jan/docs/docs/guides/install.mdx
2024-03-19 10:57:12 +07:00

296 lines
13 KiB
Plaintext

---
title: Installation
sidebar_position: 2
hide_table_of_contents: true
description: Jan is a ChatGPT-alternative that runs on your own computer, with a local API server.
keywords:
[
Jan AI,
Jan,
ChatGPT alternative,
local AI,
private AI,
conversational AI,
no-subscription fee,
large language model,
]
---
<head>
<title>Installation - Jan Guides</title>
<meta name="description" content="Instructions for installing Jan AI on Mac, Windows, Linux, and Docker, along with prerequisites and considerations for each platform."/>
<meta name="keywords" content="Jan AI, Jan, ChatGPT alternative, local AI, private AI, conversational AI, no-subscription fee, large language model, installation, macOS, Windows, Linux, Docker"/>
<meta property="og:title" content="Installation - Jan Guides"/>
<meta property="og:description" content="Instructions for installing Jan AI on Mac, Windows, Linux, and Docker, along with prerequisites and considerations for each platform."/>
<meta property="og:url" content="https://jan.ai/guides/installation"/>
<meta name="twitter:card" content="summary"/>
<meta name="twitter:title" content="Installation - Jan Guides"/>
<meta name="twitter:description" content="Instructions for installing Jan AI on Mac, Windows, Linux, and Docker, along with prerequisites and considerations for each platform."/>
</head>
import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';
import installImageURL from './assets/jan-ai-download.png';
<Tabs>
<TabItem value="mac" label = "Mac" default>
### Pre-requisites
Before installing Jan, ensure :
- You have a Mac with an Apple Silicon Processor.
- Homebrew and its dependencies are installed. (for Installing Jan with Homebrew Package)
- Your macOS version is 10.15 or higher.
### Stable Releases
To download stable releases, go to [Jan.ai](https://jan.ai/) > select **Download for Mac**.
The download should be available as a `.dmg`.
### Nightly Releases
We provide the Nightly Release so that you can test new features and see what might be coming in a future stable release. Please be aware that there might be bugs!
You can download it from [Jan's Discord](https://discord.gg/FTk2MvZwJH) in the [`#nightly-builds`](https://discord.gg/q8szebnxZ7) channel.
### Experimental Model
To enable the experimental mode, go to **Settings** > **Advanced Settings** and toggle the **Experimental Mode**
### Install with Homebrew
Install Jan with the following Homebrew command:
```brew
brew install --cask jan
```
:::warning
Homebrew package installation is currently limited to **Apple Silicon Macs**, with upcoming support for Windows and Linux.
:::
</TabItem>
<TabItem value = "windows" label = "Windows">
### Pre-requisites
Ensure that your system meets the following requirements:
- Windows 10 or higher is required to run Jan.
To enable GPU support, you will need:
- NVIDIA GPU with CUDA Toolkit 11.7 or higher
- NVIDIA driver 470.63.01 or higher
### Stable Releases
To download stable releases, go to [Jan.ai](https://jan.ai/) > select **Download for Windows**.
The download should be available as a `.exe` file.
### Nightly Releases
We provide the Nightly Release so that you can test new features and see what might be coming in a future stable release. Please be aware that there might be bugs!
You can download it from [Jan's Discord](https://discord.gg/FTk2MvZwJH) in the [`#nightly-builds`](https://discord.gg/q8szebnxZ7) channel.
### Experimental Model
To enable the experimental mode, go to **Settings** > **Advanced Settings** and toggle the **Experimental Mode**
### Default Installation Directory
By default, Jan is installed in the following directory:
```sh
# Default installation directory
C:\Users\{username}\AppData\Local\Programs\Jan
```
:::warning
If you are stuck in a broken build, go to the [Broken Build](/guides/common-error/broken-build) section of Common Errors.
:::
</TabItem>
<TabItem value = "linux" label = "Linux">
### Pre-requisites
Ensure that your system meets the following requirements:
- glibc 2.27 or higher (check with `ldd --version`)
- gcc 11, g++ 11, cpp 11, or higher, refer to this link for more information.
To enable GPU support, you will need:
- NVIDIA GPU with CUDA Toolkit 11.7 or higher
- NVIDIA driver 470.63.01 or higher
### Stable Releases
To download stable releases, go to [Jan.ai](https://jan.ai/) > select **Download for Linux**.
The download should be available as a `.AppImage` file or a `.deb` file.
### Nightly Releases
We provide the Nightly Release so that you can test new features and see what might be coming in a future stable release. Please be aware that there might be bugs!
You can download it from [Jan's Discord](https://discord.gg/FTk2MvZwJH) in the [`#nightly-builds`](https://discord.gg/q8szebnxZ7) channel.
### Experimental Model
To enable the experimental mode, go to **Settings** > **Advanced Settings** and toggle the **Experimental Mode**
<Tabs groupId = "linux_type">
<TabItem value="linux_main" label = "Linux">
To install Jan, you should use your package manager's install or `dpkg`.
</TabItem>
<TabItem value = "deb_ub" label = "Debian / Ubuntu">
To install Jan, run the following command:
```sh
# Install Jan using dpkg
sudo dpkg -i jan-linux-amd64-{version}.deb
# Install Jan using apt-get
sudo apt-get install ./jan-linux-amd64-{version}.deb
# where jan-linux-amd64-{version}.deb is path to the Jan package
```
</TabItem>
<TabItem value = "other" label = "Others">
To install Jan, run the following commands:
```sh
# Install Jan using AppImage
chmod +x jan-linux-x86_64-{version}.AppImage
./jan-linux-x86_64-{version}.AppImage
# where jan-linux-x86_64-{version}.AppImage is path to the Jan package
```
</TabItem>
</Tabs>
:::warning
If you are stuck in a broken build, go to the [Broken Build](/guides/common-error/broken-build) section of Common Errors.
:::
</TabItem>
<TabItem value="docker" label = "Docker" default>
### Pre-requisites
Ensure that your system meets the following requirements:
- Linux or WSL2 Docker
- Latest Docker Engine and Docker Compose
To enable GPU support, you will need:
- `nvidia-driver`
- `nvidia-docker2`
:::note
- If you have not installed Docker, follow the instructions [here](https://docs.docker.com/engine/install/ubuntu/).
- If you have not installed the required file for GPU support, follow the instructions [here](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html).
:::
### Run Jan in Docker
You can run Jan in Docker with two methods:
1. Run Jan in CPU mode
2. Run Jan in GPU mode
<Tabs groupId = "ldocker_type">
<TabItem value="docker_cpu" label = "CPU">
To run Jan in Docker CPU mode, by using the following code:
```bash
# cpu mode with default file system
docker compose --profile cpu-fs up -d
# cpu mode with S3 file system
docker compose --profile cpu-s3fs up -d
```
</TabItem>
<TabItem value="docker_gpu" label = "GPU">
To run Jan in Docker CPU mode, follow the steps below:
1. Check CUDA compatibility with your NVIDIA driver by running nvidia-smi and check the CUDA version in the output as shown below:
```sh
nvidia-smi
# Output
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 531.18 Driver Version: 531.18 CUDA Version: 12.1 |
|-----------------------------------------+----------------------+----------------------+
| GPU Name TCC/WDDM | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+======================+======================|
| 0 NVIDIA GeForce RTX 4070 Ti WDDM | 00000000:01:00.0 On | N/A |
| 0% 44C P8 16W / 285W| 1481MiB / 12282MiB | 2% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+
| 1 NVIDIA GeForce GTX 1660 Ti WDDM | 00000000:02:00.0 Off | N/A |
| 0% 49C P8 14W / 120W| 0MiB / 6144MiB | 0% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+
| 2 NVIDIA GeForce GTX 1660 Ti WDDM | 00000000:05:00.0 Off | N/A |
| 29% 38C P8 11W / 120W| 0MiB / 6144MiB | 0% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+
+---------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=======================================================================================|
```
2. Visit [NVIDIA NGC Catalog](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/cuda/tags) and find the smallest minor version of image tag that matches your CUDA version (e.g., 12.1 -> 12.1.0)
3. Update the `Dockerfile.gpu` line number 5 with the latest minor version of the image tag from step 2 (e.g. change `FROM nvidia/cuda:12.2.0-runtime-ubuntu22.04 AS base` to `FROM nvidia/cuda:12.1.0-runtime-ubuntu22.04 AS base`)
4. Run Jan in GPU mode by using the following command:
```bash
# GPU mode with default file system
docker compose --profile gpu-fs up -d
# GPU mode with S3 file system
docker compose --profile gpu-s3fs up -d
```
</TabItem>
</Tabs>
### Docker Compose Profile and Environment
The available Docker Compose profile and the environment variables listed below:
#### Docker Compose Profile
| Profile | Description |
|-----------|-------------------------------------------|
| cpu-fs | Run Jan in CPU mode with default file system |
| cpu-s3fs | Run Jan in CPU mode with S3 file system |
| gpu-fs | Run Jan in GPU mode with default file system |
| gpu-s3fs | Run Jan in GPU mode with S3 file system |
#### Environment Variables
| Environment Variable | Description |
|--------------------------|------------------------------------------------------------|
| S3_BUCKET_NAME | S3 bucket name - leave blank for default file system |
| AWS_ACCESS_KEY_ID | AWS access key ID - leave blank for default file system |
| AWS_SECRET_ACCESS_KEY | AWS secret access key - leave blank for default file system|
| AWS_ENDPOINT | AWS endpoint URL - leave blank for default file system |
| AWS_REGION | AWS region - leave blank for default file system |
| API_BASE_URL | Jan Server URL, please modify it as your public ip address or domain name default http://localhost:1377 |
:::warning
If you are stuck in a broken build, go to the [Broken Build](/guides/common-error/broken-build/) section of Common Errors.
:::
</TabItem>
</Tabs>