> For the complete documentation index, see [llms.txt](https://docs.ovaledge.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ovaledge.com/release8.2/connectors/connector-repositories/file-connectors/hdfs-hadoop-distributed-file-system.md).

# HDFS (Hadoop Distributed File System)

This article outlines the integration with the HDFS (Hadoop Distributed File System) connector, enabling streamlined metadata management through features such as crawling, data preview, and manual lineage building. The connector collects metadata from files and folders stored in HDFS and makes it available for cataloging and metadata management within OvalEdge.

This connector connects to HDFS using the Hadoop SDK and retrieves metadata from configured file system locations. It supports both Kerberos and Non-Kerberos authentication methods, enabling access to HDFS resources based on the deployment configuration. Authentication is established using a service account with the permissions required to access HDFS files and folders and retrieve metadata from the selected locations.

<figure><img src="/files/k5FKRXZcmOzq5ornXz4i" alt=""><figcaption></figcaption></figure>

## Overview

### Connector Details

| Connector Category                                                       | File System         |
| ------------------------------------------------------------------------ | ------------------- |
| OvalEdge Release Supported                                               | Relase4.0 and later |
| <p>Connectivity</p><p>\[How the connection is established with HDFS]</p> | Hadoop SDK          |
| Verified HDFS Version                                                    | v6.0+               |

{% hint style="info" %}
The HDFS connector has been validated with the mentioned "Verified HDFS Versions" and is expected to be compatible with other supported HDFS versions. If there are any issues with validation or metadata crawling, please submit a support ticket for investigation and feedback.
{% endhint %}

### Connector Features

| Feature                                      | Availability |
| -------------------------------------------- | :----------: |
| Crawling                                     |       ✅      |
| Delta Crawling                               |       ❌      |
| Profiling                                    |       ❌      |
| Sample Profiling                             |       ✅      |
| Query Sheet                                  |       ❌      |
| Data Preview                                 |       ✅      |
| Auto Lineage                                 |       ❌      |
| Manual Lineage                               |       ✅      |
| Secure Authentication via Credential Manager |       ✅      |
| Data Quality                                 |       ❌      |
| DAM (Data Access Management)                 |       ❌      |
| Bridge                                       |       ✅      |

### Metadata Mapping

The following objects are crawled from HDFS and mapped to the corresponding UI assets.

<table><thead><tr><th width="145.25">HDFS Object</th><th width="148.75">HDFS Attribute</th><th width="176">OvalEdge Attribute</th><th width="174">OvalEdge Category</th><th width="148">OvalEdge Type</th></tr></thead><tbody><tr><td>File/Folder</td><td>Folder</td><td>Folder</td><td>Folder</td><td>Folder</td></tr><tr><td>File/Folder</td><td>File</td><td>File</td><td>File</td><td>File</td></tr><tr><td>File</td><td>XLSX with sheets</td><td>File (Subfile)</td><td>File (Subfile)</td><td>File</td></tr><tr><td>File</td><td>XLS with sheets</td><td>File (Subfile)</td><td>File (Subfile)</td><td>File</td></tr><tr><td>File</td><td>CSV</td><td>File</td><td>File</td><td>File</td></tr><tr><td>File</td><td>TXT</td><td>File</td><td>File</td><td>File</td></tr><tr><td>File</td><td>PARQUET</td><td>File</td><td>File</td><td>File</td></tr><tr><td>File</td><td>ORC</td><td>File</td><td>File</td><td>File</td></tr><tr><td>File</td><td>JSON</td><td>File</td><td>File</td><td>File</td></tr><tr><td>File</td><td>YAML</td><td>File</td><td>File</td><td>File</td></tr><tr><td>File</td><td>PIP</td><td>File</td><td>File</td><td>File</td></tr></tbody></table>

## Set up a Connection

### Prerequisites

The following are the prerequisites to establish a connection.

Ensure that the CSV files follow the required formatting standards for proper data processing and visibility. Refer to [CSV Format Requirements](https://docs.ovaledge.com/connectors/additional-requirements/csv-format-requirements-for-file-connectors)**.**

### Service Account User Permissions

{% hint style="warning" %}
It is recommended to use a separate service account to establish the connection to the data source, configured with the following minimum set of permissions.
{% endhint %}

{% hint style="info" %}
👨‍💻**Who can provide these permissions?** These permissions are typically granted by the HDFS administrator, as users may not have the required access to assign them independently.
{% endhint %}

<table><thead><tr><th width="219">Operation</th><th width="135">Objects</th><th>Access Permissions</th></tr></thead><tbody><tr><td>Crawling &#x26; Profiling</td><td>Folder</td><td>Read (r) and Execute (x) on file/directory</td></tr><tr><td>Crawling &#x26; Profiling</td><td>Files</td><td>Read (r) and Execute (x) on file/directory</td></tr></tbody></table>

### Connection Configuration Steps

{% hint style="warning" %}
Users are required to have the Connector Creator role in order to configure a new&#x20;

connection.
{% endhint %}

1. Log into OvalEdge, go to **Administration** > **Connectors**, click + **(New Connector)**, search for **HDFS**, and complete the required parameters.

{% hint style="info" %}
Fields marked with an asterisk (\*) are mandatory for establishing a connection.
{% endhint %}

<table><thead><tr><th width="217.75">Field Name</th><th>Description</th></tr></thead><tbody><tr><td>Connector Type</td><td>By default, "<strong>HDFS</strong>" is displayed as the selected connector type.</td></tr><tr><td>Authentication</td><td><p>Select the authentication type from the drop-down list.</p><ul><li>Kerberos</li><li>Non-Kerberos</li></ul></td></tr></tbody></table>

{% tabs %}
{% tab title="Kerberos" %}

<table><thead><tr><th width="191">Field Name</th><th>Description</th></tr></thead><tbody><tr><td>Credential Manager*</td><td><p>Select the desired credentials manager from the drop-down list. Relevant parameters will be displayed based on the selected option.</p><p>Supported Credential Managers:</p><ul><li>OE Credential Manager</li><li>AWS Secrets Manager</li><li>HashiCorp</li><li>Azure Key Vault</li></ul><p>For more details, click <a href="https://docs.ovaledge.com/connectors/additional-requirements/credential-manager-configuration">here</a>.</p></td></tr><tr><td>Connector Environment</td><td>Select the environment (Example: PROD, STG) configured for the connector.<br>For more details, click <a href="https://docs.ovaledge.com/connectors/introduction-to-connectors/setup-and-connectivity/prerequisites#connector-environment">here</a>.</td></tr><tr><td>Connector Name*</td><td><p>Enter a unique name for the HDFS connection              </p><p>(Example: "HDFSdb").</p></td></tr><tr><td>Connector Description</td><td>Enter a brief description of the connector.</td></tr><tr><td>WebHdfs URL*</td><td>The endpoint URL of the Hadoop Distributed File System (HDFS) is accessible via WebHDFS REST API.</td></tr><tr><td>Keytab*</td><td>A secure file that contains encrypted Kerberos principals and keys for authentication.</td></tr><tr><td>Principal*</td><td>The Kerberos Principal name used for authentication to the Hadoop cluster.</td></tr><tr><td>Krb5-Configuration File*</td><td>Kerberos configuration file (krb5.conf) that defines realms, KDCs (Key Distribution Centers), and other Kerberos settings.</td></tr></tbody></table>
{% endtab %}

{% tab title="Non-Kerberos" %}

<table><thead><tr><th width="190">Field Name</th><th>Description</th></tr></thead><tbody><tr><td>Credential Manager*</td><td><p>Select the desired credentials manager from the drop-down list. Relevant parameters will be displayed based on the selected option.</p><p>Supported Credential Managers:</p><ul><li>OE Credential Manager</li><li>AWS Secrets Manager</li><li>HashiCorp</li><li>Azure Key Vault</li></ul><p>For more details, click <a href="https://docs.ovaledge.com/connectors/additional-requirements/credential-manager-configuration">here</a>.</p></td></tr><tr><td>Connector Environment</td><td>Select the environment (Example: PROD, STG) configured for the connector.<br>For more details, click <a href="https://docs.ovaledge.com/connectors/introduction-to-connectors/setup-and-connectivity/prerequisites#connector-environment">here</a>.</td></tr><tr><td>Connector Name*</td><td><p>Enter a unique name for the HDFS connection              </p><p>(Example: "HDFSdb").</p></td></tr><tr><td>Connector Description</td><td>Enter a brief description of the connector.</td></tr><tr><td>WebHdfs URL*</td><td>The endpoint URL of the Hadoop Distributed File System (HDFS) accessible via WebHDFS REST API.</td></tr></tbody></table>
{% endtab %}
{% endtabs %}

**Default Governance Roles**

<table data-header-hidden><thead><tr><th width="217.75"></th><th></th></tr></thead><tbody><tr><td>Default Governance Roles*</td><td>Select the appropriate users or teams for each governance role from the drop-down list. All users configured in the security settings are available for selection.</td></tr></tbody></table>

**Admin Roles**

<table data-header-hidden><thead><tr><th width="217.75"></th><th></th></tr></thead><tbody><tr><td>Admin Roles*</td><td><p>Select one or more users from the dropdown list for Integration Admin and Security &#x26; Governance Admin. All users configured</p><p>in the security settings are available for selection.</p></td></tr></tbody></table>

**No of Archive Objects**

<table data-header-hidden><thead><tr><th width="217.75"></th><th></th></tr></thead><tbody><tr><td>No Of Archive Objects*</td><td><p>This shows the number of recent metadata changes to a dataset at the source. By default, it is off. To enable it, toggle the Archive button and specify the number of objects to archive.</p><p>Example: Setting it to 4 retrieves the last four changes, displayed in the 'Version' column of the 'Metadata Changes' module.</p></td></tr></tbody></table>

**Bridge**

<table data-header-hidden><thead><tr><th width="217.75"></th><th></th></tr></thead><tbody><tr><td>Select Bridge*</td><td><p>If applicable, select the bridge from the drop-down list.</p><p>The drop-down list displays all active bridges that have been configured. These bridges facilitate communication between data sources and the system without requiring changes to firewall rules.</p></td></tr></tbody></table>

2. After entering all connection details, the following actions can be performed:
   1. Click **Validate** to verify the connection.
   2. Click **Save** to store the connection for future use.
   3. Click **Save & Configure** to apply additional settings before saving.
3. The saved connection will appear on the **Connectors** home page.

## Manage Connector Operations

### Crawl

{% hint style="info" %}
To perform crawl operations, users must be assigned the Integration Admin role.
{% endhint %}

1. Navigate to the **Connectors** page and click **Crawl/Profile.**
2. This action initiates the metadata collection process from the data source and loads the retrieved metadata into the **File Manager > File Explorer.**
3. In the File Manager, click the connector name, select the specific **folder(s) or file(s)**, then click **Catalog /** **Catalog and Profile** from the **Nine Dots** menu. For more details, click [here](https://docs.ovaledge.com/file-manager/file-explorer).
4. The selected files or folders will be added to the **Data Catalog > Files/File Columns** tab.

### Other Operations

The Connectors page provides a centralized view of all configured connectors, along with their health status.

**Managing connectors includes**:

* **Connectors Health**: Displays the current status of each connector, with a **green** icon for active connections and a **red** icon for inactive connections, helping monitor connectivity to data sources.
* **Viewing**: Click the **Eye** icon next to the connector name to view connector details.

**Nine Dots Menu Options:**

To view, edit, validate, configure, or delete connectors, click on the **Nine Dots menu**.

* **Edit Connector**: Update and revalidate the data source.
* **Validate Connector**: Check the connection's integrity.
* **Settings**: Modify connector settings.
  * **Crawler**: Configure data extraction.
  * **Access Instructions**: Add notes on how data can be accessed.
  * **Business Glossary Settings**: Manage term associations at the connector level.
* **Delete Connector**: Remove a connector with confirmation.

For more details on connector settings, click [here](https://docs.ovaledge.com/connectors/introduction-to-connectors/setup-and-connectivity/connector-settings).

## Connectivity Troubleshooting

If incorrect parameters are entered, error messages may appear. Ensure all inputs are accurate to resolve these issues. If issues persist, contact the assigned support team.

<table><thead><tr><th width="84.55548095703125">S.No.</th><th width="239.4444580078125">Error Message(s)</th><th>Error Description &#x26; Resolution</th></tr></thead><tbody><tr><td>1</td><td>Error while validating HDFS connection Error occured while validating the HDFS connection : Can't get Kerberos realm</td><td><p><strong>Error Description</strong>: The HDFS connection validation failed because Kerberos authentication could not be established. This issue can occur due to an incorrect or missing Kerberos configuration (krb5.conf), an invalid or mismatched keytab file, incorrect principal details, system time differences between the application server and Hadoop cluster, network connectivity issues, or an RPC Protection setting mismatch between the connector and the Hadoop environment.<br><strong>Resolution</strong>: </p><ul><li>Verify that the krb5.conf file contains the correct Kerberos realm and KDC details.</li><li>Ensure the keytab file is valid, corresponds to the configured principal, and is placed in the correct location.</li><li>Confirm that the principal configured in the connector matches the principal associated with the keytab file.</li><li>Validate network connectivity between the application server and the Hadoop cluster using ping, telnet, or similar connectivity tests.</li><li>Ensure the required Hadoop hostnames are resolvable and correctly configured in DNS or the /etc/hosts file.</li><li>Verify that the system time and time zone are synchronized between the application server and the Hadoop cluster.</li><li>Confirm that the Hadoop RPC Protection setting configured in the connector matches the setting required by the Hadoop cluster. If secure communication is enforced, configure the RPC Protection type as Privacy.</li><li>Retry the connection validation after applying the required configuration updates.</li></ul></td></tr><tr><td>2</td><td>Access Denied while attempting to list files in the specified HDFS folder.</td><td><p><strong>Error Description</strong>: The HDFS connector cannot access the specified folder because the configured user lacks sufficient permissions to view or list files in that location.<br><strong>Resolution</strong>: </p><ul><li>Verify that the configured HDFS user has the required read and execute permissions on the target folder.</li><li>Confirm that the folder path specified in the connector configuration is correct.</li><li>Check HDFS Access Control Lists (ACLs) and file system permissions for the affected directory.</li><li>Ensure that Kerberos authentication is configured correctly if the HDFS cluster is secured.</li><li>Validate that the user principal or service account has access to the target HDFS path.</li><li>Review HDFS NameNode and audit logs for additional permission-related details.</li><li>Retry the operation after updating the required permissions.</li></ul></td></tr><tr><td>3</td><td>Error while uploading file to HDFS: Destination path does not exist.</td><td><p><strong>Error Description</strong>: The file upload to HDFS fails because the specified destination directory does not exist in the HDFS environment. As a result, the system cannot locate the target path where the file needs to be uploaded<br><strong>Resolution</strong>: </p><ul><li>Verify that the destination HDFS path specified in the connector or upload configuration is correct.</li><li>Ensure that the target directory exists in HDFS before initiating the file upload.</li><li>Create the required directory in HDFS if it does not already exist.</li><li>Confirm that the configured user has sufficient permissions to access and write to the destination path.</li><li>Validate the HDFS URL and path format to ensure they match the actual HDFS directory structure.</li><li>Retry the file upload after correcting the destination path configuration.</li></ul></td></tr><tr><td>4</td><td>Error while validating HDFS connection: Kerberos authentication failed due to keytab file issues.</td><td><p><strong>Error Description</strong>: The HDFS connection validation fails because Kerberos authentication cannot be completed using the configured keytab file. This may occur if the keytab file is missing, corrupted, inaccessible, or does not contain the correct principal information.<br><strong>Resolution</strong>: </p><ul><li>Verify that the keytab file exists at the configured location.</li><li>Ensure that the application has the required permissions to access the keytab file.</li><li>Confirm that the keytab file contains the correct Kerberos principal.</li><li>Validate that the principal configured in the connector matches the principal stored in the keytab file.</li><li>Check that the keytab file is not corrupted and has been generated correctly.</li><li>Verify that the Kerberos realm and KDC details are configured correctly.</li><li>Ensure that system time is synchronized across the client and Kerberos server.</li><li>Retry the connection validation after correcting the keytab and Kerberos configuration.</li></ul></td></tr><tr><td>5</td><td>Kerberos principal authentication failed.</td><td><p><strong>Error Description</strong>: The HDFS connection failed because the Kerberos principal could not be authenticated. This usually occurs when the configured principal name, keytab file, or Kerberos settings are incorrect, expired, or inaccessible.<br><strong>Resolution</strong>: </p><ul><li>Verify that the Kerberos principal name is configured correctly in the connector.</li><li>Ensure that the associated keytab file exists and is accessible to the application.</li><li>Confirm that the principal is active and has not expired or been disabled in the Kerberos server.</li><li>Validate that the Kerberos realm and KDC details are correctly configured in the krb5.conf file.</li><li>Check that the system time is synchronized with the Kerberos server, as time differences can cause authentication failures.</li><li>Verify network connectivity between the application server and the Kerberos KDC server.</li><li>Renew or regenerate Kerberos credentials if they have expired.</li><li>Retry the connection after validating the Kerberos configuration and credentials.</li></ul></td></tr><tr><td>6</td><td>Timeout error while connecting to HDFS.</td><td><p><strong>Error Description</strong>: The HDFS connection attempt timed out because the application could not establish communication with the HDFS cluster within the expected time. This issue is commonly caused by network connectivity problems, incorrect host or port configuration, unavailable HDFS services, or firewall restrictions. </p><p><strong>Resolution</strong>: </p><ul><li>Verify that the HDFS NameNode hostname and port number are correct.</li><li>Ensure that the HDFS cluster services are running and accessible.</li><li>Test network connectivity between the application server and the HDFS environment.</li><li>Check for firewall, proxy, or security rules that may be blocking the connection.</li><li>Confirm that the configured user has the required access permissions.</li><li>Validate DNS resolution if host names are used in the connection configuration.</li><li>Increase the connection timeout setting if the HDFS environment has high network latency.</li><li>Retry the connection after resolving the connectivity or configuration issues.</li></ul></td></tr><tr><td>7</td><td>Errors encountered due to special characters in folder names.</td><td><p><strong>Error Description</strong>: The HDFS crawl or metadata retrieval operation fails because one or more folder names contain special characters that are not supported by the connector or underlying file system processing. As a result, the connector is unable to access or process the affected folders. </p><p><strong>Resolution</strong>: </p><ul><li>Identify the folders containing special characters in their names.</li><li>Rename the affected folders using supported alphanumeric characters and standard naming conventions.</li><li>Avoid using special characters that may not be supported by HDFS, operating systems, or connector processing.</li><li>Verify that folder paths are accessible and correctly configured in the connector.</li><li>Re-run the crawl or metadata extraction process after updating the folder names.</li><li>If renaming is not possible, exclude the affected folders from the crawl scope where applicable.</li></ul></td></tr><tr><td>8</td><td>Connection additional attributes cannot be null.</td><td><p><strong>Error Description</strong>: The HDFS connector validation fails because one or more required additional connection attributes are missing or empty. The connector requires these attributes to establish a successful connection to the HDFS environment. </p><p><strong>Resolution</strong>: </p><ul><li>Verify that all mandatory connection attributes are configured in the connector settings.</li><li>Ensure that no required additional attribute fields are left blank or contain null values.</li><li>Validate the format and values of the configured HDFS connection properties.</li><li>Review the connector configuration against the HDFS environment requirements.</li><li>Save the updated configuration and retry the connection validation.</li><li>If the issue persists, review the application logs to identify the specific missing attribute.</li></ul></td></tr><tr><td>9</td><td>Error related to file extensions encountered while processing files.</td><td><p><strong>Error Description</strong>: The HDFS connector encountered files with unsupported, invalid, or unrecognized file extensions during processing. As a result, the connector could not successfully read or process the affected files. </p><p><strong>Resolution</strong>: </p><ul><li>Verify that the files in the HDFS location have valid and supported file extensions.</li><li>Ensure that the file format matches the file extension being used.</li><li>Check for files with missing, incorrect, or corrupted extensions and update them as required.</li><li>Remove or exclude unsupported file types from the crawl path.</li><li>Confirm that the files are not corrupted and can be opened using the appropriate application.</li><li>Re-run the crawl or profiling job after correcting the file extensions and file formats.</li></ul></td></tr><tr><td>10</td><td>An authentication attribute is required.</td><td><p><strong>Error Description</strong>: HDFS connector validation fails due to a required authentication setting being missing. The connector cannot establish a connection to the HDFS environment without the necessary authentication information. </p><p><strong>Resolution</strong>: </p><ul><li>Verify that all required authentication fields are configured in the connector.</li><li>Ensure that the appropriate authentication method (for example, Kerberos or Simple Authentication) is selected.</li><li>Confirm that all mandatory credentials and authentication properties are provided.</li><li>Validate that any required configuration files, such as krb5.conf or keytab files, are correctly specified and accessible.</li><li>Review the connector configuration for any missing or invalid authentication parameters.</li><li>Retry the connection validation after updating the authentication settings.</li></ul></td></tr><tr><td>11</td><td>Connection errors encountered while attempting to connect to the HDFS cluster; unable to determine whether the issue is related to configuration settings or the HDFS environment.</td><td><p><strong>Error Description</strong>: The HDFS connection attempt failed, but the exact cause could not be determined. The issue may be related to incorrect connector settings, network connectivity problems, authentication failures, or an issue within the HDFS cluster environment. </p><p><strong>Resolution</strong>: </p><ul><li>Verify that the HDFS URL, hostname, and port number are correctly configured.</li><li>Ensure that the HDFS cluster is running and accessible from the application environment.</li><li>Validate network connectivity between the application and the HDFS cluster.</li><li>Confirm that the configured authentication settings (Kerberos, user credentials, or certificates) are correct.</li><li>Check whether other users or applications can successfully connect to the same HDFS cluster.</li><li>Review HDFS NameNode and DataNode logs for any cluster-side errors.</li><li>Verify that the configured user has the required permissions to access HDFS resources.</li><li>Retry the connection after validating the configuration and cluster availability.</li></ul></td></tr></tbody></table>

## FAQs

<details>

<summary>Unsure which authentication type to select (Kerberos or Non-Kerberos)</summary>

Confirm the authentication method configured on the HDFS cluster with the HDFS administrator. Select Kerberos Authentication when Kerberos security is enabled in the environment, and choose Non-Kerberos Authentication for unsecured or test clusters. If the authentication type is unknown, begin with Non-Kerberos Authentication and switch to Kerberos if authentication errors occur.

</details>

<details>

<summary>Unable to view files or folders when browsing an HDFS directory</summary>

Ensure the required permissions are available to access the directory, verify that the folder path is correctly specified and begins with a forward slash (for example, /user/data), confirm that the HDFS connection is successful, validate that the Kerberos principal has read access to the specified path if authentication is enabled, and attempt to list the root directory (/) to confirm basic visibility.

</details>

<details>

<summary>Unable to locate a file in HDFS</summary>

Ensure the search is performed in the correct directory path; verify the file name for special characters or spaces that may affect the search; confirm that sufficient permissions are available to access the directory; browse the directory manually to view all files; and refresh the listing if the file was created recently.

</details>

<details>

<summary>File listing is slow when opening a folder with many files</summary>

This behavior is expected for directories containing a large number of files. To improve performance, use the search or filter options instead of loading the entire folder, navigate to a more specific subfolder where possible, and consult the administrator if the directory contains an excessive number of files that may require reorganization.

</details>

<details>

<summary>Unable to download a file from HDFS</summary>

1. Verify that the required read permissions are available for the file; ensure the specified file path is correct and complete; confirm that the HDFS connection is active and reconnect if necessary; allow sufficient time for large file downloads to complete; and validate that Kerberos authentication has not expired if security is enabled.

</details>

## Known Limitations

<table><thead><tr><th width="92.666748046875">S.No.</th><th>Limitation</th></tr></thead><tbody><tr><td>1</td><td>For File-based connectors, the folder count in the File Manager and Data Catalog Files module may not match if folders or files are added or deleted in the source system after crawling. Run the connection crawl again to refresh and display the latest changes.</td></tr></tbody></table>

***

Copyright © 2026, OvalEdge LLC, Peachtree Corners, GA, USA.


---

# 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.ovaledge.com/release8.2/connectors/connector-repositories/file-connectors/hdfs-hadoop-distributed-file-system.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.