# Knowledge Base Overview

## What is a Knowledge Base?

After creating an AI assistant, the next step is to configure the **knowledge base**, which serves as the data source for the AI assistant to answer questions.

How the knowledge base works:

<figure><img src="https://1360999650-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F6v6TNkkOQVfRYfcNirHL%2Fuploads%2Fgit-blob-4f0c9f2e38378849b5dd115cfc702bd19dcab672%2Fplayma%20(5).png?alt=media" alt=""><figcaption><p>Knowledge Base Operation Diagram</p></figcaption></figure>

You can think of the knowledge base as an open-book exam. The AI assistant searches the knowledge base for content most relevant to the question and uses it as the basis for its response.

While the knowledge base can store large amounts of data, it's recommended to upload content highly relevant to the assistant's tasks. If irrelevant content is included, current retrieval technology may still retrieve unrelated information as context, leading to inaccurate responses.

## What Can the Knowledge Base Do?

With the following features of the knowledge base, you can:

### 📋 **Manage Documents with Tags**

You can add multiple tags to each document to create a systematic classification structure

* **Example**: Add `#tent #beginner #setup-guide` tags to "Tent Manual"

### 🔐 **Selective Document Access Control**

You can set different document access permissions based on user identity to implement differentiated services

* **Example**: Product price lists are only accessible in VIP member conversations, cost data is only accessible in internal conversations

### ❓ **Create FAQs**

You can organize common questions into standard Q\&A sets to ensure consistent and comprehensive responses

* **Example**: "How long is the tent warranty?" → Standard answer: "We provide a 3-year warranty service"

### 📊 **Include Document Metadata**

You can add detailed information such as version, update date, and applicable scope to documents for easier future maintenance

* **Example**: Document version v2.1, update date 2024/11/28, applicable product "Mountain Series Tents"

### 🔍 **Search Testing**

You can test retrieval results for different questions to verify whether the AI finds the correct data segments

* **Example**: Input "tent setup steps" → Check if the AI finds the correct setup guide segment

## How to Upload to the Knowledge Base?

1. Navigate to "<mark style="color:blue;">AI Features</mark>" in the left sidebar menu, select "<mark style="color:blue;">AI Assistant</mark>", choose which AI assistant to create a knowledge base for, and click the "<mark style="color:blue;">Actions</mark>" icon on the right.

<figure><img src="https://1360999650-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F6v6TNkkOQVfRYfcNirHL%2Fuploads%2Fgit-blob-bb5ac0b4f7789f82dba534e90fe9ab2ba4c5fc7f%2F%E8%9E%A2%E5%B9%95%E6%93%B7%E5%8F%96%E7%95%AB%E9%9D%A2%202025-08-20%20094056.png?alt=media" alt=""><figcaption></figcaption></figure>

2. Navigate to "<mark style="color:blue;">AI Features > AI Assistant > Knowledge Base</mark>" in the left sidebar menu, click the blue "<mark style="color:blue;">Upload File</mark>" button in the upper right corner to upload the data you want the AI assistant to know.

{% hint style="info" %}

* Different plans provide different knowledge base storage capacities
* If your files are large or contain substantial data, the system may need some time to process after upload.
  {% endhint %}

<figure><img src="https://1360999650-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F6v6TNkkOQVfRYfcNirHL%2Fuploads%2Fgit-blob-12fa488c87c8faad401ab5aa06df2f0ab7c7d431%2Fimage%20(194)%20(1)%20(1).png?alt=media" alt=""><figcaption></figcaption></figure>

You can check the processing progress in the "<mark style="color:blue;">Processing Status</mark>" field.

<figure><img src="https://1360999650-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F6v6TNkkOQVfRYfcNirHL%2Fuploads%2Fgit-blob-5e2300562aa874f413e7b2d4f271e2a6c06aaeb9%2F%E8%9E%A2%E5%B9%95%E6%93%B7%E5%8F%96%E7%95%AB%E9%9D%A2%202025-09-26%20175144.png?alt=media" alt=""><figcaption></figcaption></figure>

{% hint style="success" %}
Currently supported file types for the knowledge base:

* Spreadsheet documents: `.xls, .xlsx, .csv, .ods`
* Word processing documents: `.doc, .docx, .odt, .pdf, .md, .txt`
* Presentation documents: `.ppt, .pptx, .odp`
* Web documents: `.html, .htm`
* Data formats: `.json, .jsonl`
* Audio files: `.wav, .mp3`
  {% endhint %}

### View Data

#### Data Segment Explanation

When data is uploaded to the knowledge base, it is divided into segments. This approach offers the following benefits:

* **Improved retrieval accuracy**: Smaller segments match queries more precisely, avoiding interference from irrelevant content
* **Optimized response speed**: Faster processing with reduced computational resource consumption
* **Enhanced content relevance**: Each segment focuses on a single topic, increasing specificity
* **Easier maintenance and management**: Simplifies updates, tracking, and quality control
* **Compliance with AI model limitations**: Avoids exceeding input length limits, ensuring information integrity

#### Edit and View Segment Content

You can view the segmented content of your documents:

1. Enter the document page in the knowledge base and click "<mark style="color:blue;">Edit</mark>"
2. To view segment content, click on the segment you want to view

The screen will display the complete content of this segment in Markdown format.

<div><figure><img src="https://1360999650-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F6v6TNkkOQVfRYfcNirHL%2Fuploads%2Fgit-blob-41e18fc4ea11f8fde9c16945dc0f8db37db8607d%2Fimage%20(158).png?alt=media" alt=""><figcaption></figcaption></figure> <figure><img src="https://1360999650-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F6v6TNkkOQVfRYfcNirHL%2Fuploads%2Fgit-blob-3b62b64ce2512088b08c4e9614367c2a2b6ee433%2Fimage%20(160).png?alt=media" alt=""><figcaption></figcaption></figure></div>

#### Edit Original Document

1. Click "<mark style="color:blue;">View Document</mark>" on the edit page

<figure><img src="https://1360999650-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F6v6TNkkOQVfRYfcNirHL%2Fuploads%2Fgit-blob-33f80dbb3c38ad40757d626d7e6d57de5a2e3d59%2F%E8%9E%A2%E5%B9%95%E6%93%B7%E5%8F%96%E7%95%AB%E9%9D%A2%202025-08-20%20094550.png?alt=media" alt=""><figcaption></figcaption></figure>

2. Enter the edit page, where the text box will display the Markdown format of the document

You can edit your original document in the text box. All file formats can be edited using this method. After completing your edits, click "<mark style="color:blue;">Save</mark>" to preserve your changes.

<div><figure><img src="https://1360999650-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F6v6TNkkOQVfRYfcNirHL%2Fuploads%2Fgit-blob-0fdbaef7bd72e5fdb9692c1ac8134456a26ea90e%2F%E8%9E%A2%E5%B9%95%E6%93%B7%E5%8F%96%E7%95%AB%E9%9D%A2%202025-08-20%20094933.png?alt=media" alt=""><figcaption></figcaption></figure> <figure><img src="https://1360999650-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F6v6TNkkOQVfRYfcNirHL%2Fuploads%2Fgit-blob-0fdbaef7bd72e5fdb9692c1ac8134456a26ea90e%2F%E8%9E%A2%E5%B9%95%E6%93%B7%E5%8F%96%E7%95%AB%E9%9D%A2%202025-08-20%20094933.png?alt=media" alt=""><figcaption></figcaption></figure></div>

{% hint style="info" %}
**Data Management Reminder**

* It's recommended to back up important content before editing
* After editing the original document, the system will re-segment the content
  {% endhint %}