> 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 6 
</div>


# Searching From Examples and Feedback

Some searches have no query text. A reader clicks "more like this", or an analyst has three documents that are right and two that are wrong and no words for what separates them.

The [Recommendation API](https://qdrant.tech/documentation/search/explore/index.md#recommendation-api) searches from positive and negative examples. The [Discovery API](https://qdrant.tech/documentation/search/explore/index.md#discovery-api) takes context pairs, where each pair names one region of the vector space to move toward and one to move away from.

When a better model or a click log disagrees with your ranking, [relevance feedback](https://qdrant.tech/documentation/search/search-relevance/index.md#relevance-feedback) folds that disagreement into the next query, across the whole collection. It needs a second model and three weights fitted to your own setup, so start with the tutorial below.

A point passed in by ID, whether as `example`, `positive`, `negative`, or a relevance feedback `target`, is left out of the results. Pass its raw vector instead to keep it eligible.

- [Recommendation API](https://qdrant.tech/documentation/search/explore/index.md#recommendation-api) and [Discovery API](https://qdrant.tech/documentation/search/explore/index.md#discovery-api): searching from examples and from context pairs.
- [Relevance Feedback](https://qdrant.tech/documentation/search/search-relevance/index.md#relevance-feedback): the query interface and what the `naive` strategy computes.
- [Relevance Feedback Retrieval in Qdrant](https://qdrant.tech/documentation/tutorials-search-engineering/using-relevance-feedback/index.md): fitting the weights and evaluating the result.