> For the complete documentation index, see [llms.txt](https://docs.mydbsync.com/cloud-workflow/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.mydbsync.com/cloud-workflow/ai/knowledge-base.md).

# Knowledge Base

The knowledge base acts as the central data repository and foundational memory for your AI Chat Agent. You build the database by uploading internal documents or scanning external web pages to organize and store your proprietary content. This setup lets the chatbot reference your specific organization level information to answer questions.\
\
To configure the knowledge base, follow these steps:

{% stepper %}
{% step %}
Log in to DBSync with your credentials.
{% endstep %}

{% step %}
In the navigation pane, click <img src="/files/hbKst2r0GxYCGRISQcu9" alt="" data-size="line"> (Knowledge Base).
{% endstep %}

{% step %}
Click **Create**.
{% endstep %}

{% step %}
In the New Knowledge Base dialog, for **Name**, enter a name.\
Optional: For **Description**, enter a description.\
![](/files/U4sOwwlyoS4NxAgbYw2S)
{% endstep %}

{% step %}
Click **Save**.
{% endstep %}

{% step %}
Click the knowledge base that you created.

<figure><img src="/files/XOqPrS8v3Bi9vfSH4Yg7" alt=""><figcaption></figcaption></figure>
{% endstep %}

{% step %}
To add content, do one of the following:

* To add a local file, click **Upload File**, and then drag your files into the upload area or click the area to select files.
* To add content directly from a website, click **Scan Web Page**.\
  \
  After you add content to the knowledge base, the **Documents** table displays a new row with the content details.

  <figure><img src="/files/01CIYuKMSf4Uh0jN2X5Y" alt=""><figcaption></figcaption></figure>

{% endstep %}

{% step %}
To view information about your documents or delete them, do the following in the **Documents** table:

* To view document metadata, review the **Name**, **Source**, **Type**, and **Created** columns.
* To view the chunk count, review the number in the **Chunks** column.
* To check the processing status, review the state in the **Status** column.
* To delete a single document, click the ![](/files/Ga3V2jNDWOiP0bSl3cqv) in the **Actions** column for that document.
* To delete multiple documents, select the checkbox next to each document that you want to remove, and then click **Delete Selected**.
  {% endstep %}

{% step %}
Optional: To change the knowledge base name and description, click **Edit**.
{% endstep %}

{% step %}
Optional: To completely remove the knowledge base, click **Delete**.
{% endstep %}

{% step %}
To return to the knowledge base homepage, click <img src="/files/YWxE3ZZU7at1lo73FRYm" alt="" data-size="line">.\
\
The new knowledge base and its details appear on the knowledge base homepage.

<figure><img src="/files/d2VMIdqopyfmYLcm6MeK" alt=""><figcaption></figcaption></figure>
{% endstep %}
{% endstepper %}


---

# 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:

```
GET https://docs.mydbsync.com/cloud-workflow/ai/knowledge-base.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.
