> 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 3 
</div>


# References and Further Reading

- [Hybrid Queries](https://qdrant.tech/documentation/search/hybrid-queries/index.md): prefetch semantics, both fusion strategies, and their tuning parameters.
- [Understanding SPLADE and Sparse Vectors](https://qdrant.tech/articles/sparse-vectors/index.md): how sparse vectors work and how SPLADE compares to BM25.
- [miniCOIL: Sparse Neural Retrieval](https://qdrant.tech/articles/minicoil/index.md): why miniCOIL exists and how it extends BM25 with contextual meaning.
- [Filtering](https://qdrant.tech/documentation/search/filtering/index.md): full filter syntax and the payload index each condition needs.
- [Named Vectors](https://qdrant.tech/documentation/manage-data/vectors/index.md#named-vectors): configuring and querying more than one vector on a single point.

## What's Next: Module 4

Eight products rebuild in seconds. On a collection that takes hours to embed, one wrong decision means embedding everything again.

Module 4 designs a global news system decision by decision: what you can change on a live collection, what forces you to start over, and where Qdrant runs, from Docker to Edge.