Qdrant Guides

Practical guidance for search quality, embedding models, multitenancy, bulk uploads, and memory use.

Recently Published

A guide to choosing a Qdrant memory tier layout as your collection grows.

Run dense and sparse retrieval together: the queries each one gets wrong, what the second index costs, and how to tell if it helped.

Keep the quantized copy in RAM and the original vectors on disk, then measure what rescoring reads back on your own deployment.

Open a guide directly, or explore a topic for related examples and references.

Measure retrieval relevance and pipeline output quality to establish a baseline and decide whether a search change helps.

Choose embedding models, plan query decomposition, and apply payload filters to build search around your data and application needs.

Tune candidate depth, fusion, reranking, and memory against your search goals, following the complete retrieval tuning series.

Plan multitenancy, bulk uploads, and memory placement as your Qdrant application and vector collection grow.