# How to create a knowledge base?

### **Get started** <a href="#get-started" id="get-started"></a>

* To begin, log in to your ZBrain account.
* Once you have successfully logged in, click **Knowledge**.
* Click the 'Create' button to initiate the process of setting up a new knowledge base.

<figure><img src="/files/54CajKTrF6xmfTmabZhb" alt=""><figcaption></figcaption></figure>

### **Upload document** <a href="#upload-document" id="upload-document"></a>

#### Select a knowledge source <a href="#select-a-knowledge-source" id="select-a-knowledge-source"></a>

You will be directed to a screen where you can select the source for your knowledge base to start building it. You can:

* Upload a document from your device. When you choose ‘Upload document’, you can upload supported files directly from your device.
* You can upload multiple documents at a time.

<figure><img src="/files/oq0lo7R6497zik3IxS9C" alt=""><figcaption></figcaption></figure>

* Also, you can import data from other sources such as Add via Flows, Web URL, Webhook, Google Sheets, and Google Slides, etc.

A few source options are explained in detail below.

**Web URL**

You can use the Web URL option to import content directly from a webpage.

<figure><img src="/files/v6tY5TPi3IayoO6DsMzB" alt=""><figcaption></figcaption></figure>

For Web URL ingestion, refer to the video below for a step-by-step walkthrough.

**Create a knowledge base via existing Flow**

If you want to automate ingestion or reuse an existing processing pipeline, you can create a knowledge base using an existing Flow. Using a Flow to create a knowledge base:

* Integrates automation logic directly with enterprise knowledge.
* Allows dynamic data pipelines to populate and update the knowledge base continuously.
* Eliminates manual file uploads for recurring or large-scale ingestion.
* Improves retrieval quality by turning Flows into live, reusable knowledge sources.

**Steps to create a Knowledge Base via Flow**

* In the Select Knowledge Source step, choose ‘Add via Flows’.

<figure><img src="/files/LVpinibVEymIDvuD2jKL" alt=""><figcaption></figcaption></figure>

* You will be presented with a list of available Flows.
* Use the search bar or filters to locate your desired Flow.
* Select the Flow to serve as your ingestion pipeline and click ‘Add’. Add only one Flow at a time.

**Note:** For other sources, follow the instructions displayed on the screen to complete the setup.

{% embed url="<https://www.youtube.com/watch?v=AoqWo6vjevE>" %}

### **Data source configuration**  <a href="#data-source-configuration" id="data-source-configuration"></a>

This page allows users to configure the foundational elements of a new knowledge base.

* After uploading or importing the data, you will be prompted to provide a name and description for the chosen file/data.
* To upload additional documents to the knowledge base, click the ‘Add More’ button located below the uploaded documents. Select the documents from your device to add them.

**Document summarization**

* Enable document summarization by toggling the dedicated switch.
* Select an appropriate large language model to perform the summarization process.
* This feature creates concise overviews of lengthy documents for easier comprehension.

**Automated reasoning policy**

* Create an automated reasoning policy by activating the feature toggle.
* An automated reasoning policy consists of predefined rules, conditions, and variables that guide the system's reasoning process when responding to queries.
* It extracts structured data from the knowledge base, applies logical reasoning, and ensures responses are accurate and consistent.
* This policy governs how the system interprets information, processes queries, and delivers answers based on established knowledge and logic.

<figure><img src="/files/P0Ni5wRLQtMP48ym69zl" alt=""><figcaption></figcaption></figure>

**Improve efficiency using Flow**

* Enable ‘Improve efficiency using Flow’ by activating the feature toggle.
* Select a predefined or custom Flow to apply during ingestion for advanced data refinement.
* This feature helps transform raw documents into structured, high-quality knowledge that is easier to search, summarize, and reason over.

*Detailed configuration options for this feature are covered in the dedicated **Improve efficiency using Flows** guide.*

#### Review extracted knowledge <a href="#review-extracted-knowledge" id="review-extracted-knowledge"></a>

Before finalizing a knowledge base, you can review and edit the extracted content to ensure it is accurate, relevant, and well-structured. Refining the data at this stage improves overall knowledge quality and enhances downstream retrieval and reasoning.

To make updates, edit the content directly in the Extracted Knowledge panel. Click ‘Next’ to proceed to connect to the next page.

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


---

# 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-builder/knowledge-base/how-to-create-a-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.
