> For the complete documentation index, see [llms.txt](https://docs.glbnxt.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.glbnxt.com/tutorials/guides/openwebui/embedding-openwebui.md).

# Embedding in OpenWebUI

### Introduction

An embedding is a process that translates unstructured text—such as PDFs, markdown files, or website content—into high-dimensional numerical vectors that capture the actual context and meaning of your data. Instead of performing simple keyword searches, the system uses these mathematical representations to quickly compare and match queries with relevant passages across your uploaded knowledge bases.

By setting up an embedding model in OpenWebUI, you power its built-in **Retrieval-Augmented Generation (RAG)** engine. This enables AI models to search through your private documents in real time, extract precise context, and deliver highly accurate, grounded answers directly within your chat threads.

***

### Prerequisites

Before configuring embeddings in OpenWebUI, ensure you have the following:

* **OpenWebUI Environment:** Admin access to OpenWebUI running within your secure GLBNXT workspace.
* **GLBNXT API Key:** Create a [GLBNXT API Key](https://platform.glbnxt.com/api-keys) to track your embeddings.

***

### Configuration

#### Step 1: Create an API Key

1. Go to [GLBNXT API Keys](https://platform.glbnxt.com/api-keys) and click on `+ Create Key`.
2. Enter a name, risk level, expiration and select models (make sure to at least include the embedding models).
3. Copy the API Key and store it somewhere safe.

#### Step 2: Configure embedding in OpenWebUI

1. Open OpenWebUI, make sure that you log in as an admin.
2. Select the Admin Account, go to Admin Panel > Settings > Documents.
3. Halfway the page you will find "Embedding", click on "Default (SentenceTransformers)".

<img src="https://4059874881-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FgWFuB1gB3woFh7jbZA3S%2Fuploads%2Fgit-blob-78d4989e5a2c3a78a9f0f7063d12fb25d142b0e4%2Fembedding-openwebui.png?alt=media" alt="" width="800">

4. A dropdown will appear, then select from the dropdown "OpenAI".

<img src="https://4059874881-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FgWFuB1gB3woFh7jbZA3S%2Fuploads%2Fgit-blob-471ee0c63fcf8fa99d539ef4dde6c8af10c92fa8%2Fembedding-openwebui-1.png?alt=media" alt="" width="800">

5. Use the **API Base URL:** OpenAI-compatible endpoint found in [GLBNXT API Keys](https://platform.glbnxt.com/api-keys).
6. Enter the API Key from Step 1 in the API Key field in OpenWebUI.
7. Then go to the [GLBNXT Model Hub](https://platform.glbnxt.com/models) , search for `embedding` and copy the model ID of your preferred embedding model. In the example below, we have chosen for `qwen3-embedding:8b`

<img src="https://4059874881-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FgWFuB1gB3woFh7jbZA3S%2Fuploads%2Fgit-blob-a5815accb858bf73343135c8044f6ba00c7ba858%2Fembedding-openwebui-2.png?alt=media" alt="" width="800">

8. Press `Save`, your OpenWebUI instance is now ready to use embedding.

***

*Need help? Contact the GLBNXT support team or ask a GLBNXT agent to walk you through the setup.*


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.glbnxt.com/tutorials/guides/openwebui/embedding-openwebui.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
