# Improve Search

*Embedding choice, chunking strategies, and retrieval evaluation using Python ecosystem tools.*

| Tutorial | Objective | Stack | Time | Level |
| :--- | :--- | :--- | :--- | :--- |
| [Measuring Retrieval Relevance](https://qdrant.tech/documentation/improve-search/retrieval-relevance/index.md) | Build a labeled golden set and score retrieval relevance with ranx. | <span class="pill">Python</span> | 40m | <span class="text-yellow">Intermediate</span> |
| [Evaluating Pipeline Output Quality](https://qdrant.tech/documentation/improve-search/pipeline-output-quality/index.md) | Score a RAG pipeline with Ragas and isolate retrieval vs generation failures. | <span class="pill">Python</span> | 45m | <span class="text-yellow">Intermediate</span> |
| [Query Decomposition for Multi-Hop Questions](https://qdrant.tech/documentation/improve-search/query-decomposition/index.md) | Answer multi-hop questions by retrieving in steps, with an LLM asking the next sub-question. | <span class="pill">Python</span> | 15m | <span class="text-yellow">Intermediate</span> |