> For the complete documentation index, see [llms.txt](https://docs.nexthink.com/platform/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.nexthink.com/platform/user-guide/administration/ai-resources/managing-knowledge-sources.md).

# Knowledge management

Configure knowledge sources for Nexthink Spark and Workspace to generate responses grounded in your organization's internal knowledge base (KB). Import KB articles as CSV files, or connect to a live external system, then classify and manage each source from one central location.

{% hint style="info" %}
Knowledge source configuration is shared between **Spark** and **Workspace**, meaning configured knowledge base sources become available to both.

* Refer to [Understanding Spark data inputs](/platform/user-guide/spark/setting-up-and-managing-spark/managing-spark-data-inputs.md) for information on how Spark uses knowledge sources.
* Refer to [Using Workspace](https://docs.nexthink.com/platform/user-guide/search-and-workspace/using-workspace#troubleshooting-it-incidents) for information on how Workspace uses knowledge sources.
  {% endhint %}

## Accessing Knowledge management

Select **Administration > Knowledge management** from the navigation panel.

<figure><img src="/files/0Bt0hW0BLzU5KDMQBw1e" alt=""><figcaption></figcaption></figure>

***

## Connecting Nexthink to knowledge sources

To connect Nexthink to knowledge sources, follow one of these options:

* **Import knowledge sources** from a CSV file.
* Use **New connector** to connect to a live external system.

Refer to the procedures described on this page for details.

### Connecting to a live external knowledge source

From the top right corner of the **Knowledge management** page, use **New connector** to connect to a live external system, such as ServiceNow, instead of manually importing a CSV file.

In addition, from the action menu of the **New connector** button, you may directly access:

* The ServiceNow **Request catalog** connector configuration. Refer to [ServiceNow Request Catalog connector](/platform/configuring_nexthink/bringing-data-into-your-nexthink-instance/integrating-nexthink-with-third-party-tools/inbound-connectors/connector-for-servicenow-request-catalog.md) for connector setup.
* The ServiceNow **Knowledge Base** connector configuration. Refer to [ServiceNow Knowledge Base connector](/platform/configuring_nexthink/bringing-data-into-your-nexthink-instance/integrating-nexthink-with-third-party-tools/inbound-connectors/connector-for-servicenow-knowledge-base.md) for connector setup.

{% hint style="info" %}
The system automatically references the Nexthink knowledge base when troubleshooting issues with Nexthink itself—no configuration is required for this source.
{% endhint %}

<figure><img src="/files/8roYg4IbRFWPgcxogEgm" alt=""><figcaption></figcaption></figure>

### Importing a knowledge source from a CSV file

Each imported CSV file is treated as an independent knowledge source and is processed independently. Multiple knowledge sources can coexist.

The following procedure uses ServiceNow as an example; however, on a high level, the process is similar in other ITSM platforms.

{% stepper %}
{% step %}

#### **Identify data to export from your ITSM**

1. Open the list of knowledge base articles in your ITSM. In this case, ServiceNow.
2. Select knowledge base articles by applying these filters:
   * **Published** articles only.
   * Articles available to your service desk users.
   * Exclude translated versions of the same article.
   * Include every article you want to import.

{% hint style="warning" %}
Workspace and Spark index every uploaded article regardless of ITSM permissions.
{% endhint %}
{% endstep %}

{% step %}

#### **Export data from your ITSM**

Export data from your ITSM, in this case ServiceNow, by performing a standard CSV export:

1. Navigate to your knowledge base articles list.
2. Click **Apply filter** to configure the desired filters.
3. Click the **cogwheel icon > Personalize list**.
4. Include the following columns in the CSV, using the exact case-sensitive column names listed in the table below.
5. Click the action menu in any column header and select **Export > CSV** to download the file.

{% hint style="warning" %}
Ensure the file is UTF‑8 encoded. If your ServiceNow instance is not configured to perform UTF-8 exports by default, convert the file to UTF-8 afterward.
{% endhint %}

<table><thead><tr><th width="212.16668701171875">Column name</th><th>Description</th></tr></thead><tbody><tr><td><code>number</code></td><td>Identifier of the knowledge base article.<br>Example: <code>KB0012345</code></td></tr><tr><td><code>short_description</code></td><td>Title of the knowledge base article.<br>Example: <code>How to troubleshoot network issues</code></td></tr><tr><td><code>kb_knowledge_base</code></td><td>Name of the knowledge base the article belongs to<br>Example: <code>IT Knowledge</code></td></tr><tr><td><p><code>kb_category</code></p><p>(optional)</p></td><td>Category of the knowledge base article.<br>Example: <code>Network</code></td></tr><tr><td><p><code>sys_updated_on</code></p><p>(optional)</p></td><td>Last update date.<br>Example: <code>11-06-2025</code></td></tr><tr><td><code>text</code></td><td>Article content, in one of the supported formats: plain-text, markdown or HTML.<br>Example: <code>&#x3C;p>test kb&#x3C;/p></code></td></tr></tbody></table>
{% endstep %}

{% step %}

#### Upload the CSV file to Nexthink

In Nexthink, **Import knowledge sources** from the top-right corner of the **Knowledge managemen**t page.

<details>

<summary>Enter the source URL</summary>

Provide a full, parameterized URL that links to individual knowledge articles in your knowledge system, including a placeholder for the article identifier. Root-only hostnames aren't supported: `https://example.company.com/path/to/item/{number}`

URL examples:

* ServiceNow: `https://<instance>.service-now.com/sp?id=kb_article&sysparm_article={number}`
* BMC Helix: `https://<instance>.onbmc.com/portal/kb/article/{number}`
* JSM: `https://<instance>.atlassian.net/servicedesk/customer/kb/view/{number}`

<figure><img src="/files/dM64S4Xg41nPb1UtZP7S" alt=""><figcaption></figcaption></figure>

</details>

<details>

<summary>Upload the CSV file</summary>

Drag and drop your CSV file into the upload area, or **Choose file** to browse—up to 100 MB per file. Each row in the file represents one knowledge article.

<figure><img src="/files/QbsDcTdQlYusYDfcQB8h" alt=""><figcaption></figcaption></figure>

After choosing a CSV file, the dialog displays the file name and size, define the **Target group**:

* **Technical support**: Users responsible for diagnosing and resolving IT issues.
* **Employee**: End users consuming IT services for their daily work.

If an error occurs during import, the dialog displays a warning message. Check your file and retry the import.

{% hint style="success" %}
Once the import succeeds, the system validates the file and displays a confirmation indicator.
{% endhint %}

<figure><img src="/files/TfMrPG1Vas3L7oTfzDbk" alt=""><figcaption></figcaption></figure>

</details>

File processing occurs asynchronously and may take up to 15 minutes for large knowledge bases.

<figure><img src="/files/0y6MJXY08vRw83YQdVKB" alt=""><figcaption></figcaption></figure>

{% hint style="warning" %}
Manual uploads are not incremental. When uploading a new CSV file into Nexthink, the new content replaces the previous content.
{% endhint %}
{% endstep %}
{% endstepper %}

#### Updating manually imported knowledge sources

To ensure Nexthink Spark and Workspace always have a knowledge base available, even when the system is processing a new version of a knowledge source file, Nexthink recommends the following order:

1. Upload the updated knowledge source file while still leaving the old one in the system.
2. Once the new knowledge source file is processed, delete the old file.

{% hint style="info" %}
Nexthink recommends the following best practices to improve the selection of knowledge base articles:

* Keep articles current and up to date.
* Use HTML formatting for optimal results.
* Include key information in the article body text.
  {% endhint %}

***

## Managing knowledge sources

The **Knowledge management** page lists every imported or connected knowledge source. Each table row shows:

* **Name:** the CSV file name or connector name.
* **Origin:** how the source was added. Imported and connected sources both show as **Custom**.
* **Target group:** The intended audience of the knowledge source. AI agents use this attribute during search and ranking to surface the most relevant content based on context:
  * **Employee**: end-user-facing knowledge Spark or Workspace can expose to the employee.
  * **Technical support**: IT or support-facing knowledge Spark or Workspace uses for troubleshooting.
* **Type:** **Connector** or **File**, depending on how the source was added.
* **Size**: the number of articles in the CSV. The system can also display the following statuses:
  * **Failed**: if the file cannot be processed, for example, if it contains a syntax error. In this case, hover over the error message to see more details and a remediation proposal.
  * **Processing**: if the file contains many articles, it may take the system time to process.
* **Last update:** when the source was last imported or synced—helps to assess if an article is up to date.

<figure><img src="/files/b16F84PKfUOVfqXLoCSO" alt=""><figcaption></figcaption></figure>

From the table, hover over a knowledge source to reveal the action menu on the right side of the row. Depending on the knowledge source type, you can:

* **Edit:** update the settings of an existing knowledge source.
* **Export**: Download the original CSV file corresponding to the last successful import. Each knowledge source CSV file can be exported only individually.
* **Delete**: Permanently remove a previously uploaded CSV and all knowledge articles associated with that knowledge source.

<figure><img src="/files/efYF7Es9VjcapL3FtW2C" alt=""><figcaption></figcaption></figure>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://docs.nexthink.com/platform/user-guide/administration/ai-resources/managing-knowledge-sources.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.