Skip to main content

Create a New Knowledge Source

This guide explains how to create a new knowledge source on the Aumo platform. The process is divided into two steps: selecting the type of source and configuring the details.

Overview​

When creating a new knowledge source, you will be setting up a connector that will import and process documents from an external source. These documents will then be indexed and made available for use by AI assistants.

Accessing the Creation Page​

To create a new knowledge source:

  1. Navigate to the Projects section in the sidebar menu
  2. Select the desired project
  3. Click on Knowledge Source in the project's sidebar menu
  4. Click the New Source button at the top of the page

Step 1: Selecting the Source Type​

In the first step, you need to select the type of knowledge source you want to create. The Aumo platform supports the following types:

Google Drive​

Connects to Google Drive to import documents stored in the cloud. Allows automatic synchronization of specific folders and files.

Organizational Google Drive​

Similar to Google Drive, but allows access to documents from another Google Drive account using service account credentials (domain-delegated service account).

Web Scraper​

Extracts content from web pages. You can configure it to extract a specific page or all related pages.

Upload​

Allows direct upload of files from your computer to the platform. Ideal for documents that are not hosted on external services.

Confluence​

Connects to Confluence (Atlassian) to import pages and knowledge spaces.

Jira​

Connects to Jira (Atlassian) to import issues, comments, and project documentation.

How to Select a Type​

  1. On the creation page, you will see the different available source types
  2. Click on the source type you want to configure (e.g., "Google Drive")
  3. After selecting, the breadcrumb will show the steps: "Source Type", "Credential Selection", and "Source Details"
  4. For types that require credentials (like Google Drive), you will need to select or create a credential before you can proceed
  5. After selecting the necessary credential, the Next button will be enabled
  6. Click Next to proceed to the next step

Intermediate Step: Credential Selection​

For source types that require authentication (such as Google Drive, Confluence, Jira), you will need to select or create a credential before proceeding to the detail configuration.

How to Select a Credential​

  1. After selecting the source type (e.g., "Google Drive"), the interface will display a list of available credentials
  2. If you already have configured credentials, select the appropriate credential from the list
  3. If there are no available credentials or you need to create a new one, you can:
    • Create a new credential directly from this screen (if available)
    • Navigate to the Credentials section to create a new credential before continuing
  4. After selecting a valid credential, the Next button will be enabled
  5. Click Next to continue

Note: Make sure you have configured the necessary credentials in the Credentials section before creating sources that require authentication. For more information on how to create credentials, refer to the Credentials documentation.

Step 2: Configuring the Details​

In the second step, you will need to provide specific information about the knowledge source you are creating. The required fields may vary according to the selected source type.

Common Fields​

Regardless of the source type, you will generally need to provide:

  • Name: A descriptive name to identify the knowledge source
  • Description (optional): A more detailed description of the purpose of the source

Specific Settings by Type​

Google Drive / Organizational Google Drive​

  • Root Folder ID: The ID of the Google Drive folder that will be synchronized
  • Credentials: Select the configured Google credentials from the Credentials section
  • Target User Email (only for Organizational Google Drive): The email of the account whose documents will be accessed

Web Scraper​

  • URL: The URL of the web page to be extracted
  • Extraction Type: Choose between "single" (only the specified page) or "all" (all related pages)
  • Owner Email: The email of the user who will be marked as the owner of the extracted files

Upload​

  • Files: Select the files you want to upload
  • Owner Email: The email of the user who will be marked as the owner of the files

Confluence​

  • Base URL: The base URL of your Confluence (e.g., https://your-domain.atlassian.net)
  • Credentials: Select the configured Confluence credentials
  • Spaces: Configure which Confluence spaces will be imported

Jira​

  • Base URL: The base URL of your Jira (e.g., https://your-domain.atlassian.net)
  • Credentials: Select the configured Jira credentials
  • Projects: Configure which Jira projects will be imported

Finalizing the Creation​

  1. Fill in all required fields
  2. Review the provided information
  3. Click Create or Save to finalize the creation of the source

Next Steps​

After creating the knowledge source:

  1. The source will be processed and the documents will be automatically indexed
  2. You can monitor the processing status on the main Knowledge Sources page
  3. The indexed documents will be available for use in AI assistants and knowledge collections

Important Notes​

  • Make sure to configure the necessary credentials before creating sources that require authentication (Google Drive, Confluence, Jira)
  • Document processing may take some time depending on the amount of content
  • Some source types may require specific permissions on external services

Troubleshooting​

If you encounter issues while creating a knowledge source:

  • Verify that the credentials are configured correctly
  • Confirm that you have the necessary permissions on external services
  • Check that the URL or folder ID is correct
  • Refer to the logs section for more details on processing errors
Last updated on by gabriel.ambrozini