🔎 Semantic Search - hop1.ng.1357 · Scour

Mixing numeric attributes into text search for better first-stage relevance 🔍Information Retrieval

turbopuffer.com·3d·Lobsters, Hacker News

HNSW Explained: The Algorithm Powering Fast Vector Search 🌸Bloom Filters

Health System Scale Semantic Search Across Unstructured Clinical Notes 🔍Information Retrieval

Diagnosing protein sequence search in the era of language models 📚RAG

biorxiv.org·3h

Retrieval-Augmented Generation (RAG) Systems with Claude 📚RAG

·18h

Qdrant’s AI vector search is faster, auditable and more available 📚RAG

blocksandfiles.com·2d

Embeddings & Vector Search 📚RAG

taoofmac.com·5d

On pgvectorscale, and Hybrid Search Without an Elasticsearch Sidecar 🌸Bloom Filters

thebuild.com·25m

neuml/txtai: 💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows 🤖LLM

Can agents replace the search stack? 🔧Agent Tooling

softwaredoug.com

·2d·Hacker News

When to Retrieve During Reasoning: Adaptive Retrieval for Large Reasoning Models 🔍Information Retrieval

Effective KV Compression with TurboQuant ℹ️Information Theory

machinelearningmastery.com·10h

RAG Vector Distance Calculator | Cosine Similarity & Euclidean Distance 📚RAG

fmtdev.dev·1d·DEV

When RAG Isn’t Enough: Moving from Retrieval to Relationship-Aware Systems in Enterprise AI: 📚RAG

techcommunity.microsoft.com·6d

Building with Gemini Embedding 2: Agentic multimodal RAG and beyond ✨Gemini

developers.googleblog.com·5h

AI 101: What’s So Magical About Embeddings? 🔢BitNet

turingpost.com·1d

GraphRAG beyond the demo: Lessons from the trenches (12 minute read) 🧠Obsidian

·22h

RAG precision tuning can quietly cut retrieval accuracy by 40%, putting agentic pipelines at risk 📚RAG

venturebeat.com·3d

Decoupling Knowledge and Task Subspaces for Composable Parametric Retrieval Augmented Generation 📚RAG

brunokeymolen/nn20db-sdk: million-scale vector search on small devices 🔌Embedded Systems

github.com·2d·Hacker News

Log in to enable infinite scrolling