AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
4min snip
Open source, on-disk vector search with LanceDB
Practical AI: Machine Learning, Data Science, LLM
Separation of Compute and Storage in Data Architecture
The separation of compute and storage allows for the scaling up of storage and compute separately, enabling systems to process huge amounts of data using seemingly weak compute resources. This separation is achieved through a columnar format paired with an index, such as a vector index, allowing for fast random access and scan. The new columnar format like lands provides the ability for fast random access and fast scans, essential for interactive query performance. This separation is made possible by the underlying data architecture, which supports storing vectors and data. The data architecture relies on wide tables in columnar format and an index, while the connection between the index and columnar format enables fast random access and query performance. Additionally, the core of the data format and the vector database is implemented in Rust, which is also used to build embedded databases in JavaScript.
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any
moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share
& Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode