#Qdrant
7 posts
How neural search evolved beyond keywords, why intent is hard to capture on the first pass, and how Qdrant's native relevance feedback closes that gap.
Build a multimodal search stack with Gemini 2 embeddings and Qdrant, using MRL to reduce storage costs.
Slicing is all you need.
How quantization can reduce memory usage by 32x without losing accuracy using Qdrant.
Learn how to build efficient multi-tenant AI applications using Qdrant, from payload-based filtering to advanced tiered multitenancy for high-volume users.
Vector search changed the game entirely, and Qdrant is making it ridiculously easy to implement. It understands meaning, not just exact words.
Ever wondered how Spotify knows exactly what song you'll love next?