Document Management: Tags and Metadata
Due to the potential large volume of documents or FAQs in the knowledge base, MaiAgent provides tag management and metadata management features, allowing you to categorize and organize extensive documents and FAQs.
Tag Management
When your knowledge base contains a large amount of data, the tag system helps you quickly organize document and FAQ attributes, or control access permissions for reference materials. For example:
Product Information Knowledge Base (Categorized by Product Information)
|-- #Tent
|-- #4-Person Tent
|-- #Three-Season Tent
|-- #SnowPeakEducational Content Knowledge Base (Categorized by Permission Level)
|-- #Non-Member
|-- #Regular Member
|-- #VIPAdding Tags
Click the add button

Enter the tag name

After clicking add, the tag you just entered will be displayed as follows, including ID, name, etc.

Adding Tags to Documents
After tags are added, proceed to the document page
Click edit file information

Select tags
According to different document requirements, add corresponding tags (you can select multiple tags)

Thus, the added tags will be displayed after the corresponding document:

Adding Tags to FAQs
If you wish to add hierarchical classification or tag management to FAQs, you can:
Enter the FAQ management interface within the knowledge base, select the FAQ to edit, and click the edit button

Select the tags to add, and after adding, click "Confirm"


The added tags will appear in the FAQ field

Tag-Based Access Control
You can control different users to see different content based on different tags, such as VIP customers being able to see more advanced product demonstrations, while non-members can only see general demonstrations.
AND Filter
The AND tag filter opens content that simultaneously meets all tag conditions.
For example: if this conversation is related to educational content for non-members, you can use tag filtering to only open documents that simultaneously meet the "non-member" and "educational" tags for the AI assistant to use.
As shown: after filtering, the AI assistant can only use beginner camping documents, avoiding disclosure of irrelevant information to non-member conversations.

OR Filter
For conversations with members, you can use the OR filter to allow documents that meet either regular member or non-member conditions to be referenced by the AI assistant:

Members will be able to see more document content than non-members, achieving permission tiering.

For filtering results, please refer to: Internal Q&A Features
Document Metadata Management
What is Metadata?
Metadata is like a document's "ID card," recording detailed information about the document to help the system better manage and use these documents.
Example: Beginner Camping.pdf
Metadata Settings:
├── Document Version: v2.1
├── Creation Date: 2024-03-15
├── Last Updated: 2024-11-20
├── Next Review: 2025-05-20
├── Update Department: Marketing
└── Version Status: Reviewed and AvailableWhy Use Metadata?
In situations with complex data, using metadata helps you maintain data quality more conveniently and quickly, assisting you in:
Improving Management Efficiency
Quickly identify document status and version information
More organized when batch managing large numbers of documents
Reduce manual search and verification time
Ensuring Content Quality
Use the latest document versions
Track document update history and version status
Ensure AI assistants use the latest and reviewed content
Set periodic review reminders to maintain data quality
Adding Metadata to Documents
Enter the document page and click edit document information:

Switch to the metadata tab and enter metadata mappings
MaiAgent uses key-value pairs to store and retrieve metadata


After entering, click the "Add Metadata" button to add the key-value mapping you just entered (you can add multiple metadata entries at once).

After completion, you will see the metadata you just added appear in the field.
Adding Metadata to FAQs
Enter the FAQ management interface within the knowledge base, select the FAQ to edit, and click the edit button

Switch to the metadata page, enter information and click add metadata
After completing all entries, click "Confirm"

The added metadata will appear in the FAQ list

Custom URL Mapping
url is a reserved word in the metadata system. If you set url: https://...your specified URL, the URL you set will override the original file location when viewing reference snippets in conversations, and will instead open your specified URL.
Example Scenario: Brand Spring Promotion Campaign
Original Settings:
title: "2025 Spring Big Promotion Details"
content: "This campaign includes 20% off storewide, free gifts with purchase, and many other offers..."
url: https://www.yourstore.com/spring-sale-2025Usage Effect: When users ask "What offers are in the spring promotion?" in the conversation:
The AI will reference this knowledge snippet to answer the question
When users click the reference source, it won't open the internal file location
Instead, it will directly jump to
https://www.yourstore.com/spring-sale-2025official campaign pageUsers can immediately see the latest campaign details, purchase buttons, countdown timers, and other dynamic content
Practical Scenarios:
Website Announcements:
url: https://www.company.com/announcements/system-maintenanceProduct Specifications:
url: https://www.product.com/specs/model-x1Customer Service Policies:
url: https://support.company.com/return-policyEvent Registration:
url: https://events.company.com/register/webinar-2025
The advantage of this setup is making AI responses more practical — not just providing information, but also guiding users directly to relevant pages to take action, improving user experience and conversion rates.
Before Setting URL
As shown below, before setting the URL value, when clicking on reference nodes, clicking any node (e.g., Beginner Camping.pdf) allows viewing the original document (you can set whether to allow users to download original document files on the conversation platform):


After Setting URL (Using Google as Example)

When clicking on the referenced node file (Camping Precautions.txt) again, it will not display the document preview, but instead override to open the Google homepage:


When you set the url field in metadata, users can directly click to jump to your set link when they see the AI assistant referencing that document in conversations, obtaining more complete information
Last updated
Was this helpful?
