This article explores the technical challenges and unexpected interactions encountered while tuning Approximate Nearest Neighbor (ANN) indexing for a massive 100 million document retrieval system.
The authors detail how instruction-aware query embeddings corrected significant biases toward short documents and analyze the relationship between graph connectivity, search depth, and latency. They also demonstrate how quantization sets an absolute ceiling on recall that cannot be overcome by index tuning alone.
The authors detail how instruction-aware query embeddings corrected significant biases toward short documents and analyze the relationship between graph connectivity, search depth, and latency. They also demonstrate how quantization sets an absolute ceiling on recall that cannot be overcome by index tuning alone.
A from-scratch reimplementation of Stanford's XTR-Warp semantic search engine written in safe Rust. It is designed for client-side deployment, utilizing a single-file SQLite database for storage without the need for external API keys, vector databases, or complex chunking strategies. The engine offers high performance with extremely low end-to-end search latency and supports hybrid search by combining semantic results with standard BM25 functionality.
Key features and components:
- High-speed semantic search capable of running on local devices.
- SQLite backend for easy data persistence and portability.
- Support for various backends including T5 quantized weights via candle and OpenVINO.
- Pickbrain CLI example for indexing AI coding session transcripts (Claude Code/OpenAI Codex).
- Hardware acceleration support for Apple Silicon (Metal) and x86 (fbgemm).
- Available as a Node.js native module.
Key features and components:
- High-speed semantic search capable of running on local devices.
- SQLite backend for easy data persistence and portability.
- Support for various backends including T5 quantized weights via candle and OpenVINO.
- Pickbrain CLI example for indexing AI coding session transcripts (Claude Code/OpenAI Codex).
- Hardware acceleration support for Apple Silicon (Metal) and x86 (fbgemm).
- Available as a Node.js native module.
Zvec is engineered for speed, scale, and efficiency — and has been battle-tested across demanding production workloads within Alibaba Group. This page presents benchmark results demonstrating Zvec's performance under various workloads and configurations, using VectorDBBench with Cohere 1M and 10M datasets.
Zvec is an open-source, in-process vector database — lightweight, lightning-fast, and designed to embed directly into applications. Built on Proxima (Alibaba's battle-tested vector search engine), it delivers production-grade, low-latency, scalable similarity search with minimal setup.
This post explores how to solve challenges in vector search using NVIDIA cuVS with the Meta Faiss library. It covers the benefits of integration, performance improvements, benchmarks, and code examples.
This article details the process of building a fast vector search system for a large legal dataset (Australian High Court decisions). It covers choosing embedding providers, performance benchmarks, using USearch and Isaacus embeddings, and the importance of API terms of service. It focuses on achieving speed and scalability while maintaining reasonable accuracy.
Turso is the small database for your biggest ideas. The most efficient way to build for apps, AI, agents, and everything in between. It's an embedded database engine that goes anywhere, offering features like vector search, async design, and SQLite compatibility.
An article detailing the reasons for creating Turso, a Rust-based rewrite of SQLite, addressing limitations in performance, modern features, and contribution model.
This article explains the internal workings of vector databases, highlighting that they don't perform a brute-force search as commonly described. It details algorithms like HNSW, IVF, and PQ, the tradeoffs between recall, speed, and memory, and how different RAG patterns impact vector database usage. It also discusses production challenges like filtering, updates, and sharding.
sqlite-vec is an extremely small, 'fast enough' vector search SQLite extension designed to run anywhere. It allows storing and querying of float, int8, and binary vectors using virtual tables, written in pure C with no dependencies. It supports storing non-vector data in metadata, auxiliary, or partition key columns. It is a Mozilla Builders project with additional sponsorship from companies like Fly.io, Turso, SQLite Cloud, and Shinkai.
