Pgvecto.rs adopted a design akin to FreshDiskANN, resembling the Log-Structured Merge (LSM) tree concept. This architecture comprises three components: the writing segment, the growing segment, and the sealed segment. New vectors are initially written to the writing segment. A background process then asynchronously transforms them into the immutable growing segment. Subsequently, the growing segment undergoes a... - Source: dev.to / 3 months ago

If you saw my recent newsletter you can see I joined Zilliz to work on the Open Source AI Database, Milvus. - Source: dev.to / 5 days ago

If you find yourself unsure about the optimization process, leverage the power of benchmarking tools like VectorDBBench. This tool, developed and open-sourced by Zilliz, can evaluate all mainstream vector databases. It allows you to conduct comprehensive experiments and fine-tune your system for optimal performance. - Source: dev.to / about 1 month ago

Last week I celebrated my first year at Zilliz 🎉, the startup behind the open source vector database Milvus, in the heart of the AI boom. Somehow, the year has been both the shortest and longest year of my 17 years in the software industry. It seems like a prudent time to stop, catch my breath, and reflect on what I’ve learned. - Source: dev.to / 4 months ago

Zilliz is a powerful vector database designed to empower developers and data scientists in building the next generation of AI and search applications. It offers a robust platform for scalable, efficient, and accurate vector search and analytics, supporting a wide array of AI-driven applications. - Source: dev.to / 4 months ago

As an open-source and self-hosted solution, developers can deploy their own version of the plugin and register it with ChatGPT. The plugin leverages OpenAI embeddings and allows developers to choose a vector database (Milvus, Pinecone, Qdrant, Redis, Weaviate or Zilliz) for indexing and searching documents. Information sources can be synchronized with the database using webhooks. Source: 11 months ago