Making AI search fast
I help teams build fast search over unstructured data: vector databases, RAG pipelines, and over a decade of web performance craft.
Migrating Self-managed Milvus to Managed Milvus to gain >99% Performance
At small scale, self-managing a vector database is manageable. Once you're in the tens of millions of embeddings you'll probably want to offload the headache to a managed service.
Milvus 3.0: Closing the Search Gap
Milvus 3.0 bundled a host of features that closed the search gap - one database for vectors, text search, and everything else! In this talk I cover the key updates backed up by a live side-by-side of Milvus 3.0 vs. Elasticsearch 9.14. Query semantics, results, performance - all reproducible with an open source framework.
More in the blog and the talk archive.