# Reference

This section provides detailed reference information for configuring and integrating the MariaDB AI RAG system.

## Documentation in This Section

### [Configuration Guide](/docs/tools/mariadb-ai-rag/reference/configuration-guide-config.env.md)

Complete reference for all environment variables:

* Database configuration
* API keys and secrets
* Embedding provider settings
* LLM provider configuration
* Service ports and hosts
* Authentication settings

### [Supported File Formats](/docs/tools/mariadb-ai-rag/reference/supported-formats.md)

List of supported document formats for ingestion:

* PDF documents
* Microsoft Office files (DOCX, XLSX, PPTX)
* Text files (TXT, MD, CSV)
* Code files (Python, JavaScript, Java, etc.)
* And more

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

Guide for integrating the RAG API with external systems:

* REST API integration examples
* Authentication workflows
* Client library usage
* Document management system integration
* Business intelligence tool integration
* Custom application integration

## Configuration Best Practices

When configuring your MariaDB AI RAG deployment:

1. **Security**: Always use strong secrets for JWT tokens and API keys
2. **Performance**: Configure appropriate batch sizes for your workload
3. **Scalability**: Set connection pool sizes based on expected load
4. **Monitoring**: Enable logging and health check endpoints
5. **Integration**: Use environment variables for flexible deployment

## Additional Resources

* [API Reference](/docs/tools/mariadb-ai-rag/api-reference.md) - Complete API endpoint documentation
* [Configuration Guide](/docs/tools/mariadb-ai-rag/getting-started/configuration.md) - Detailed configuration instructions

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

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


---

# 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://mariadb.com/docs/tools/mariadb-ai-rag/reference.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.