AI Summary
→ WHAT IT COVERS Simon Eskildsen explains how TurboPuffer reduces vector database costs by 95% using object storage instead of memory, enabling companies like Cursor and Notion to scale AI search economically at 2¢ per gigabyte. → KEY INSIGHTS - **Storage architecture economics:** TurboPuffer uses S3 object storage at 2¢ per gigabyte versus traditional in-memory vector databases at $2-5 per gigabyte, achieving 100x cost reduction while maintaining sub-second query performance through strategic caching layers. - **Cluster-based indexing for disk:** Graph-based vector indexes require hundreds of milliseconds per jump on S3, making them impractable. Cluster-based indexes fetch centroids and clusters in just three round trips, enabling cold queries under one second on object storage. - **Production recall monitoring:** TurboPuffer samples 1% of production queries to measure recall accuracy against exact results, maintaining 90-95% recall across real-world datasets. This catches edge cases that academic benchmarks miss, ensuring consistent search quality at scale. - **Namespace sharding primitive:** TurboPuffer maps each namespace to one shard with separate S3 prefixes, supporting over 100 million namespaces. Each namespace can use customer-managed encryption keys, providing isolation equivalent to separate buckets without coordination overhead. → NOTABLE MOMENT Eskildsen discovered the vector database cost problem when calculating that storing Readwise article embeddings would cost $30,000 monthly versus $3,000 for their entire Postgres database, revealing a 10x cost amplification blocking AI feature adoption. 💼 SPONSORS [{"name": "Capital One", "url": null}, {"name": "Redis", "url": "redis.io/genai"}, {"name": "Stream", "url": "getstream.io/podcast"}] 🏷️ Vector Databases, Database Architecture, Object Storage, AI Infrastructure