🕸️ HNSW - emschwartz · Scour

Nested Vectors Search in Apache Lucene 📇Vector Indexing

The Postgres Developer's Guide to Vector Index Tradeoffs 🌲GIN Indexes

tigerdata.com·3d

Researchers Debate Transformer Vs Post-Transformer Architectures In Boxing Ring 🏆LLM Benchmarking

A Double Shot of DuckDB 🔍Paradedb

peterdohertys.website·1d·Hacker News

LLMs in Production and Semantic Search Engine, Tue, Apr 4, 2023, 5:00 PM 🏗️LLM Infrastructure

meetup.com·21h

SQLiteGraph – embedded graph database with HNSW vector search 🗄LiteFS

github.com·4d·Hacker News

A disk-first C++ vector engine ⚡Vectorized Execution

news.ycombinator.com·1d·Hacker News

AI-native database (vector, graph, SQL, AutoML, LLM) 🎨Chroma

synapcores.com·4d·Hacker News

SurrealDB 3.1: stability, DiskANN, and a new release process | Blog 🪨RocksDB

surrealdb.com·2d·Hacker News

How CockroachDB Built Vector Indexing at Scale 🗂️Vector Indexes

blog.bytebytego.com·4d

Building OmniPulse’s Rust Core: FFI Bridges, Optimal Transport, and a Real MCP Server 🔬Rust Profiling

pub.towardsai.net

·3d

Barycentric Simplicial Hashing for Approximate Nearest Neighbor Search: A Four-State Topological Hash Competitive with Industry-Standard Product Quantization at Half the Memory 🔍Vector Search Algorithms

zenodo.org·3d·Hacker News

grep vs. RAG: Choosing the Right Search Strategy for AI Agents 🏗️Search Infrastructure

llamaindex.ai·3d·Hacker News

Generalized Range Filtering Approximate Nearest Neighbor Search: Containment and Overlap [Technical Report] 🔍Vector Search Algorithms

vitaliyfedotovpro-art/astrum-verum: Composition-episodic cognitive memory for AI agents (VSA + lattice geometry) 🧠Agent Memory

github.com·4d·Hacker News

Co-Designing Graph-based Approximate Nearest Neighbor Search at Billion Scale for Processing-in-Memory 📏ANN Benchmarks

0xJaksun/lithium-core: Hierarchical versioned storage on PostgreSQL ltree. Scoped retrieval, built-in versioning, zero runtime deps. 💚Neon

github.com·3d·DEV, Hacker News

Agent Memory with Vector Stores: HNSW, Forgetting, and Budgets 🧠Agent Memory

pub.towardsai.net

·6d

CS-PQ: Cache-Friendly SIMD Product Quantization for Large-Scale ANNS Index Construction 📏ANN Benchmarks

Build an AI Contract Intelligence System: OCR + Hybrid RAG + LangGraph to Extract Key Terms… 🔤Tokenization

pub.towardsai.net

·5d

No more posts from emschwartz's subscribed feeds.

Scour all 24820 feeds Learn more about Feeds

Log in to enable infinite scrolling