> 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

# Guides

Explore practical Qdrant guides for evaluating search quality, choosing embedding models, and planning multitenancy, bulk uploads, and memory use.

## [Search Evaluation](https://qdrant.tech/documentation/search-evaluation/index.md)

Evaluate Qdrant retrieval relevance and pipeline output quality with labeled queries, repeatable measurements, and checks for meaningful improvements.

- [Measuring Retrieval Relevance](https://qdrant.tech/documentation/search-evaluation/retrieval-relevance/index.md): Build a labeled query set and measure whether retrieved documents answer users' questions, with query-level relevance metrics.
- [Evaluating Pipeline Output Quality](https://qdrant.tech/documentation/search-evaluation/pipeline-output-quality/index.md): Separate retrieval failures from generation failures and evaluate whether your full pipeline produces supported, useful answers.

## [Search Patterns](https://qdrant.tech/documentation/search-patterns/index.md)

Design Qdrant search around your application by choosing embedding models, decomposing multi-hop queries, and filtering results with payload indexes.

- [How to Choose an Embedding Model: Evaluation & Tradeoffs](https://qdrant.tech/documentation/search-patterns/choose-embedding-model/index.md): There is no one-size-fits-all solution when it comes to embedding models. Learn how to choose the right one for your use case.
- [Query Decomposition for Multi-Hop Questions](https://qdrant.tech/documentation/search-patterns/query-decomposition/index.md): Answer multi-hop questions by retrieving in steps: an LLM asks each follow-up sub-question, then fuse the per-hop results with RRF.
- [A Complete Guide to Filtering in Vector Search](https://qdrant.tech/documentation/search-patterns/vector-search-filtering/index.md): Apply payload filters, build payload indexes, and combine conditions to narrow Qdrant search results to the right data.

## [Search Tuning](https://qdrant.tech/documentation/search-tuning/index.md)

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.

## [Production & Operations](https://qdrant.tech/documentation/production-operations/index.md)

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

- [Memory Tiers in Qdrant: What to Use and When](https://qdrant.tech/documentation/production-operations/memory-tiers/index.md): A guide to choosing a Qdrant memory tier layout as your collection grows.
- [Bulk Uploading Data to Qdrant](https://qdrant.tech/documentation/production-operations/bulk-data-import/index.md): Plan bulk uploads in Qdrant at scale: batching, parallelization, sharding, payload indexes, quantization, and on-disk storage.
- [How to Implement Multitenancy and Custom Sharding in Qdrant](https://qdrant.tech/documentation/production-operations/multitenant-search/index.md): Explore how Qdrant's multitenancy and custom sharding streamline machine-learning operations, enhancing scalability and data security.