SilverTorch: A Unified Retrieval Architecture for Scalable Recommendation Systems
We’re introducing SilverTorch, a reimagining of recommendation systems that unifies all retrieval components for user generated content under a unified architecture. SilverTorch shows up to 23.7x …
Read the full articleYou might also wanna read
Local-First Information Retrieval: Keeping Search Private on Consumer Hardware
The sensitive information in personal documents, legal files, and medical records is among the most valuable things to search, yet current r
arxiv.org·18d ago
Scaling Bloom Filter-Based Full-Text Search to Large Document Collections
Jonathan Arns's personal blog
notpeerreviewed.com·8mo agoProject Sauron: building a two-tower retrieval model for personalized recommendations at daily.dev
Discover how daily.dev uses Project Sauron, a powerful two-tower retrieval model, to deliver personalized content to over half a million dev
ClickHouse Rebuilds Full-Text Search with Native Columnar Integration
A deep dive into ClickHouse’s built-in full-text search — how it works, what’s new, and how to use it for fast, precise text queries.
ClickHouse·10mo agoClickHouse Rebuilds Full-Text Search with Native Columnar Integration
A deep dive into ClickHouse’s built-in full-text search — how it works, what’s new, and how to use it for fast, precise text queries.
clickhouse.com·10mo ago
Benchmarking GLM-5.2 vs Opus 4.8: Long-context retrieval performance for coding agents
A Braintrust-native eval comparing GLM-5.2 and Opus 4.8 on exact long-context retrieval, cost, and latency.
braintrust.dev·17d ago
Technical Analysis of Local RAG Implementation: Tradeoffs Between Inference Speed and Retrieval Accuracy
I interacted with the authors of these models quite a bit!
news.ycombinator.com·6mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.