Engineering posts about Vector Database
Curated summaries and key learnings for engineers working with Vector Database.
What is pgvector?
pgvector is an open-source PostgreSQL extension designed to facilitate vector storage and similarity search directly within Postgres, eliminating the need for separate vector databases for AI...
AI Search: the search primitive for your agents
The article discusses AI Search, a search primitive designed for coding agents that need to retrieve relevant information from various data sources efficiently. It highlights the architecture of AI...
AiChemy: Next-Generation Agent with MCP, Skills and Custom Data for Drug Discovery
The article introduces AiChemy, a multi-agent system designed for drug discovery that leverages the Model Context Protocol (MCP) to integrate external knowledge bases such as OpenTargets, PubChem,...
From Legacy to Lakehouse: How Mazda Accelerated GenAI for Technical Service Operations
Mazda has successfully transitioned to a GenAI framework using Databricks Lakehouse, integrating various data sources such as service history and diagnostic documents to enhance the efficiency of...
Decoupled by Design: Billion-Scale Vector Search
The article discusses the challenges and solutions in building a billion-scale vector search system at Databricks. It highlights the limitations of traditional vector databases that couple storage...
How 7‑Eleven Transformed Maintenance Technician Knowledge Access with Databricks Agent Bricks
The article details how 7-Eleven transformed its maintenance operations by implementing an AI-powered Technician's Maintenance Assistant (TMA) built on Databricks. This solution significantly reduced...
Amazon S3 Vectors now generally available with increased scale and performance
Amazon S3 Vectors has been launched with enhanced capabilities for storing and querying vector data, allowing users to handle up to 2 billion vectors in a single index. The service boasts improved...
Amazon OpenSearch Service improves vector database performance and cost with GPU acceleration and auto-optimization
Amazon has introduced significant enhancements to the OpenSearch Service, enabling serverless GPU acceleration and auto-optimization for vector databases. These features allow developers to build...