# Knowledge Management Permissions (Query Metadata) Overview

## Feature Description

When implementing an AI dialogue system, detailed control over the available scope of "Knowledge Base / AI Assistant / Chat Platform" is usually needed due to different user permissions and usage requirements.

In MaiAgent, you can use Query Metadata attached to different conversation/identity levels to determine "what content this person/conversation can reference".

### What is Query Metadata?

Query Metadata is a set of dynamic conditions that limit the query scope, specifying what "Knowledge Base, FAQ, documents matching tag conditions" and other data content users can query under a certain chat platform.

It doesn't replace roles or contacts, but rather makes these identities "work conditionally", implementing conversation-level least privilege control.

> **Roles/Contacts/Conversations are containers, Query Metadata is the actual condition settings that control visible scope**

{% hint style="info" %}
Learn more through these articles:

* [**Contact Integration Steps**](/tech/maiagent-tech-en/authorization-integration/contacts.md)
* [**Differences between Roles and Contacts**](/tech/maiagent-tech-en/authorization-integration/role-vs-contact.md)
  {% endhint %}

## Permission Level Concept

Before service construction, Agent confirms all available knowledge bases through Query Metadata at different levels, with permission levels referenced in the following order:

```
AI Assistant > Chat Platform > User (Message/Contact/Role) > query_metadata > Query Permissions
```

You can specify permissions at each level using either graphical interface or JSON format

> Reference these documents for operation:
>
> 1. [Graphical Interface Operation Guide (Contact, Internal Q\&A Settings)](/tech/maiagent-tech-en/authorization-integration/zhi-shi-guan-li-quan-xian-query-metadata-cha-xun-yuan-zi-liao-zong-lan/graphical-interface.md)
> 2. [JSON Interface Configuration Guide (Contact, Web Chat Embedding Settings)](/tech/maiagent-tech-en/authorization-integration/zhi-shi-guan-li-quan-xian-query-metadata-cha-xun-yuan-zi-liao-zong-lan/json-interfaces.md)

{% @mermaid/diagram content="flowchart TB
subgraph Identity Layer
Message --> Identity\[Identity Information]
Contact --> Identity
Role --> Identity
end

subgraph Query Condition Layer
Identity --> QM\[query\_metadata conditions]
QM --> KB\[Knowledge Base]
QM --> Chatbot\_file\[File Documents]
QM --> FAQ\[FAQ]
QM --> Label\[Tags]

```
KB --> Filter1[Filter Available Knowledge Bases]
Chatbot_file --> Filter2[Filter Available File Documents]
FAQ --> Filter3[Filter Available FAQs]
Label --> Filter4[Filter Tag Conditions]
```

end

subgraph Response Layer
Filter1 --> Chatbot\[AI Assistant Response Content]
Filter2 --> Chatbot
Filter3 --> Chatbot
Filter4 --> Chatbot
end" %}

* Contact/Role are identity containers
* Message corresponds to controlling which knowledge bases to use during internal conversations through filtering
* `query_metadata` is the "filter condition set" actually executed during conversations

### Document Filter Condition Decision Levels

The open filtering logic is:

{% @mermaid/diagram content="flowchart TB
%% Knowledge Base Level
KB\["Knowledge Base"]

```
%% Document Level
Docs["Documents under Knowledge Base"]

%% Tag Filtering Level
Tags["Filter available documents from opened documents by tags"]

%% Final Result
Result["Final Available Documents"]

%% Connections
KB --> Docs
Docs --> Tags
Tags --> Result

%% Style Settings
classDef kbBox fill:#e3f2fd,stroke:#1976d2,stroke-width:2px,color:#000000
classDef docBox fill:#f3e5f5,stroke:#7b1fa2,stroke-width:2px,color:#000000
classDef tagBox fill:#e8f5e8,stroke:#388e3c,stroke-width:2px,color:#000000
classDef resultBox fill:#fff3e0,stroke:#f57c00,stroke-width:2px,color:#000000

class KB kbBox
class Docs docBox
class Tags tagBox
class Result resultBox" %}
```

Through layer-by-layer transmission, Query Metadata becomes the actual decision basis for AI response logic

## Practical Application Scenarios

<table><thead><tr><th width="162.5028076171875">Identity</th><th>Input Conditions (query_metadata)</th><th>Response Result</th></tr></thead><tbody><tr><td>Visitor</td><td>Knowledge Base: <code>General</code><br>File Documents: None<br>Tags: <code>Visitor</code><br>FAQ: <code>1</code>, <code>2</code></td><td>Get documents with <code>Visitor</code> tag from <code>General</code> knowledge base and FAQ <code>1</code>, FAQ <code>2</code></td></tr><tr><td>Regular Member</td><td>Knowledge Base: <code>General</code><br>File Documents: <code>A</code>, <code>B</code>, <code>C</code><br>Tags: None<br>FAQ: None</td><td>Get documents <code>A</code>, <code>B</code>, <code>C</code> from <code>General</code> knowledge base and all FAQs</td></tr><tr><td>Customer Service</td><td>Knowledge Base: <code>Employee</code><br>File Documents: None<br>Tags: <code>CS</code><br>FAQ: None</td><td>Get documents tagged as <code>CS</code> from <code>Employee</code> knowledge base and all FAQs</td></tr><tr><td>Internal Employee</td><td>Knowledge Base: <code>Employee</code><br>File Documents: <code>A</code>, <code>B</code><br>Tags: None<br>FAQ: None</td><td>Get documents <code>A</code>, <code>B</code> from <code>Employee</code> knowledge base and all FAQs</td></tr><tr><td>Administrator</td><td>Knowledge Base: <code>Employee</code>, <code>General</code><br>File Documents: None<br>Tags: None<br>FAQ: None</td><td>Get all document content and FAQs from <code>Employee</code> and <code>General</code> knowledge bases</td></tr></tbody></table>

***

## Summary: The Value of query\_metadata for Enterprises

🎯 **Multi-dimensional Identity Cross-Control** (Role + Region + Product Line)

🎯 **Real-time Query Control**: No need to copy assistants, just change conditions to adapt to different scenarios

🎯 **Flexible Large Knowledge Base Management**: Tags and knowledge bases can be split and authorized according to scenarios

> **It is recommended to incorporate query\_metadata into the core product architecture, allowing enterprises to achieve maximum authorization flexibility with minimum settings,**\
> **ensuring knowledge security while improving conversation experience and operational efficiency.**


---

# 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.maiagent.ai/tech/maiagent-tech-en/authorization-integration/zhi-shi-guan-li-quan-xian-query-metadata-cha-xun-yuan-zi-liao-zong-lan.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.