# Self-hosted Embedder installation 

**Prerequisites** 

* A system with Ubuntu with docker and docker-compose installed and with the latest Nvidia driver for the GPU-s in the system. 
* Install the [Nvidia Container Toolkit.](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html) 
* Install git-lfs with the command: sudo apt-get install git-lfs 
* The embedder service can also be runned with multiple instances if necessary. 
* Copy the provided tar file and the embedder-wrapper folder into the server, where the embedder service will be hosted. After that, run this command: 
* docker load --input embedder-service.tar 

For running multiple instances modify the docker-compose file, copy the part after the ‘services’ as many times as many instances you would like to run. Modify the service and the container name for each copy. Also modify the ports so the instances could run separately. 

The model will be downloaded at the first start of the container. 

**Start the instances** 

Go back to the root folder and execute this command: 

* docker compose up –d 

The embedder service should start without errors. 

**Load balancers** 

If you are running multiple instances of LLMs and/or embedders, you will need separate load balancers which will handle the concurrent loads. We will provide you with further instructions for installing load balanacers during the onboarding period.


---

# 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://docs.kodesage.ai/deploy-kodesage/self-hosted-embedder-installation.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.