klbr/khoj
1
0
Fork 0
mirror of https://github.com/khoaliber/khoj.git synced 2026-03-02 21:19:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

Simplify docs to self-host with pip since can use embedded DB now

Browse Source 
Remove postgres setup instructions from self host with pip docs. It is
unnecessary if embedded postgres DB works on the operating system.
This commit is contained in:
Debanjum
2025-03-29 19:04:56 +05:30
parent 713ba06a8d
commit 85d627ceb0
1 changed files with 13 additions and 59 deletions
Download Patch File Download Diff File Expand all files Collapse all files

72
documentation/docs/get-started/setup.mdx
View File

@@ -115,53 +115,7 @@ Your setup is complete once you see `🌖 Khoj is ready to use` in the server lo
</TabItem>
<TabItem value="pip" label="Pip">
<h3>1. Install Postgres (with PgVector)</h3>
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.
<Tabs groupId="operating-systems" queryString="os">
<TabItem value="macos" label="MacOS">
Install [Postgres.app](https://postgresapp.com/). This comes pre-installed with `pgvector` and relevant dependencies.
</TabItem>
<TabItem value="windows" label="Windows">
For detailed instructions and troubleshooting, see [this section](/contributing/development#2-postgres-installation--setup).
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.
</TabItem>
<TabItem value="linux" label="Linux">
From [official instructions](https://wiki.postgresql.org/wiki/Apt)
</TabItem>
<TabItem value="source" label="From Source">
1. Follow instructions to [Install Postgres](https://www.postgresql.org/download/)
2. Follow instructions to [Install PgVector](https://github.com/pgvector/pgvector#installation) in case you need to manually install it.
</TabItem>
</Tabs>
<h3>2. Create the Khoj database</h3>
<Tabs groupId="operating-systems" queryString="os">
<TabItem value="macos" label="MacOS">
```shell
createdb khoj -U postgres --password
```
</TabItem>
<TabItem value="windows" label="Windows">
```shell
createdb -U postgres khoj --password
```
</TabItem>
<TabItem value="linux" label="Linux">
```shell
sudo -u postgres createdb khoj --password
```
</TabItem>
</Tabs>
:::info[Postgres Env Config]
Make sure to update the `POSTGRES_HOST`, `POSTGRES_PORT`, `POSTGRES_USER`, `POSTGRES_DB` or `POSTGRES_PASSWORD` environment variables to match any customizations in your Postgres configuration.
:::
<h3>3. Install Khoj Server</h3>
<h3>1. Install Khoj Server</h3>
- Make sure [python](https://realpython.com/installing-python/) and [pip](https://pip.pypa.io/en/stable/installation/) are installed on your machine
- Check [llama-cpp-python setup](https://github.com/abetlen/llama-cpp-python?tab=readme-ov-file#supported-backends) if you hit any llama-cpp issues with the installation
@@ -172,12 +126,12 @@ Run the following command in your terminal to install the Khoj server.
<Tabs groupId="gpu" queryString="gpu">
<TabItem value="arm" label="ARM/M1+">
```shell
CMAKE_ARGS="-DGGML_METAL=on" python -m pip install khoj
CMAKE_ARGS="-DGGML_METAL=on" python -m pip install 'khoj[local]'
```
</TabItem>
<TabItem value="intel" label="Intel">
```shell
python -m pip install khoj
python -m pip install 'khoj[local]'
```
</TabItem>
</Tabs>
@@ -188,7 +142,7 @@ python -m pip install khoj
<TabItem value="cpu" label="CPU">
```shell
# Install Khoj
py -m pip install khoj
py -m pip install 'khoj[local]'
```
</TabItem>
<TabItem value="nvidia" label="NVIDIA (CUDA) GPU">
@@ -196,7 +150,7 @@ python -m pip install khoj
# 1. To use NVIDIA (CUDA) GPU
$env:CMAKE_ARGS = "-DGGML_CUDA=on"
# 2. Install Khoj
py -m pip install khoj
py -m pip install 'khoj[local]'
```
</TabItem>
<TabItem value="amd" label="AMD (ROCm) GPU">
@@ -204,7 +158,7 @@ python -m pip install khoj
# 1. To use AMD (ROCm) GPU
$env:CMAKE_ARGS = "-DGGML_HIPBLAS=on"
# 2. Install Khoj
py -m pip install khoj
py -m pip install 'khoj[local]'
```
</TabItem>
<TabItem value="vulkan" label="VULKAN GPU">
@@ -212,7 +166,7 @@ python -m pip install khoj
# 1. To use VULCAN GPU
$env:CMAKE_ARGS = "-DGGML_VULKAN=on"
# 2. Install Khoj
py -m pip install khoj
py -m pip install 'khoj[local]'
```
</TabItem>
</Tabs>
@@ -221,34 +175,34 @@ python -m pip install khoj
<Tabs groupId="gpu" queryString="gpu">
<TabItem value="cpu" label="CPU">
```shell
python -m pip install khoj
python -m pip install 'khoj[local]'
```
</TabItem>
<TabItem value="nvidia" label="NVIDIA (CUDA) GPU">
```shell
CMAKE_ARGS="-DGGML_CUDA=on" FORCE_CMAKE=1 python -m pip install khoj
CMAKE_ARGS="-DGGML_CUDA=on" FORCE_CMAKE=1 python -m pip install 'khoj[local]'
```
</TabItem>
<TabItem value="amd" label="AMD (ROCm) GPU">
```shell
CMAKE_ARGS="-DGGML_HIPBLAS=on" FORCE_CMAKE=1 python -m pip install khoj
CMAKE_ARGS="-DGGML_HIPBLAS=on" FORCE_CMAKE=1 python -m pip install 'khoj[local]'
```
</TabItem>
<TabItem value="vulkan" label="VULKAN GPU">
```shell
CMAKE_ARGS="-DGGML_VULKAN=on" FORCE_CMAKE=1 python -m pip install khoj
CMAKE_ARGS="-DGGML_VULKAN=on" FORCE_CMAKE=1 python -m pip install 'khoj[local]'
```
</TabItem>
</Tabs>
</TabItem>
</Tabs>
<h3>4. Start Khoj Server</h3>
<h3>2. Start Khoj Server</h3>
Run the following command from your terminal to start the Khoj service.
```shell
khoj --anonymous-mode
USE_EMBEDDED_DB="true" khoj --anonymous-mode
```
`--anonymous-mode` allows access to Khoj without requiring login. This is usually fine for local only, single user setups. If you need authentication follow the [authentication setup docs](/advanced/authentication).