# Searching in ZSearch

### How to run a search in ZSearch <a href="#how-to-run-a-search-in-zsearch" id="how-to-run-a-search-in-zsearch"></a>

ZSearch allows users to search across enterprise knowledge that has been indexed and made available through the enterprise context configured in ZBrain Builder. All searches are executed within the scope of approved data sources and respect existing access permissions.

This section explains how to run a search and interpret results in ZSearch.

#### Search scope and enterprise context <a href="#search-scope-and-enterprise-context" id="search-scope-and-enterprise-context"></a>

Every search in ZSearch is performed against the enterprise context defined by your organization. This context includes:

* Knowledge bases created from connected data sources
* Knowledge bases created from uploaded files
* Indexed and synchronized enterprise content

Users can only search and retrieve information from knowledge bases they are authorized to access.

#### Starting a search <a href="#starting-a-search" id="starting-a-search"></a>

To run a search:

1. Open the ZSearch panel
2. Locate the search input field on the home screen
3. Enter a search query using keywords or natural language
4. Click the search icon or press Enter

<figure><img src="/files/wpIyXkhWld1EEX9GrBtg" alt=""><figcaption></figcaption></figure>

ZSearch immediately processes the query and retrieves relevant results from the indexed enterprise knowledge.

<figure><img src="/files/H66byFE8IwRls4dPyyXE" alt=""><figcaption></figcaption></figure>

#### Types of queries supported <a href="#types-of-queries-supported" id="types-of-queries-supported"></a>

ZSearch supports multiple query styles:

* **Keyword searches**\
  Example: `vendor contract renewal`
* **Natural language questions**\
  Example: `Which contracts are expiring next quarter?`
* **Contextual queries**\
  Example: `Find the budget report from last Q3`

ZSearch interprets intent, applies relevance ranking, and returns results that best match the query.

#### Understanding search results <a href="#understanding-search-results" id="understanding-search-results"></a>

Search results are displayed as a list of documents that match the query. Each result represents a full document from the enterprise knowledge base.

Each search result typically includes:

* Document name or title
* Source and last updated information
* A brief content snippet for context
* A match score. The match score represents how closely a document matches the search query based on semantic and contextual relevance.

  Key points about match scores:

  * Scores are expressed as percentages
  * Higher scores indicate stronger relevance to the query
  * Scores are calculated based on semantic similarity and relevance signals

  Match scores help users quickly assess which documents are most likely to contain the information they are looking for.

<figure><img src="/files/psVnEs3lcI5AP6i4u0rC" alt=""><figcaption></figcaption></figure>

#### Search history <a href="#search-history" id="search-history"></a>

ZSearch automatically maintains a search history for each user. Search history is displayed in the left navigation panel under **Search history**.

<figure><img src="/files/dhfiu6VIWFzIKb9gAavp" alt=""><figcaption></figcaption></figure>

Search history allows users to:

* View previous search queries
* Quickly rerun a recent search by selecting it
* Return to earlier topics without retyping queries

Key points about search history:

* Search history is user-specific
* Other users cannot view your search history
* Selecting a query from history reloads its corresponding results

Search history improves efficiency when working across recurring topics or ongoing research.

#### Best practices for effective search <a href="#best-practices-for-effective-search" id="best-practices-for-effective-search"></a>

* Use specific terms when searching for known documents
* Use natural language questions when exploring topics
* Review match scores to prioritize highly relevant results
* Start a new search when switching topics

After identifying relevant documents, you can group them into projects for focused collaboration and deeper exploration.

Continue to:

* **Creating a project in ZSearch**


---

# 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://docs.zbrain.ai/zbrain-documentation/zbrain-zsearch/searching-in-zsearch.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.