> For the complete documentation index, see [llms.txt](https://docs.clickai.vn/clickai-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.clickai.vn/clickai-docs/clickai-docs-en/database/quick-create.md).
# Quick Create
## Table of Contents
· \[Quick Create Workflow]\(#quick-create-workflow)
· \[Step 1: Import Data]\(#step-1-import-data)
· \[Step 2: Configure Chunk Settings]\(#step-2-configure-chunk-settings)
· \[Step 3: Configure Index Method & Retrieval Settings]\(#step-3-configure-index-method--retrieval-settings)
· \[Step 4: Wait for Processing]\(#step-4-wait-for-processing)
## Quick Create Workflow
Quick Create is the most common method to create a Knowledge Base on ClickAI. The process consists of 4 main steps:
1\. Click Knowledge > Create Knowledge, then upload local files, sync data from Notion, or import from webpages, or create an empty knowledge base.
2\. Configure the Chunk Settings and preview the chunking results. This stage involves content preprocessing and structuring, where long texts are divided into multiple smaller chunks.
3\. Specify the Index Method and Retrieval Settings. Once the knowledge base receives a user query, it searches existing documents according to preset retrieval methods and extracts highly relevant content chunks.
4\. Wait for the data processing to complete.
💡 TIP: You can create an empty Knowledge Base first and add documents later. This is useful when you want to prepare the configuration beforehand.
## Step 1: Import Data
ClickAI supports 3 data import sources:
### Upload Local Files
Supported file formats:
| |
|---|
| Format | Description |
| .txt | Plain text |
| .md / .markdown | Markdown documents |
| .pdf | PDF documents |
| .html / .htm | HTML web pages |
| .docx | Microsoft Word |
| .csv | CSV data tables |
| .xlsx / .xls | Microsoft Excel |
| .pptx | Microsoft PowerPoint |
Upload limits:
| |
|---|
| Parameter | Value |
| Maximum files per upload | 20 |
| Maximum file size | 15 MB |
📝 NOTE: ClickAI supports processing images embedded in DOCX files. For other file types (e.g., PDF), you can use document extraction plugins in Knowledge Pipeline to extract images.
Images via Markdown URL: In addition to embedded images, ClickAI also supports images referenced via URLs using Markdown syntax:
!\[alt text]\(image\_url)\
!\[alt text]\(image\_url "optional title")
### Sync Data from Notion
Connect your Notion account to sync pages and databases directly into your Knowledge Base.
Steps:
5\. Go to Knowledge > Create Knowledge
6\. Select Sync from Notion as the data source
7\. If not connected, click Connect to authorize your Notion account
8\. Select the Notion pages you want to sync
9\. Click Import to begin
⚠️ IMPORTANT: When using Notion sync, content is synced at the time of import. To update with new content, you need to re-sync manually.
### Import Data from Website
Crawl content from public web pages to create a Knowledge Base.
Steps:
10\. Go to Knowledge > Create Knowledge
11\. Select Sync from Website as the data source
12\. Enter the URL to crawl
13\. Configure crawl scope (single page or crawl sub-pages)
14\. Click Run to begin
## Step 2: Configure Chunk Settings
See details at: \[Configure Chunk Settings]\(./03-chunk-settings.md)
## Step 3: Configure Index Method & Retrieval Settings
See details at: \[Index Method & Retrieval Settings]\(./04-index-retrieval-settings.md)
## Step 4: Wait for Processing
After configuration, click Save & Process. ClickAI will automatically:
· Pre-process text (remove extra characters, normalize)
· Split documents into chunks per configuration
· Create embedding vectors for each chunk
· Index for retrieval readiness
Processing time depends on:
· Number and size of documents
· Selected indexing method (High Quality takes longer than Economical)
💡 TIP: You can monitor processing progress on the Knowledge Base detail page. Status will change from "Processing" to "Available" when complete.
*📖 Previous: \[Overview]\(./01-overview\.md) · Next: \[Chunk Settings]\(./*
---
# 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.clickai.vn/clickai-docs/clickai-docs-en/database/quick-create.md?ask=&goal=
```
`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.