# Knowledge Base

The Knowledge Bases section under the Data module provides centralized content management for powering AI agents, automated responses, and customer support workflows. This system enables teams to organize, version, and deploy structured information across all customer touchpoints.

## Knowledge Base Dashboard

**Dashboard Overview** The main interface displays all knowledge bases with detailed metadata:

* **Name:** Knowledge base identifier
* **Data Type:** Content format (Documents, Table, Proxy, Media Catalogue, Json)
* **Status:** Current state (Active, Inactive)
* **Size:** Content volume (Files, Rows, Items, Keys)
* **Last Updated:** Most recent modification timestamp
* **Connections:** Number of integrations using this knowledge base
* **Tags:** Classification labels for organization

<figure><img src="/files/baWOl1mDJmGa21AuUfh1" alt=""><figcaption></figcaption></figure>

## Available Data Types

Click **Create New KB** to select from available data types:

<figure><img src="/files/p28WgveMcHNqmZIpJ0bg" alt=""><figcaption></figcaption></figure>

* **Documents:** Store and manage text-based content including PDFs, articles, FAQs, and policy documents. Ideal for AI agent responses and automated customer support.
* **Table:** Structured data in rows and columns for systematic information retrieval. Supports CSV imports and database connections for dynamic content updates.
* **Proxy:** Dynamic data connections that retrieve real-time information from both external sources (third-party APIs and databases) and Angoor.ai's internal database systems without storing data locally.
* **Media Catalogue:** Visual content management for images, videos, and multimedia assets used in customer communications and product showcases.
* **Json:** Structured data objects for complex information hierarchies and API integrations requiring specific data formats.
* **Links:** URL collections and web resource management for quick reference and automated link sharing.

## Best Practices

* Knowledge bases directly impact AI agent performance and customer experience. Ensure content accuracy and regular maintenance for optimal results.
* Keep document sizes manageable for faster AI processing.
* Use appropriate data types for content format and use case.
* Regular cleanup of outdated or redundant information.


---

# 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://angoor-ai.gitbook.io/angoor-ai/basics/interactive-blocks/knowledge-base.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.