> 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

<div class="date">
  <img class="date-icon" src="/icons/outline/date-blue.svg" alt="Calendar" />  Module 2 
</div>


# Further Reading

- [Distance Metrics](https://qdrant.tech/course/essentials/day-1/distance-metrics/index.md) A closer look at cosine similarity, dot product, Euclidean, and Manhattan, and when each one fits.
- [What Is HNSW](https://qdrant.tech/course/essentials/day-2/what-is-hnsw/index.md) How the graph index is built and tuned, once you have real searches to measure it against.
- [Filtering](https://qdrant.tech/documentation/search/filtering/index.md) The full filter syntax, including range, geo, and nested conditions.
- [Payload Indexing](https://qdrant.tech/documentation/manage-data/indexing/index.md#payload-index) The available payload index types and how to configure them.
- [Chunking Strategies](https://qdrant.tech/course/essentials/day-1/chunking-strategies/index.md) The full comparison of fixed-size, semantic, and sliding-window chunking, with worked examples.

## What's Next: Module 3

Dense vectors capture meaning well, but they can miss exact keyword matches such as product codes or model numbers. Module 3 introduces sparse vectors, which complement dense vectors by capturing exact terms and keywords. You'll learn how to combine both in a single hybrid search query.