> For the complete documentation index, see [llms.txt](https://docs.skyone.cloud/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.skyone.cloud/english/skyone-studio/artificial-intelligence/voxone/using-rag-in-voxone.md).
# Using RAG in VoxOne
**RAG (Retrieval-Augmented Generation)** is a feature that allows the agent to respond using documents or URLs you upload as its reference.
This means that when you upload a PDF, TXT, DOC, or add a link, Vox One reads that content and uses it as the basis for responses.
Vox One includes a dedicated **RAG** tab where you can create, manage, and test your own RAGs.
### **How to access**
1. Access **Vox One**. At the top of the screen, click the **“RAG”** tab.
2. Create a New RAG
* Click **“New RAG.”**
* Give it a name (e.g., *TestRAG*).
* Click "**Save**.
3. Upload Content to the RAG.
Once created, the newly created RAG will be available to receive the content.
To upload the content, click on "**Customize**" next to your RAG.
On the Main Settings screen, click "**Add resource**".
On “**Configure resources**” modal, add the **Name** and **Description** (optional).
You can add the resources in two ways:
a) **Web**
* Click "**Add URL".**
* Paste the link to the documentation or website you want to use.
* After paste URL, click "**Save resource**".
b) **Document**
* Upload a PDF, TXT, DOC, or similar file.
After upload, click "**Save resource**".
The main configuration screen will display again, this time with the added resource. Click "**Update RAG**" to finish.
4\. Test the RAG
* Inside the RAG you created, enter a keyword.
* Click "**Test"**.
* If everything is correct, the response will be based on the uploaded content.
5\. Link the RAG to an Agent
* Go to the **Agents** section.
* Create a new agent or edit an existing one.
* Select the model (e.g., *Ultravox*).
* In the **Manage your RAG** field, choose the RAG you created.
* Click "**Save**".
6\. Test the agent with the RAG
* Run a test or simulate a conversation.
* The agent should respond based on the content you added to the RAG.
***
### **Glossary**
| Terms | Description |
| ---------------------------------------- | ----------------------------------------------------------------------------------------------- |
| **RAG (Retrieval-Augmented Generation)** | A feature that allows the agent to consult documents or URLs to respond using real information. |
| **URL** | A link to a webpage that contains the content you want to use. |
| **Agent** | The intelligent assistant that responds to users inside Vox One. |
***
### **FAQ**
Can I upload more than one file to the same RAG?
Yes. You can upload multiple documents or URLs.
Will the agent respond only using the RAG?
No. It uses the RAG as a reference but still combines the content with the AI model.
Can I edit a RAG after it has been created?
Yes, you can add new files or remove old documents.
What should I do if the test doesn’t return the expected response?
Check whether the document was uploaded correctly and whether the keyword exists within the content.
---
# 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://docs.skyone.cloud/english/skyone-studio/artificial-intelligence/voxone/using-rag-in-voxone.md?ask=&goal=
```
`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.