> For the complete documentation index, see [llms.txt](https://mariadb.com/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://mariadb.com/docs/tools/mariadb-ai-rag/api-reference.md).

# API Reference

The MariaDB AI RAG API provides a comprehensive RESTful interface for document ingestion, chunking, retrieval, and AI-powered generation. All endpoints require JWT authentication except for the login endpoint.

## Available API Documentation

### [API Reference](/docs/tools/mariadb-ai-rag/api-reference/api-reference.md)

Complete reference for all API endpoints including:

* Document ingestion and management
* Chunking operations
* Retrieval and search
* AI generation
* Batch operations

### [Access Control](/docs/tools/mariadb-ai-rag/api-reference/access-control.md)

Authentication and authorization documentation:

* JWT-based authentication
* User management endpoints
* Role-based access control
* Document sharing and permissions
* User directory management

### [Database Integration](/docs/tools/mariadb-ai-rag/api-reference/database-integration.md)

Direct database ingestion capabilities:

* SQL query ingestion
* Table and view ingestion
* Role-based database access
* Structured data processing

### [Orchestration](/docs/tools/mariadb-ai-rag/api-reference/orchestration.md)

High-level workflow endpoints:

* Full pipeline orchestration
* Ingestion orchestration
* Generation orchestration
* Multi-step RAG workflows

## Quick Start

All API requests require authentication. First, obtain a JWT token:

```bash
curl -X POST "http://localhost:8000/token" \
  -H "Content-Type: application/x-www-form-urlencoded" \
  -d "username=user@example.com&password=your_password"
```

Then include the token in subsequent requests:

```bash
curl -X GET "http://localhost:8000/documents" \
  -H "Authorization: Bearer YOUR_TOKEN"
```

## Base URL

The default base URL for the API is:

```
http://localhost:8000
```

For production deployments, replace with your configured host and port.

<sub>*This page is: Copyright © 2025 MariaDB. All rights reserved.*</sub>

{% @marketo/form formId="4316" %}


---

# 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://mariadb.com/docs/tools/mariadb-ai-rag/api-reference.md?ask=<question>&goal=<endgoal>
```

`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.