> For the complete documentation index, see [llms.txt](https://docs.kodesage.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.kodesage.ai/deploy-kodesage/self-hosted-llm-installation.md).

# Self-hosted LLM installation

Installation guide for self-hosted LLM setup

**Prerequisites**&#x20;

* A system with Ubuntu with docker and docker-compose installed (as mentioned before) and with the latest Nvidia driver for the GPU-s in the system.&#x20;
* Install the [Nvidia Container Toolkit.](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html)&#x20;
* Install git-lfs with the command: sudo apt-get install git-lfs&#x20;

Copy the provided text-generation-webui folder to a server with one or more Nvidia GPU-s. &#x20;

**With multiple GPU-s**&#x20;

You can modify the compose file to add more instances if you have more GPU-s. For this copy the part from the  ‘text-generation-webui-docker-1:’ as many times as the number of GPU-s in the system. Change the ‘device\_ids:’ part to the corresponding GPU id, which you can check by executing the command ‘nvidia-smi’ in the system’s terminal.&#x20;

Change the service and the container name to a different one than the first one (change the number).&#x20;

Finally, change the ports exposed to a different one than the first for each instance.&#x20;

**Download the model**

We will provide you with the most up-to-date LLM model during onboarding. But you can also use the model of your choice.


---

# 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.kodesage.ai/deploy-kodesage/self-hosted-llm-installation.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.
