# Relevance Tuning

### Overview

Relevance tuning enables administrators to fine-tune the weighting of various factors influencing search results, ensuring that users can swiftly locate the most pertinent information. Within this section, administrators gain granular control over the factors influencing the relevance of search results, enabling them to tailor the search experience to meet the specific needs of their organization.

<figure><img src="/files/Wk06WGKPVtEPFJboyvrW" alt="" width="563"><figcaption></figcaption></figure>

***

### Relevance Ranking

Relevance settings allow administrators to rank the importance of different properties that impact search result prioritization. These properties include:

* **Title**: The presence of the search term in the title field of an item influences its ranking in search results. Administrators can configure the weight assigned to this boost, encompassing page titles, file names, post titles, and wiki names.
* **Hashtag**: Detection of the search term within the assigned hashtags enhances an item's prominence in search results. Administrators can adjust the weight assigned to hashtags to fine-tune their impact on search relevance.
* **Meta Data**: Search term discovery within item metadata, including descriptions, properties, and custom fields, influences the item's position in search results. Administrators can configure the weight assigned to metadata to optimize search relevance.
* **From User**: Prioritizing content posted by specific users elevates their items in search results. Administrators can assign weights to users to control their impact on search relevance.
* **Time**: Administrators can prioritize recent items in search results by adjusting the weight assigned to time relevance.
* **Content**: The presence of the search term within item content boosts its position in comprehensive search results. Administrators can fine-tune the weight assigned to content relevance for optimal search performance.

Both predictive look-ahead and full search results consider the weights set by the admin to tune the relevancy of search results.

For ease of management, administrators can reset relevance settings to the recommended system defaults or make adjustments as needed.&#x20;

Clicking **Save** applies any changes made to the relevance tuning configuration, ensuring that the updated settings are reflected in search results.

***

### FAQ

**Q: How does AI Search determine and rank results? Can we weigh search results similarly to our internal advanced search?**

**A:**  AI Search retrieves the top 10 results based on predefined ranking factors and generates a summary from them. While the weights defined in the system influence the results indirectly, there is no additional manual control or setting to adjust the ranking or weighting beyond what is already configured in the system.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://guides.mangoapps.com/admin-guide/search/relevance-tuning.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.