1. **Privacy**: Your data will never have to leave your private network. You can even use Khoj without an internet connection if deployed on your personal computer.
2. **Customization**: You can customize Khoj to your liking, from models, to host URL, to feature enablement.
If you want to use the offline chat model and you have a GPU, you should use Installation Option 2 - local setup via the Python package directly. Our Docker image doesn't currently support running the offline chat model on GPU, making inference times really slow.
1. Get the sample docker-compose file [from Github](https://github.com/khoj-ai/khoj/blob/master/docker-compose.yml).
2. Configure the environment variables in the docker-compose.yml to your choosing.<br />
Note: *Your admin account will automatically be created based on the admin credentials in that file, so pay attention to those.*
3. Now start the container by running the following command in the same directory as your docker-compose.yml file. This will automatically setup the database and run the Khoj server.
Khoj uses Postgres DB for all server configuration and to scale to multi-user setups. It uses the pgvector package in Postgres to manage your document embeddings. Both Postgres and pgvector need to be installed for Khoj to work.
1. Use the [recommended installer](https://www.postgresql.org/download/windows/).
2. Follow instructions to [Install PgVector](https://github.com/pgvector/pgvector#windows) in case you need to manually install it. Windows support is experimental for pgvector currently, so we recommend using Docker.
Make sure to update your environment variables to match your Postgres configuration if you're using a different name. The default values should work for most people. When prompted for a password, you can use the default password `postgres`, or configure it to your preference. Make sure to set the environment variable `POSTGRES_PASSWORD` to the same value as the password you set here.
- Check [llama-cpp-python setup](https://python.langchain.com/docs/integrations/llms/llamacpp#installation) if you hit any llama-cpp issues with the installation
`--anonymous-mode` allows you to run the server without setting up Google credentials for login. This allows you to use any of the clients without a login wall. If you want to use Google login, you can skip this flag, but you will have to add your Google developer credentials.
On the first run, you will be prompted to input credentials for your admin account and do some basic configuration for your chat model settings. Once created, you can go to http://localhost:42110/server/admin and login with the credentials you just created.
Note: To start Khoj automatically in the background use [Task scheduler](https://www.windowscentral.com/how-create-automated-task-using-task-scheduler-windows-10) on Windows or [Cron](https://en.wikipedia.org/wiki/Cron) on Mac, Linux (e.g. with `@reboot khoj`)
Setup which chat model you'd want to use. Khoj supports local and online chat models.
:::tip[Multiple Chat Models]
Add a `ServerChatSettings` with `Default` and `Summarizer` fields set to your preferred chat model via [the admin panel](http://localhost:42110/server/admin/database/serverchatsettings/add/). Otherwise Khoj defaults to use the first chat model in your [ChatModelOptions](http://localhost:42110/server/admin/database/chatmodeloptions/) for all non chat response generation tasks.
1. Go to the [OpenAI settings](http://localhost:42110/server/admin/database/openaiprocessorconversationconfig/) in the server admin settings to add an OpenAI processor conversation config. This is where you set your API key and server API base URL. The API base URL is optional - it's only relevant if you're using another OpenAI-compatible proxy server.
2. Go over to configure your [chat model options](http://localhost:42110/server/admin/database/chatmodeloptions/). Set the `chat-model` field to a supported chat model[^1] of your choice. For example, you can specify `gpt-4o` if you're using OpenAI.
- Make sure to set the `model-type` field to `OpenAI`.
- The `tokenizer` and `max-prompt-size` fields are optional. Set them only if you're sure of the tokenizer or token limit for the model you're using. Contact us if you're unsure what to do here.
- If your model supports vision, set the `vision enabled` field to `true`. This is currently only supported for OpenAI models with vision capabilities.
##### Configure Anthropic Chat
1. Go to the [OpenAI settings](http://localhost:42110/server/admin/database/openaiprocessorconversationconfig/) in the server admin settings to add an OpenAI processor conversation config. This is kind of a misnomer, we know. Do not configure the API base url. Just add your API key and give the configuration a friendly name.
2. Go over to configure your [chat model options](http://localhost:42110/server/admin/database/chatmodeloptions/). Set the `chat-model` field to a supported chat model by Anthropic of your choice. For example, you can specify `claude-3-5-sonnet-20240620`.
- Make sure to set the `model-type` field to `Anthropic`.
- The `tokenizer` and `max-prompt-size` fields are optional. Set them only if you're sure of the tokenizer or token limit for the model you're using. Contact us if you're unsure what to do here.
2. Go over to configure your [chat model options](http://localhost:42110/server/admin/database/chatmodeloptions/). Set the `chat-model` field to a supported chat model[^1] of your choice. For example, we recommend `bartowski/Meta-Llama-3.1-8B-Instruct-GGUF`, but [any gguf model on huggingface](https://huggingface.co/models?library=gguf) should work.
- The `tokenizer` and `max-prompt-size` fields are optional. You can set these for non-standard models (i.e not Mistral or Llama based models) or when you know the token limit of the model to improve context stuffing.
You can sync your files and folders with Khoj using the [Desktop](/clients/desktop#setup), [Obsidian](/clients/obsidian#setup), or [Emacs](/clients/emacs#setup) clients or just drag and drop specific files on the [website](/clients/web#upload-documents). You can also directly sync your [Notion workspace](/data-sources/notion_integration).
[^1]: Khoj, by default, can use [OpenAI GPT3.5+ chat models](https://platform.openai.com/docs/models/overview) or [GGUF chat models](https://huggingface.co/models?library=gguf). See [this section](/advanced/use-openai-proxy) on how to locally use OpenAI-format compatible proxy servers.
Set the host URL on your clients settings page to your Khoj server URL. By default, use `http://127.0.0.1:42110` or `http://localhost:42110`. Note that `localhost` may not work in all cases.
From the same directory where you have your `docker-compose` file, run the command below to remove the server to delete its containers, networks, images and volumes.
```shell
docker-compose down --volumes
```
</TabItem>
<TabItem value="emacs" label="Emacs">
Uninstall the khoj Emacs, or desktop client in the standard way from Emacs or your OS respectively
You can also `rm -rf ~/.khoj` to remove the Khoj data directory if did a local install.
</TabItem>
<TabItem value="obsidian" label="Obsidian">
Uninstall the khoj Obisidan, or desktop client in the standard way from Obsidian or your OS respectively
You can also `rm -rf ~/.khoj` to remove the Khoj data directory if did a local install.
#### Dependency conflict when trying to install Khoj python package with pip
- **Reason**: When conflicting dependency versions are required by Khoj vs other python packages installed on your system
- **Fix**: Install Khoj in a python virtual environment using [venv](https://docs.python.org/3/library/venv.html) or [pipx](https://pypa.github.io/pipx) to avoid this dependency conflicts
- **Fix**: Install Rust to build the tokenizers package. For example on Mac run:
```shell
brew install rustup
rustup-init
source ~/.cargo/env
```
- **Refer**: [Issue with Fix](https://github.com/khoj-ai/khoj/issues/82#issuecomment-1241890946) for more details
#### Khoj in Docker errors out with \"Killed\" in error message
- **Fix**: Increase RAM available to Docker Containers in Docker Settings
- **Refer**: [StackOverflow Solution](https://stackoverflow.com/a/50770267), [Configure Resources on Docker for Mac](https://docs.docker.com/desktop/mac/#resources)
You can self-host Khoj behind a custom domain as well. To do so, you need to set the `KHOJ_DOMAIN` environment variable to your domain (e.g., `export KHOJ_DOMAIN=my-khoj-domain.com` or add it to your `docker-compose.yml`). By default, the Khoj server you set up will not be accessible outside of `localhost` or `127.0.0.1`.
:::warning[Without HTTPS certificate]
To expose Khoj on a custom domain over the public internet, use of an SSL certificate is strongly recommended. You can use [Let's Encrypt](https://letsencrypt.org/) to get a free SSL certificate for your domain.
To disable HTTPS, set the `KHOJ_NO_HTTPS` environment variable to `True`. This can be useful if Khoj is only accessible behind a secure, private network.
