragmatic Engineer
Vector and full-text search built on object storage: fast, 10x cheaper, and extremely scalable.
turbopuffer.com
November 16, 2026 at 2:56 PM
Lakegres: Vector search on existing Open/Hudi/Iceberg tables

https://www.onehouse.ai/blog/lakegres-vector-search-on-open-table-formats
November 18, 2026 at 6:10 PM
For my setup I have a vector search based context archive running locally, and I just chuck anything that MIGHT be useful in there.
November 16, 2026 at 3:49 PM
omg it's @paul.irish writing about how Modern Web Guidance efficiently serves hundreds of guides to coding agents without overloading the context window

developer.chrome.com/blog/mwg-tec...
Local vector search for coding agents: From 507 MB to a 7-line loop  |  Blog  |  Chrome for Developers
How we shrunk Modern Web Guidance's local vector search to a 7-line loop while improving search accuracy.
developer.chrome.com
November 12, 2026 at 7:50 PM
Amazon S3 Vectors now supports hybrid search combining vector and full text for more relevant search results
Amazon S3 Vectors now supports hybrid search that combines vector similarity search with full-text search within a single query. By combining semantic meaning and exact term matching into a single ranked list of results, hybrid search captures both intent and precise terms for retrieval-augmented generation (RAG), agent memory, and search applications. This can deliver more relevant ranked results than either method alone. Hybrid search works with the same S3 Vectors APIs and maintains subsecond latency for infrequent queries and latency around 100 milliseconds or less for frequent queries. S3 Vectors is designed to provide the same elasticity, durability, and availability as Amazon S3, and it reduces the total costs of storing and querying vectors by up to 90% compared to alternative vector solutions. With hybrid search, customers can now store the data that they want to make full-text searchable alongside the vectors. Customers write data with the PutVectors API as they do today and include the searchable text as another metadata field. S3 Vectors then automatically indexes that field for full-text search with BM25 relevance scoring. By default, S3 Vectors uses a language-agnostic text analyzer to index this data which works across most languages, and customers can optionally select a language-specific analyzer for more accurate language-aware matching. To perform a hybrid query, customers send their query text strings alongside their query vector in a single QueryVectors call; S3 Vectors runs both a vector search and a full-text search, fuses the two with Reciprocal Rank Fusion (RRF), and returns a single ranked list of the top K requested results. Customers can also run full-text and vector queries separately to apply own ranking logic, search across multiple text fields in a single query, and enable full-text search on existing data in place. Hybrid search is available today in all commercial AWS Regions where Amazon S3 Vectors is available, and in the AWS China Regions. To get started, use the AWS CLI, AWS SDKs, or the Amazon S3 console. To learn more, visit the Amazon S3 Vectors documentation, and the Amazon S3 pricing page for pricing.
dlvr.it
November 16, 2026 at 11:05 PM
Brought to you by:

• turbopuffer – a ridiculously scalable, fast & cheap hybrid search engine, built on top of object storage. turbopuffer.com/pragmatic

• Entire – launched its own Git forge, shipped Continuous Memory & reinvented the pull request (called Trails). Check it out: entire.io/pragmatic
turbopuffer x Pragmatic Engineer
Vector and full-text search built on object storage: fast, 10x cheaper, and extremely scalable.
turbopuffer.com
November 18, 2026 at 6:47 PM
🆕 Amazon S3 Vectors now supports hybrid search, combining vector and full-text for better results via Reciprocal Rank Fusion. Available in all AWS regions, it cuts costs by up to 90%. Use AWS CLI, SDKs, or S3 console. For details, see S3 Vectors docs.

#AWS #AmazonS3
Amazon S3 Vectors now supports hybrid search combining vector and full text for more relevant search results
Amazon S3 Vectors now supports hybrid search that combines vector similarity search with full-text search within a single query. By combining semantic meaning and exact term matching into a single ranked list of results, hybrid search captures both intent and precise terms for retrieval-augmented generation (RAG), agent memory, and search applications. This can deliver more relevant ranked results than either method alone. Hybrid search works with the same S3 Vectors APIs and maintains subsecond latency for infrequent queries and latency around 100 milliseconds or less for frequent queries. S3 Vectors is designed to provide the same elasticity, durability, and availability as Amazon S3, and it reduces the total costs of storing and querying vectors by up to 90% compared to alternative vector solutions. With hybrid search, customers can now store the data that they want to make full-text searchable alongside the vectors. Customers write data with the PutVectors API as they do today and include the searchable text as another metadata field. S3 Vectors then automatically indexes that field for full-text search with BM25 relevance scoring. By default, S3 Vectors uses a language-agnostic text analyzer to index this data which works across most languages, and customers can optionally select a language-specific analyzer for more accurate language-aware matching. To perform a hybrid query, customers send their query text strings alongside their query vector in a single QueryVectors call; S3 Vectors runs both a vector search and a full-text search, fuses the two with Reciprocal Rank Fusion (RRF), and returns a single ranked list of the top K requested results. Customers can also run full-text and vector queries separately to apply own ranking logic, search across multiple text fields in a single query, and enable full-text search on existing data in place. Hybrid search is available today in all commercial AWS Regions where Amazon S3 Vectors is available, and in the AWS China Regions. To get started, use the AWS CLI, AWS SDKs, or the Amazon S3 console. To learn more, visit the Amazon S3 Vectors documentation, and the Amazon S3 pricing page for pricing.
aws.amazon.com
November 16, 2026 at 11:10 PM
SIMQ: A Single Graph-based Index for Multi-Vector Query

Introduces a single graph index for multi-vector retrieval. It approximates MaxSim via per-token graph search over data-aware clusters, with no interaction matrix.

📝 arxiv.org/abs/2611.22079
SIMQ: A Single Graph-based Index for Multi-Vector Query
Multi-vector retrieval models such as ColBERT achieve state-of-the-art effectiveness by representing documents as sets of token-level vectors and scoring via MaxSim, but their high computational cost ...
arxiv.org
November 18, 2026 at 7:48 AM
Amazon S3 Vectors now supports hybrid search combining vector similarity and full-text search for more relevant results in RAG and search applications.
Amazon S3 Vectors now supports hybrid search combining vector and full text for more relevant search results
Amazon S3 Vectors now supports hybrid search combining vector similarity and full-text search for more relevant results in RAG and search applications.
aws-news.com
November 16, 2026 at 10:50 PM
📢 RAG Security: Vector Database Attacks and Data Leakage — Day 2: Embeddings, Chunking and Similarity Search

https://securityelites.com/academy/rag-security-vector-database-attacks/day-2-embeddings-chunking-similarity-search/

#cybersecurity #ethicalhacking
November 18, 2026 at 1:10 PM
🚀 Open source meets serious computing power!
🦭 MariaDB Server 12.3 LTS on IBM Power Virtual Server!

✅ One-click deployment
✅ Automated replication
✅ Built-in vector search
✅ IBM Power performance

🔗 community.ibm.com/community/us... #mariadb #ibm
November 17, 2026 at 6:49 PM
#OpenSearch 3.10 is out! 🚀
⚡️ 2.6x vector query throughput with Intel SVS (at 0.95 recall, 37-40% less graph memory) 🔀 Hybrid queries without a search pipeline 🤖 Agentic search via templates 📦 Pull-based ingestion from S3, GCS & Azure Blob
opensearch.org/blog/explore...
#VectorSearch @opensearch.org
November 18, 2026 at 7:46 PM
"Embed multimodal content for enterprise search with Amazon Nova Multimodal Embeddings" by Wale Akinfaderin

#agentic-ai #amazon-bedrock #amazon-nova #amazon-opensearch #vector-search
Embed multimodal content for enterprise search with Amazon Nova Multimodal Embeddings
How to choose embedding settings and vector sizes for multimodal enterprise search.
community.aws
November 18, 2026 at 4:00 PM
Lakegres: Vector search on existing Open/Hudi/Iceberg tables
Discussion | hackernews | Author: cloud8bits

#Databases
Lakegres: Vector search on existing Open/Hudi/Iceberg tables
Native vector indexes on existing and new Hudi and Iceberg tables. Explore the open design, index layout and Lakegres benchmark results.
www.onehouse.ai
November 18, 2026 at 6:16 PM
EF Core 11: Vector Search, Smarter LINQ, and a Friendlier dotnet ef

youtube.com/watch?v=dgd3...

#efcore #dotnet #csharp #dotnet11
EF Core 11: Vector Search, Smarter LINQ, and a Friendlier dotnet ef
YouTube video by dotnet
youtube.com
November 14, 2026 at 4:15 PM
#GPU accelerated O-means #clustering #algorithm faster than E-means. Use for:
- Near #duplicate removal
- #IVF indexes for vector search & #RAG

#OpenSource MIT lic
#k-means

github.com/owlgebra-ai/...
November 15, 2026 at 1:20 PM
Vector Search and Retrieval at Scale: pgvector vs Pinecone vs Qdrant in Production (2026 Latency and Cost Analysis) #AI #Tech

techwhoknows.com
Vector Search and Retrieval at Scale: pgvector vs Pinecone vs Qdrant in Production (2026 Latency and Cost Analysis)
An in-depth evaluation of memory consumption, index build speeds, filtering latency, and operational cost across embedded PostgreSQL and dedicated vector databases.
techwhoknows.com
November 15, 2026 at 3:32 AM