Document Management: Tags and Metadata

Due to the potentially large number of documents or FAQs that need to be managed in the knowledge base, MaiAgent provides tag management and metadata management features to help you classify and organize large amounts of documents and FAQs.

Tag Management

When your knowledge base contains large amounts of data, the tagging system can help you quickly organize document and FAQ attributes, or control reference material permissions. For example:

Product Information Knowledge Base (Categorized by Product Information)
|-- #Tent
|-- #4PersonTent
|-- #3SeasonTent 
|-- #SnowPeak
Tutorial Content Knowledge Base (Categorized by Permission Level)
|-- #NonMember
|-- #RegularMember
|-- #VIP

Adding Tags

  1. Click the Add button

  1. Enter tag name

  1. After clicking Add, the tag you just entered will be displayed as below, including ID, name, etc.

ID can be used when setting document permissions, for details please see Technical Manual—Query Metadata Control Items

Adding Tags to Documents

After adding tags, go to the document page

  1. Click Edit File Information

  1. Select tags

Add corresponding tags according to different document requirements (you can select multiple tags)

This way, the added tags will appear after the corresponding document:

Adding Tags to FAQs

If you want to add hierarchical classification or tag management to FAQs, you can:

  1. Enter the FAQ management interface in the knowledge base, select the FAQ you want to edit, and click the Edit button

  1. Select the tags you want to add, then click "Confirm"

The added tags will appear in the FAQ field


Tag Permission Access Control

You can control different users' access to different content based on tags, such as VIP customers being able to see more advanced product tutorials while non-members can only see general tutorials.

Both FAQs and documents can apply filtering

AND Filter

AND tag filtering allows content that matches all tag conditions simultaneously.

For example: If this conversation is related to non-member tutorials, you can use tag filtering to only allow AI assistants to use documents that simultaneously match the "NonMember" and "Tutorial" tags.

As shown: After filtering, the AI assistant can only use beginner camping documents, avoiding revealing irrelevant information to non-member conversations.

OR Filter

For member conversations, you can use the OR filter to allow AI assistants to reference documents that match either regular member or non-member tags:

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

You can switch filtering mechanisms by clicking "AND" or "OR" in the tag filter

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.

For example: BeginnerCamping.pdf

Metadata Settings:
├── Document Version: v2.1
├── Creation Date: 2024-03-15
├── Last Update: 2024-11-20
├── Next Review: 2025-05-20
├── Updating Department: Marketing
└── Version Status: Reviewed and Approved

Why Use Metadata?

In complex data situations, using metadata can help you maintain data quality more conveniently and quickly, helping you:

Improve Management Efficiency

  • Quickly identify document status and version information

  • More organized when managing large amounts of documents

  • Reduce manual search and confirmation time

Ensure Content Quality

  • Use the latest document versions

  • Track document update history and version status

  • Ensure AI assistants use the latest and reviewed content

  • Set regular review reminders to maintain data quality

Adding Metadata to Documents

  1. Enter the document page and click Edit File Information:

  1. Switch to the metadata tab and enter metadata mapping

MaiAgent uses key-value pair mapping to access metadata

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

After adding, you'll see the metadata you just added appear in the field.

Adding Metadata to FAQs

  1. Enter the FAQ management interface in the knowledge base, select the FAQ you want to edit, and click the Edit button

  1. Switch to the metadata page, enter and click Add Metadata

After entering all data, click "Confirm"

The added metadata will appear in the FAQ list

URL is a reserved word in the metadata system. If you set url: https://...your specified URL, when viewing referenced snippets in conversations, your specified URL will override the original file location and open your specified URL instead.

Example Scenario: Brand Spring Sale Campaign

Original Settings:

title: "2025 Spring Mega Sale Details"
content: "This campaign includes storewide 20% off, free gifts with purchase, and more..."
url: https://www.yourstore.com/spring-sale-2025

Usage Effect: When users ask "What promotions are available in the spring sale?" in conversation:

  • 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 redirect to https://www.yourstore.com/spring-sale-2025 campaign page

  • Users 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-maintenance

  • Product Specification Pages: url: https://www.product.com/specs/model-x1

  • Customer Service Policies: url: https://support.company.com/return-policy

  • Event Registration: url: https://events.company.com/register/webinar-2025

The benefit of this setting is that it makes 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 a URL value, clicking reference nodes allows you to view the original document when clicking any node (such as: BeginnerCamping.pdf) (you can set whether to allow users to download original document files in the conversation platform):

View Reference Nodes
View Original File Location

After Setting URL (Using Google as Example)

When clicking the referenced file node (CampingGuidelines.txt) again, it won't show the document preview, but instead open the Google homepage:

When you set a 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, getting more complete information

Last updated

Was this helpful?