OpenSearch 3.7: 5.5x Faster Vector Search and Native Prometheus
OpenSearch 3.7 delivers 5.5x faster vector retrieval via docvalue_fields and native Prometheus integration—no reindexing or data migration required. The post OpenSearch 3.7: 5.5x Faster Vector Search…
Read the full articleYou might also wanna read
From 48 Seconds to 130 Milliseconds: Vector Search in Tinybird
A customer needed semantic search over 20 million embeddings. Their first attempt timed out. Three changes turned it into sub-200ms queries.
More Like This Search: From Keyword Matching to Embeddings and Vector Search
More Like This lets search start from a selected document instead of a new query. The classic approach relies on similar words; the modern a
manticoresearch.com·1mo ago
Choosing Vector Stores for Retrieval Workloads
Vector retrieval has become a standard component in data platform architectures, not just an ML research topic. RAG pipelines use it to retr
Indexing Time vs. Query Time Retrieval Strategies
If you’ve spent any time building RAG systems, you’ve hit this wall: your embeddings look fine, your vector DB is fast and retrieval is stil
AI Search - AI Search now has hybrid search and relevance boosting
AI Search now supports hybrid search and relevance boosting, giving you more control over how results are found and ranked. Hybrid search Hy
Valori: A Python-Native Vector Database Built for Modularity and Extensibility
I’ve been working on a project called Valori, a Python-native vector database I built from the ground up — not by reinventing every algorith
news.ycombinator.com·8mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.