> Explore Qdrant's agent skills catalog at https://skills.qdrant.tech/
> Search the documentation at https://skills.qdrant.tech/search?query=your+query+here
> Use this file to discover all available pages: https://qdrant.tech/llms.txt

# Search Tuning

Tune Qdrant retrieval with measured changes to candidate depth, hybrid fusion, reranking, and memory use. Follow the six-part series in order.

- [Hybrid Search in Qdrant](https://qdrant.tech/documentation/search-tuning/hybrid-search/index.md): Run dense and sparse retrieval together: the queries each one gets wrong, what the second index costs, and how to tell if it helped.
- [What to Check Before Tuning a Qdrant Collection](https://qdrant.tech/documentation/search-tuning/before-tuning-a-qdrant-collection/index.md): Seven collection settings that degrade retrieval without an error, the order to try changes in, and how many labeled queries a gain needs.
- [Candidate Depth: How Much Retrieval Is Enough?](https://qdrant.tech/documentation/search-tuning/candidate-depth/index.md): Raising candidate depth raises the best score a later ranking stage could reach, but default fusion barely used that extra room.
- [How to Tune Hybrid Search in Qdrant](https://qdrant.tech/documentation/search-tuning/how-to-tune-hybrid-search/index.md): Tune hybrid search with RRF or DBSF, choose k from relevance labels, and learn why weights are pairs instead of ratios.
- [When Is a Reranker Worth It?](https://qdrant.tech/documentation/search-tuning/when-a-reranker-is-worth-it/index.md): Rerank 10 candidates, compare with your tuned first stage on held-out queries, and raise the count only after the win holds.
- [When Your Collection Outgrows RAM](https://qdrant.tech/documentation/search-tuning/when-your-collection-outgrows-ram/index.md): Keep the quantized copy in RAM and the original vectors on disk, then measure what rescoring reads back on your own deployment.