SupportNet just turbo‑charged RAG by routing queries with the largest k scores—think faster vector search, smarter MIPS, and leaner quantization. Curious how this boosts retrieval‑augmented generation? Dive in! #RAG #VectorSearch #Quantization
🔗 aidailypost.com/news/support...
🔗 aidailypost.com/news/support...
November 6, 2026 at 9:25 PM
SupportNet just turbo‑charged RAG by routing queries with the largest k scores—think faster vector search, smarter MIPS, and leaner quantization. Curious how this boosts retrieval‑augmented generation? Dive in! #RAG #VectorSearch #Quantization
🔗 aidailypost.com/news/support...
🔗 aidailypost.com/news/support...
Percona Search for MongoDB is now generally available! 🚀
Run full-text, vector & hybrid search on your own infrastructure, with local embeddings, operator-managed deployments and no vendor lock-in.
Learn more: https://bit.ly/4ixzTxF
#MongoDB #VectorSearch #OpenSource #Databases
Run full-text, vector & hybrid search on your own infrastructure, with local embeddings, operator-managed deployments and no vendor lock-in.
Learn more: https://bit.ly/4ixzTxF
#MongoDB #VectorSearch #OpenSource #Databases
Percona Announces General Availability of Percona Search for MongoDB®
Percona, a provider of open source database software, support, and services, today announced the general availability of Percona Search for MongoDB®....
bit.ly
November 4, 2026 at 2:37 PM
Percona Search for MongoDB is now generally available! 🚀
Run full-text, vector & hybrid search on your own infrastructure, with local embeddings, operator-managed deployments and no vendor lock-in.
Learn more: https://bit.ly/4ixzTxF
#MongoDB #VectorSearch #OpenSource #Databases
Run full-text, vector & hybrid search on your own infrastructure, with local embeddings, operator-managed deployments and no vendor lock-in.
Learn more: https://bit.ly/4ixzTxF
#MongoDB #VectorSearch #OpenSource #Databases
A vector index lets a query head for promising regions of embedding space and return close matches without comparing it against every stored item.
#VectorSearch #Embeddings #Databases #MachineLearning
#VectorSearch #Embeddings #Databases #MachineLearning
November 1, 2026 at 7:11 PM
A vector index lets a query head for promising regions of embedding space and return close matches without comparing it against every stored item.
#VectorSearch #Embeddings #Databases #MachineLearning
#VectorSearch #Embeddings #Databases #MachineLearning
How much can an index help MySQL vector search?
At Percona Live Amsterdam, Dominic Preuss showed one vector search test running 50x faster with indexing than without.
🎥 Watch the side-by-side performance test.
#MySQL #VectorSearch
At Percona Live Amsterdam, Dominic Preuss showed one vector search test running 50x faster with indexing than without.
🎥 Watch the side-by-side performance test.
#MySQL #VectorSearch
October 29, 2026 at 3:14 PM
How much can an index help MySQL vector search?
At Percona Live Amsterdam, Dominic Preuss showed one vector search test running 50x faster with indexing than without.
🎥 Watch the side-by-side performance test.
#MySQL #VectorSearch
At Percona Live Amsterdam, Dominic Preuss showed one vector search test running 50x faster with indexing than without.
🎥 Watch the side-by-side performance test.
#MySQL #VectorSearch
Report e moduli con MongoDB 9? Sì, è possibile. Valentina Studio, Valentina Server e altri prodotti sono compatibili con Mongo 9. Versione gratuita del software di gestione database disponibile! valentina-db.com/it/mongo-9
#MongoDB #vectorsearch #mongodb9
#MongoDB #vectorsearch #mongodb9
October 26, 2026 at 2:20 PM
Report e moduli con MongoDB 9? Sì, è possibile. Valentina Studio, Valentina Server e altri prodotti sono compatibili con Mongo 9. Versione gratuita del software di gestione database disponibile! valentina-db.com/it/mongo-9
#MongoDB #vectorsearch #mongodb9
#MongoDB #vectorsearch #mongodb9
Report e moduli con MongoDB 9? Sì, è possibile. Valentina Studio, Valentina Server e altri prodotti sono compatibili con Mongo 9. Versione gratuita del software di gestione database disponibile! valentina-db.com/it/mongo-9
#MongoDB #vectorsearch #mongodb9
#MongoDB #vectorsearch #mongodb9
October 26, 2026 at 2:19 PM
Report e moduli con MongoDB 9? Sì, è possibile. Valentina Studio, Valentina Server e altri prodotti sono compatibili con Mongo 9. Versione gratuita del software di gestione database disponibile! valentina-db.com/it/mongo-9
#MongoDB #vectorsearch #mongodb9
#MongoDB #vectorsearch #mongodb9
UC Berkeley's LEANN cut a 60M-chunk index from 201 GB to 6 GB.
On NQ: 4 GB against HNSW's 188 GB, at the same 25.5% accuracy.
Retrieval 2.48s vs 0.05s. End to end 20.95s vs 23.34s.
An index bills you even when nobody queries it. #VectorSearch
On NQ: 4 GB against HNSW's 188 GB, at the same 25.5% accuracy.
Retrieval 2.48s vs 0.05s. End to end 20.95s vs 23.34s.
An index bills you even when nobody queries it. #VectorSearch
October 28, 2026 at 1:05 AM
UC Berkeley's LEANN cut a 60M-chunk index from 201 GB to 6 GB.
On NQ: 4 GB against HNSW's 188 GB, at the same 25.5% accuracy.
Retrieval 2.48s vs 0.05s. End to end 20.95s vs 23.34s.
An index bills you even when nobody queries it. #VectorSearch
On NQ: 4 GB against HNSW's 188 GB, at the same 25.5% accuracy.
Retrieval 2.48s vs 0.05s. End to end 20.95s vs 23.34s.
An index bills you even when nobody queries it. #VectorSearch
Implementing HNSW graphs and locality-sensitive hashing to query high-dimensional embeddings in milliseconds. Galgotias University keeps developers ahead in modern AI retrieval infrastructure! 🧠📊
#GalgotiasUniversity #VectorSearch #AI #DataScience
#GalgotiasUniversity #VectorSearch #AI #DataScience
October 23, 2026 at 3:27 PM
Implementing HNSW graphs and locality-sensitive hashing to query high-dimensional embeddings in milliseconds. Galgotias University keeps developers ahead in modern AI retrieval infrastructure! 🧠📊
#GalgotiasUniversity #VectorSearch #AI #DataScience
#GalgotiasUniversity #VectorSearch #AI #DataScience
🚀 Cohere just dropped Rerank 5, nailing 92.2 on ViDoRe V3 with a passage‑level focus. Think smarter reranking, tighter context, and better relevance scores. Curious how this reshapes vector search? Dive in! #CohereRerank5 #PassageLevel #VectorSearch
🔗 aidailypost.com/news/cohere-...
🔗 aidailypost.com/news/cohere-...
October 22, 2026 at 5:41 PM
🚀 Cohere just dropped Rerank 5, nailing 92.2 on ViDoRe V3 with a passage‑level focus. Think smarter reranking, tighter context, and better relevance scores. Curious how this reshapes vector search? Dive in! #CohereRerank5 #PassageLevel #VectorSearch
🔗 aidailypost.com/news/cohere-...
🔗 aidailypost.com/news/cohere-...
Vector Search Inside Out by Ritesh Modi is a new release on Leanpub!
HNSW powers almost every vector database, and few of the engineers who rely on it have seen inside it.
Link: leanpub.com/vectorsearch...
#books #ebooks #newreleases
HNSW powers almost every vector database, and few of the engineers who rely on it have seen inside it.
Link: leanpub.com/vectorsearch...
#books #ebooks #newreleases
October 14, 2026 at 12:15 AM
Vector Search Inside Out by Ritesh Modi is a new release on Leanpub!
HNSW powers almost every vector database, and few of the engineers who rely on it have seen inside it.
Link: leanpub.com/vectorsearch...
#books #ebooks #newreleases
HNSW powers almost every vector database, and few of the engineers who rely on it have seen inside it.
Link: leanpub.com/vectorsearch...
#books #ebooks #newreleases
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
#AIprivacy #VectorSearch #MachineLearning
https://arxiv.org/abs/2609.19456
October 7, 2026 at 8:01 PM
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
#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-...
BGE-M3 gives dense and sparse vectors from one pass; Qdrant fuses both with RRF.
#rag #vectorsearch #llm
abchaudary.me/blog/qdrant-...
Qdrant and BGE-M3 Hybrid Search for Production RAG
How to run Qdrant hybrid search with BGE-M3 for production RAG: dense and sparse vectors from one model, RRF fusion, payload filters, and retrieval checks.
abchaudary.me
October 6, 2026 at 9:41 PM
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-...
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
I Tested Amazon S3 Vectors' New Pre-Filtering Against Exact Ground Truth
#aws #vectorsearch #rag #machinelearning
I Tested Amazon S3 Vectors' New Pre-Filtering Against Exact Ground Truth
A filtered vector query that asks for 10 results can come back with 2, and nothing errors. AWS's own...
dev.to
October 6, 2026 at 5:24 PM
✍️ New blog post by Ajay kumar
I Tested Amazon S3 Vectors' New Pre-Filtering Against Exact Ground Truth
#aws #vectorsearch #rag #machinelearning
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
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
October 4, 2026 at 12:53 PM
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
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
- Similarly search: #pgvector + #pgvectorscale, high-performance storage
- #FullText search: #pg_textsearch, #BM25 and #ranking
#AI #LLM #Embeddings #Agents #RAG
GitHub - Ladybug-Memory/pgembed: Embedded PostgreSQL for Agents
Embedded PostgreSQL for Agents. Contribute to Ladybug-Memory/pgembed development by creating an account on GitHub.
github.com
October 3, 2026 at 2:12 PM
#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
- Similarly search: #pgvector + #pgvectorscale, high-performance storage
- #FullText search: #pg_textsearch, #BM25 and #ranking
#AI #LLM #Embeddings #Agents #RAG
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
Each vector carries 2 KB of filterable metadata. No re-ingestion, no cost.
#VectorSearch #AWS
ift.tt/IJKT9Rh
September 30, 2026 at 8:09 PM
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
Each vector carries 2 KB of filterable metadata. No re-ingestion, no cost.
#VectorSearch #AWS
ift.tt/IJKT9Rh
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
#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
Amazon S3 Vectors now supports metadata pre-filtering for higher recall on filtered searches | Amazon Web Services
Amazon S3 Vectors now supports metadata pre filtering, delivering up to 5x higher recall on filtered searches. Filters evaluate before similarity search so scoped queries return more relevant results. Ideal for RAG, agentic apps, and document search.
lckhd.eu
October 1, 2026 at 2:30 AM
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
#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
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
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
September 28, 2026 at 6:06 AM
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
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
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
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
DISTANCE() and VECTOR_DISTANCE(): Vector Similarity in Percona Server for MySQL 9.7
TL;DR Percona Server for MySQL 9.7.2-2 now supports DISTANCE() for vector similarity scoring directly in SQL (COSINE, EUCLIDEAN, MANHATTAN, DOT metrics). This is the compute primitive you need to rank...
www.percona.com
September 28, 2026 at 5:59 PM
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
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
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
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
September 24, 2026 at 12:34 PM
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
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
🔗 https://ow.ly/t4pL50ZQyr0
#AI #VectorSearch #DigitalStrategy
September 23, 2026 at 1:36 PM
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
🔗 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
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
September 18, 2026 at 12:31 PM
🚀 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
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