# RAG Collections

Enhance knowledge retrieval with **Retrieval-Augmented Generation** (**RAG) Collections**, enabling designers to create and configure collections from external data sources. 

RAG collections help designers efficiently manage and organize data from files and URLs using AI-powered semantic analysis for more relevant retrieval. They serve as a structured data source in FlowGenie Studio, enhancing Genies' ability to access and use information.

* **External Data Sources**: Upload files, or URLs, with automatic data extraction and storage.
* **FlowGenie Integration:** Genies use RAG collections for better data retrieval, with configurable match thresholds and limits.
* **Enhanced Insights:** AI-driven analysis improves question-answering with precise, context-aware responses.
* **External System Support:** APIs and data connectors enable seamless data exchange.
* **Automation:** Files added through processes are automatically stored in RAG collections, streamlining workflows.

{% embed url="<https://demos.processmaker.com/demo/cm8l1ou9e00yfzb0ipgrs47vx>" %}

{% hint style="success" %}

#### <mark style="color:green;">Learn More</mark>

* [**ProcessMaker Knowledge Cente**~~**r**~~](https://docs.processmaker.com/docs/rag-collections): Find detailed product documentation.
* [**ProcessMaker University**](https://university.processmaker.com/course/view.php?id=305): Enroll in free courses to learn how to use ProcessMaker Platform.
  {% endhint %}


---

# 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://processmaker.gitbook.io/quick-start-guides/spring-2025/new/rag-collections.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.