Merge branch 'master' into fix-1000-file-index-update-limit

This commit is contained in:
Debanjum Singh Solanky
2024-01-16 16:50:58 +05:30
80 changed files with 24067 additions and 467 deletions

View File

@@ -0,0 +1,46 @@
name: build and deploy github pages for documentation
on:
push:
branches:
- 'master'
permissions:
contents: read
pages: write
id-token: write
jobs:
deploy:
environment:
name: github-pages
url: https://docs.khoj.dev
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@v3
# 👇 Build steps
- name: Set up Node.js
uses: actions/setup-node@v3
with:
node-version: 18.x
cache: yarn
cache-dependency-path: documentation/yarn.lock
- name: Install dependencies
run: |
cd documentation
yarn install --frozen-lockfile --non-interactive
- name: Build
run: |
cd documentation
yarn build
# 👆 Build steps
- name: Setup Pages
uses: actions/configure-pages@v3
- name: Upload artifact
uses: actions/upload-pages-artifact@v2
with:
# 👇 Specify build output path
path: documentation/build
- name: Deploy to GitHub Pages
id: deployment
uses: actions/deploy-pages@v2

View File

@@ -40,7 +40,7 @@ It works with jpeg, markdown, notion, org-mode, pdf files and github repositorie
|:---------:|:-------:|
| Quickly retrieve relevant documents using natural language | Get answers and create content from your existing knowledge base |
| Does not need internet | Can be configured to work without internet |
| <img src="https://docs.khoj.dev/assets/khoj_search_on_web.png" width="400px"> | <img src="https://docs.khoj.dev/assets/khoj_chat_on_web.png" width="400px"> |
| <img src="https://docs.khoj.dev/img/khoj_search_on_web.png" width="400px"> | <img src="https://docs.khoj.dev/img/khoj_chat_on_web.png" width="400px"> |
## Contributors
Cheers to our awesome contributors! 🎉

View File

@@ -1 +0,0 @@
docs.khoj.dev

View File

@@ -1,53 +0,0 @@
<p align="center"><img src="./assets/khoj-logo-sideways-500.png" width="200" alt="Khoj Logo"></p>
<div align="center">
[![test](https://github.com/khoj-ai/khoj/actions/workflows/test.yml/badge.svg)](https://github.com/khoj-ai/khoj/actions/workflows/test.yml)
[![dockerize](https://github.com/khoj-ai/khoj/actions/workflows/dockerize.yml/badge.svg)](https://github.com/khoj-ai/khoj/pkgs/container/khoj)
[![pypi](https://github.com/khoj-ai/khoj/actions/workflows/pypi.yml/badge.svg)](https://pypi.org/project/khoj-assistant/)
</div>
<div align="center">
<b>An AI copilot for your Second Brain</b>
</div>
<div align="center">
[📜 Explore Code](https://github.com/khoj-ai/khoj)
<span>&nbsp;&nbsp;•&nbsp;&nbsp;</span>
[🌍 Try Khoj Cloud](https://khoj.dev)
<span>&nbsp;&nbsp;•&nbsp;&nbsp;</span>
[💬 Get Involved](https://discord.gg/BDgyabRM6e)
</div>
## Introduction
Welcome to the Khoj Docs! This is the best place to get setup and explore Khoj's features.
- Khoj is an open source, personal AI
- You can [chat](chat.md) with it about anything. When relevant, it'll use any notes or documents you shared with it to respond
- Quickly [find](search.md) relevant notes and documents using natural language
- It understands pdf, plaintext, markdown, org-mode files, [notion pages](notion_integration.md) and [github repositories](github_integration.md)
- Access it from your [Emacs](emacs.md), [Obsidian](obsidian.md), [Web browser](web.md) or the [Khoj Desktop app](desktop.md)
- You can self-host Khoj on your consumer hardware or share it with your family, friends or team from your private cloud
## Quickstart
- [Try Khoj Cloud](https://app.khoj.dev) to get started quickly
- [Read these instructions](./setup.md) to self-host a private instance of Khoj
## Overview
<img src="https://docs.khoj.dev/assets/khoj_search_on_web.png" width="400px">
<span>&nbsp;&nbsp;</span>
<img src="https://docs.khoj.dev/assets/khoj_chat_on_web.png" width="400px">
#### [Search](search.md)
- **Natural**: Use natural language queries to quickly find relevant notes and documents.
- **Incremental**: Incremental search for a fast, search-as-you-type experience
#### [Chat](chat.md)
- **Faster answers**: Find answers faster, smoother than search. No need to manually scan through your notes to find answers.
- **Iterative discovery**: Iteratively explore and (re-)discover your notes
- **Assisted creativity**: Smoothly weave across answers retrieval and content generation
- **Online or Offline**: Choose online or offline chat depending on your requirements

View File

@@ -1,14 +0,0 @@
<!-- _coverpage.md -->
![logo](./assets/khoj-logo-sideways-200.png)
> An open source, AI personal assistant for your notes
- Lightning fast search
- Multi-turn chat
- Keeps you in control of your data
[GitHub](https://github.com/khoj-ai/khoj)
[Get Started](#khoj)
![color](#f9f5de)

View File

@@ -1,23 +0,0 @@
- Get Started
- [Overview](README.md)
- [Self-Host](setup.md)
- [Demos](demos.md)
- Use
- [Features](features.md)
- [Chat](chat.md)
- [Search](search.md)
- Clients
- [Desktop](desktop.md)
- [Obsidian](obsidian.md)
- [Emacs](emacs.md)
- [Web](web.md)
- Online Data Sources
- [Github](github_integration.md)
- [Notion](notion_integration.md)
- Contributing
- [Development](development.md)
- Miscellaneous
- [Telemetry](telemetry.md)
- [Advanced](advanced.md)
- [Performance](performance.md)
- [Credits](credits.md)

View File

@@ -1,32 +0,0 @@
# Installing the Desktop Application [Deprecated -- for 0.11.4 and below]
We have beta desktop images available for download with new releases. This is recommended if you don't want to bother with the command line. Download the latest release from [here](https://github.com/khoj-ai/khoj/releases). You can find the latest release under the `Assets` section.
## MacOS
1. Download the latest release from [here](https://github.com/khoj-ai/khoj/releases).
- If your Mac uses one of the Silicon chips, then download the `Khoj_<version>_arm64.dmg` file. Otherwise, download the `Khoj_<version>_amd64.dmg` file.
2. Open the downloaded file and drag the Khoj app to your Applications folder.
## Windows
Make sure you meet the prerequisites for Windows installation. You can find them [here](windows_install.md#prerequisites).
1. Download the latest release from [here](https://github.com/khoj-ai/khoj/releases). You'll want the `khoj_<version>_amd64.exe` file.
2. Open the downloaded file and double click to install.
## Linux
For the Linux installation, you have to have `glibc` version 2.35 or higher. You can check your version with `ldd --version`.
1. Download the latest release from [here](https://github.com/khoj-ai/khoj/releases). You'll want the `khoj_<version>_amd64.deb` file.
2. In your downloads folder, run `sudo dpkg -i khoj_<version>_amd64.deb` to install Khoj.
# Uninstall
If you decide you want to uninstall the application, you can uninstall it like any other application on your system. For example, on MacOS, you can drag the application to the trash. On Windows, you can uninstall it from the `Add or Remove Programs` menu. On Linux, you can uninstall it with `sudo apt remove khoj`.
In addition to that, you might want to `rm -rf` the following directories:
- `~/.khoj`
- `~/.cache/gpt4all`

View File

@@ -1,34 +0,0 @@
## Features
#### [Search](search.md)
- **Local**: Your personal data stays local. All search and indexing is done on your machine.
- **Incremental**: Incremental search for a fast, search-as-you-type experience
#### [Chat](chat.md)
- **Faster answers**: Find answers faster, smoother than search. No need to manually scan through your notes to find answers.
- **Iterative discovery**: Iteratively explore and (re-)discover your notes
- **Assisted creativity**: Smoothly weave across answers retrieval and content generation
#### General
- **Natural**: Advanced natural language understanding using Transformer based ML Models
- **Pluggable**: Modular architecture makes it easy to plug in new data sources, frontends and ML models
- **Multiple Sources**: Index your Org-mode and Markdown notes, PDF files, Github repositories, and Photos
- **Multiple Interfaces**: Interact from your [Web Browser](./web.md), [Emacs](./emacs.md) or [Obsidian](./obsidian.md)
### Supported Interfaces
[![Khoj on Emacs](https://img.shields.io/badge/Emacs-%237F5AB6.svg?&style=for-the-badge&logo=gnu-emacs&logoColor=white)](./emacs.md)
<span>&nbsp;</span>
[![Khoj on Obsidian](https://img.shields.io/badge/Obsidian-%23483699.svg?style=for-the-badge&logo=obsidian&logoColor=white)](./obsidian.md)
### Supported Data Sources
- markdown*
- org-mode*
- pdf*
- images*
- [github](./github_integration.md)
- [notion](./notion_integration.md)
\* These data sources are offline only.
If you're using Github or Notion, you can get on a waitlist for [Khoj Cloud](https://khoj.dev).

View File

@@ -1,47 +0,0 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<title>Document</title>
<meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1" />
<meta name="description" content="Description">
<!-- Open Graph metadata -->
<meta property="og:title" content="Khoj Documentation">
<meta property="og:type" content="website">
<meta property="og:site_name" content="Khoj Documentation">
<meta property="og:description" content="Quickly get started with using or self-hosting Khoj">
<meta property="og:image" content="https://khoj-web-bucket.s3.amazonaws.com/link_preview_docs.png">
<meta property="og:url" content="https://docs.khoj.dev">
<meta name="viewport" content="width=device-width, initial-scale=1.0, minimum-scale=1.0">
<link rel="stylesheet" href="//cdn.jsdelivr.net/npm/docsify/lib/themes/buble.css" />
<link rel="icon" href="./assets/favicon-128x128.ico">
</head>
<body>
<div id="app"></div>
<script>
window.$docsify = {
name: 'Khoj',
repo: 'https://github.com/khoj-ai/khoj',
loadSidebar: true,
themeColor: '#c2a600',
auto2top: true,
// coverpage: true,
}
</script>
<!-- Docsify v4 -->
<script src="//cdn.jsdelivr.net/npm/docsify@4"></script>
<script src="//cdn.jsdelivr.net/npm/docsify-tabs@1"></script>
<script src="//cdn.jsdelivr.net/npm/docsify/lib/plugins/search.min.js"></script>
<script src="//cdn.jsdelivr.net/npm/docsify-copy-code/dist/docsify-copy-code.min.js"></script>
<script src="//cdn.jsdelivr.net/npm/prismjs@1/components/prism-bash.min.js"></script>
<script src="//cdn.jsdelivr.net/npm/prismjs@1/components/prism-diff.min.js"></script>
<script defer data-domain="khoj.dev" src="https://plausible.io/js/script.js"></script>
</body>
<style>
video {
max-width: 800px;
}
</style>
</html>

View File

@@ -1,23 +0,0 @@
# Windows Installation
These steps can be used to setup Khoj on a clean, new Windows 11 machine. It has been tested on a Windows VM
## Prerequisites
1. Ensure you have Visual Studio C++ Build tools installed. You can download it [from Microsoft here](https://visualstudio.microsoft.com/visual-cpp-build-tools/). At the minimum, you should have the following configuration:
<img width="1152" alt="Screenshot 2023-07-12 at 3 56 25 PM" src="https://github.com/khoj-ai/khoj/assets/65192171/b506a858-2f5e-4c85-946b-5422d83f112a">
2. Ensure you have Python installed. You can check by running `python --version`. If you don't, install the latest version [from here](https://www.python.org/downloads/).
- Ensure you have pip installed: `py -m ensurepip --upgrade`.
## Quick start
1. Open a PowerShell terminal.
2. Run `pip install khoj-assistant`
3. Start Khoj with `khoj`
## Installation in a Virtual Environment
Use this if you want to install with a virtual environment. This will make it much easier to manage your dependencies. You can read more about [virtual environments](https://packaging.python.org/en/latest/guides/installing-using-pip-and-virtual-environments/) here.
1. Open a PowerShell terminal with the `Run as Administrator` privileges.
2. Create a virtual environment: `mkdir khoj && cd khoj && py -m venv .venv`
3. Activate the virtual environment: `.\.venv\Scripts\activate`. If you get a permissions error, then run `Set-ExecutionPolicy -ExecutionPolicy RemoteSigned`.
4. Run `pip install khoj-assistant`
5. Start Khoj with `khoj`

20
documentation/.gitignore vendored Normal file
View File

@@ -0,0 +1,20 @@
# Dependencies
/node_modules
# Production
/build
# Generated files
.docusaurus
.cache-loader
# Misc
.DS_Store
.env.local
.env.development.local
.env.test.local
.env.production.local
npm-debug.log*
yarn-debug.log*
yarn-error.log*

41
documentation/README.md Normal file
View File

@@ -0,0 +1,41 @@
# Website
This website is built using [Docusaurus](https://docusaurus.io/), a modern static website generator.
### Installation
```
$ yarn
```
### Local Development
```
$ yarn start
```
This command starts a local development server and opens up a browser window. Most changes are reflected live without having to restart the server.
### Build
```
$ yarn build
```
This command generates static content into the `build` directory and can be served using any static contents hosting service.
### Deployment
Using SSH:
```
$ USE_SSH=true yarn deploy
```
Not using SSH:
```
$ GIT_USER=<Your GitHub username> yarn deploy
```
If you are using GitHub pages for hosting, this command is a convenient way to build the website and push to the `gh-pages` branch.

View File

Before

Width:  |  Height:  |  Size: 200 KiB

After

Width:  |  Height:  |  Size: 200 KiB

View File

Before

Width:  |  Height:  |  Size: 13 KiB

After

Width:  |  Height:  |  Size: 13 KiB

View File

Before

Width:  |  Height:  |  Size: 36 KiB

After

Width:  |  Height:  |  Size: 36 KiB

View File

Before

Width:  |  Height:  |  Size: 1.2 MiB

After

Width:  |  Height:  |  Size: 1.2 MiB

View File

Before

Width:  |  Height:  |  Size: 350 KiB

After

Width:  |  Height:  |  Size: 350 KiB

View File

Before

Width:  |  Height:  |  Size: 298 KiB

After

Width:  |  Height:  |  Size: 298 KiB

View File

Before

Width:  |  Height:  |  Size: 302 KiB

After

Width:  |  Height:  |  Size: 302 KiB

View File

Before

Width:  |  Height:  |  Size: 394 KiB

After

Width:  |  Height:  |  Size: 394 KiB

View File

Before

Width:  |  Height:  |  Size: 358 KiB

After

Width:  |  Height:  |  Size: 358 KiB

File diff suppressed because one or more lines are too long

After

Width:  |  Height:  |  Size: 27 KiB

View File

Before

Width:  |  Height:  |  Size: 544 KiB

After

Width:  |  Height:  |  Size: 544 KiB

File diff suppressed because one or more lines are too long

After

Width:  |  Height:  |  Size: 43 KiB

View File

Before

Width:  |  Height:  |  Size: 49 KiB

After

Width:  |  Height:  |  Size: 49 KiB

View File

Before

Width:  |  Height:  |  Size: 333 KiB

After

Width:  |  Height:  |  Size: 333 KiB

View File

Before

Width:  |  Height:  |  Size: 445 KiB

After

Width:  |  Height:  |  Size: 445 KiB

View File

Before

Width:  |  Height:  |  Size: 333 KiB

After

Width:  |  Height:  |  Size: 333 KiB

View File

Before

Width:  |  Height:  |  Size: 420 KiB

After

Width:  |  Height:  |  Size: 420 KiB

View File

Before

Width:  |  Height:  |  Size: 478 KiB

After

Width:  |  Height:  |  Size: 478 KiB

View File

Before

Width:  |  Height:  |  Size: 268 KiB

After

Width:  |  Height:  |  Size: 268 KiB

File diff suppressed because one or more lines are too long

After

Width:  |  Height:  |  Size: 6.3 KiB

View File

@@ -0,0 +1,3 @@
module.exports = {
presets: [require.resolve('@docusaurus/core/lib/babel/preset')],
};

View File

@@ -0,0 +1,8 @@
{
"label": "Clients",
"position": 4,
"link": {
"type": "generated-index",
"description": "Different ways for indexing data with the Khoj backend"
}
}

View File

@@ -1,6 +1,14 @@
<h1><img src="./assets/khoj-logo-sideways-500.png" width="200" alt="Khoj Logo"> Desktop</h1>
---
sidebar_position: 1
---
> An AI copilot for your Second Brain
# Desktop
> Query your Second Brain from your machine
Use the Desktop app to chat and search with Khoj.
You can also sync any relevant files with Khoj using the app.
Khoj will use these files to provide contextual reponses when you search or chat.
## Features
- **Chat**
@@ -19,5 +27,6 @@
4. [Optional] Add any files, folders you'd like Khoj to be aware of on the *Settings* page and Click *Save*
## Interface
![](./assets/khoj_chat_on_desktop.png ':size=600px')
![](./assets/khoj_search_on_desktop.png ':size=600px')
| Chat | Search |
|:----:|:------:|
| ![](/img/khoj_chat_on_desktop.png) | ![](/img/khoj_search_on_desktop.png) |

View File

@@ -1,13 +1,18 @@
<h1><img src="./assets/khoj-logo-sideways-500.png" width="200" alt="Khoj Logo"> Emacs</h1>
---
sidebar_position: 2
---
> An AI copilot for your Second Brain in Emacs
# Emacs
<img src="https://stable.melpa.org/packages/khoj-badge.svg" width="150" alt="Melpa Stable Badge">
<img src="https://melpa.org/packages/khoj-badge.svg" width="150" alt="Melpa Badge">
<img src="https://stable.melpa.org/packages/khoj-badge.svg" width="130" alt="Melpa Stable Badge" />
<img src="https://melpa.org/packages/khoj-badge.svg" width="150" alt="Melpa Badge" />
<img src="https://github.com/khoj-ai/khoj/actions/workflows/build_khoj_el.yml/badge.svg" width="150" alt="Build Badge">
<img src="https://github.com/khoj-ai/khoj/actions/workflows/test_khoj_el.yml/badge.svg" width="150" alt="Test Badge">
<img src="https://github.com/khoj-ai/khoj/actions/workflows/build_khoj_el.yml/badge.svg" width="150" alt="Build Badge" />
<img src="https://github.com/khoj-ai/khoj/actions/workflows/test_khoj_el.yml/badge.svg" width="150" alt="Test Badge" />
<br />
<br />
> Query your Second Brain from Emacs
## Features
- **Chat**
@@ -19,19 +24,16 @@
- **Incremental**: Incremental search for a fast, search-as-you-type experience
## Interface
#### Search
![khoj search on emacs](./assets/khoj_search_on_emacs.png ':size=400px')
#### Chat
![khoj chat on emacs](./assets/khoj_chat_on_emacs.png ':size=400px')
| Search | Chat |
|:------:|:----:|
| ![khoj search on emacs](/img/khoj_search_on_emacs.png) | ![khoj chat on emacs](/img/khoj_chat_on_emacs.png) |
## Setup
1. Generate an API key on the [Khoj Web App](https://app.khoj.dev/config#clients)
2. Add below snippet to your Emacs config file, usually at `~/.emacs.d/init.el`
<!-- tabs:start -->
#### **Direct Install**
*Khoj will index your org-agenda files, by default*
@@ -83,16 +85,15 @@ M-x package-install khoj
khoj-org-files '("~/docs/todo.org" "~/docs/work.org")))
```
<!-- tabs:end -->
## Use
### Search
See [Khoj Search](search.md) for details
See [Khoj Search](/features/search) for details
1. Hit `C-c s s` (or `M-x khoj RET s`) to open khoj search
2. Enter your query in natural language<br/>
E.g *"What is the meaning of life?"*, *"My life goals for 2023"*
### Chat
See [Khoj Chat](chat.md) for details
See [Khoj Chat](/features/chat) for details
1. Hit `C-c s c` (or `M-x khoj RET c`) to open khoj chat
2. Ask questions in a natural, conversational style<br/>
E.g *"When did I file my taxes last year?"*
@@ -113,7 +114,7 @@ This feature finds entries similar to the one you are currently on.
- Note: If you have [speed keys](https://orgmode.org/manual/Speed-Keys.html) enabled, `o 2` will also work
### Khoj Menu
![](./assets/khoj_emacs_menu.png)
![](/img/khoj_emacs_menu.png)
Hit `C-c s` (or `M-x khoj`) to open the khoj menu above. Then:
- Hit `t` until you preferred content type is selected in the khoj menu
`Content Type` specifies the content to perform `Search`, `Update` or `Find Similar` actions on

View File

@@ -1,6 +1,10 @@
<h1><img src="./assets/khoj-logo-sideways-500.png" width="200" alt="Khoj Logo"> Obsidian</h1>
---
sidebar_position: 3
---
> An AI copilot for your Second Brain in Obsidian
# Obsidian
> Query your Second Brain from Obsidian
## Features
- **Chat**
@@ -12,8 +16,10 @@
- **Incremental**: Incremental search for a fast, search-as-you-type experience
## Interface
![](./assets/khoj_search_on_obsidian.png ':size=400px')
![](./assets/khoj_chat_on_obsidian.png ':size=400px')
| Search | Chat |
|:------:|:----:|
| ![](/img/khoj_search_on_obsidian.png) | ![](/img/khoj_chat_on_obsidian.png) |
## Setup
@@ -30,7 +36,7 @@ See the official [Obsidian Plugin Docs](https://help.obsidian.md/Extending+Obsid
Run *Khoj: Chat* from the [Command Palette](https://help.obsidian.md/Plugins/Command+palette) and ask questions in a natural, conversational style.<br />
E.g *"When did I file my taxes last year?"*
See [Khoj Chat](/chat) for more details
See [Khoj Chat](/features/chat) for more details
### Find Similar Notes
To see other notes similar to the current one, run *Khoj: Find Similar Notes* from the [Command Palette](https://help.obsidian.md/Plugins/Command+palette)
@@ -38,7 +44,7 @@ To see other notes similar to the current one, run *Khoj: Find Similar Notes* fr
### Search
Click the *Khoj search* icon 🔎 on the [Ribbon](https://help.obsidian.md/User+interface/Workspace/Ribbon) or run *Khoj: Search* from the [Command Palette](https://help.obsidian.md/Plugins/Command+palette)
See [Khoj Search](/search) for more details. Use [query filters](/advanced#query-filters) to limit entries to search
See [Khoj Search](/features/search) for more details. Use [query filters](/miscellaneous/advanced#query-filters) to limit entries to search
[search_demo](https://user-images.githubusercontent.com/6413477/218801155-cd67e8b4-a770-404a-8179-d6b61caa0f93.mp4 ':include :type=mp4')

View File

@@ -1,6 +1,12 @@
<h1><img src="./assets/khoj-logo-sideways-500.png" width="200" alt="Khoj Logo"> Web</h1>
---
sidebar_position: 4
---
> An AI copilot for your Second Brain
# Web
> Query your Second Brain from your Web Browser
Without any desktop clients, you can start chatting with Khoj on the web. Bear in mind you do need one of the desktop clients in order to share and sync your data with Khoj.
## Features
- **Chat**
@@ -15,5 +21,7 @@
No setup required. The Khoj web app is the default interface to Khoj. You can access it from any web browser. Try it on [Khoj Cloud](https://app.khoj.dev)
## Interface
![](./assets/khoj_search_on_web.png ':size=400px')
![](./assets/khoj_chat_on_web.png ':size=400px')
| Search | Chat |
|:------:|:----:|
| ![](/img/khoj_search_on_web.png) | ![](/img/khoj_chat_on_web.png) |

View File

@@ -0,0 +1,8 @@
{
"label": "Contributing",
"position": 2,
"link": {
"type": "generated-index",
"description": "Development Setup"
}
}

View File

@@ -1,23 +1,29 @@
---
sidebar_position: 0
---
# Development
Welcome to the development docs of Khoj! Thanks for you interesting in being a contributor ❤️. Open source contributors are a corner-store of the Khoj community. We welcome all contributions, big or small.
To get started with contributing, check out the official GitHub docs on [contributing to an open-source project](https://docs.github.com/en/get-started/exploring-projects-on-github/contributing-to-a-project).
Join the [Discord](https://discord.gg/WaxF3SkFPU) server and pick up click the ✅ for the question "Are you interested in becoming a contributor?" in the `#welcome-and-rules` channel. This will give you access to the `#contributors` channel where you can ask questions and get help from other contributors.
Join the [Discord](https://discord.gg/WaxF3SkFPU) server and click the ✅ for the question "Are you interested in becoming a contributor?" in the `#welcome-and-rules` channel. This will give you access to the `#contributors` channel where you can ask questions and get help from other contributors.
If you're looking for a place to get started, check out the list of [Github Issues](https://github.com/khoj-ai/khoj/issues) with the tag `good first issue` to find issues that are good for first-time contributors.
## Local Server Installation
### Using Pip
#### 1. Install
```mdx-code-block
import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';
```
<!-- tabs:start -->
#### **MacOS**
```shell
```mdx-code-block
<Tabs>
<TabItem value="macos" label="MacOS">
```shell
# Get Khoj Code
git clone https://github.com/khoj-ai/khoj && cd khoj
@@ -26,11 +32,10 @@ python3 -m venv .venv && source .venv/bin/activate
# For MacOS or zsh users run this
pip install -e '.[dev]'
```
#### **Windows**
```shell
```
</TabItem>
<TabItem value="win" label="Windows">
```shell
# Get Khoj Code
git clone https://github.com/khoj-ai/khoj && cd khoj
@@ -39,13 +44,11 @@ python3 -m venv .venv && .venv\Scripts\activate
# Install Khoj for Development
pip install -e .[dev]
```
#### **Linux**
```shell
# Get Khoj Code
```
</TabItem>
<TabItem value="unix" label="Linux">
```shell
# Get Khoj Code
git clone https://github.com/khoj-ai/khoj && cd khoj
# Create, Activate Virtual Environment
@@ -53,15 +56,15 @@ python3 -m venv .venv && source .venv/bin/activate
# Install Khoj for Development
pip install -e .[dev]
```
</TabItem>
</Tabs>
```
<!-- tabs:end -->
#### 2. Run
1. Start Khoj
```shell
```bash
khoj -vv
```
2. Configure Khoj
@@ -115,7 +118,9 @@ In whichever clients you're using for testing, you'll need to update the server
### Before Creating PR
!> **Note**: You should be in an active virtual environment for Khoj in order to run the unit tests and linter.
:::tip[Note]
You should be in an active virtual environment for Khoj in order to run the unit tests and linter.
:::
1. Ensure that you have a [Github Issue](https://github.com/khoj-ai/khoj/issues) that can be linked to the PR. If not, create one. Make sure you've tagged one of the maintainers to the issue. This will ensure that the maintainers are notified of the PR and can review it. It's best discuss the code design on an existing issue or Discord thread before creating a PR. This helps get your PR merged faster.
1. Run unit tests.
@@ -129,7 +134,7 @@ In whichever clients you're using for testing, you'll need to update the server
4. Think about how to add unit tests to verify the functionality you're adding in the PR. If you're not sure how to do this, ask for help in the Github issue or on Discord's `#contributors` channel.
### After Creating PR
1. Automated [validation workflows](.github/workflows) should run for every PR. Tag one of the maintainers in the PR to trigger it.
1. Automated [validation workflows](https://github.com/khoj-ai/khoj/tree/master/.github/workflows) should run for every PR. Tag one of the maintainers in the PR to trigger it.
## Obsidian Plugin Development
### Plugin development setup
@@ -163,14 +168,14 @@ Follow the steps below to [release](https://github.com/debanjum/khoj/releases/)
## Architecture
![](./assets/khoj_architecture.png)
![](/img/khoj_architecture.png)
## Visualize Codebase
*[Interactive Visualization](https://mango-dune-07a8b7110.1.azurestaticapps.net/?repo=debanjum%2Fkhoj)*
![](./assets/khoj_codebase_visualization_0.2.1.png)
![](/img/khoj_codebase_visualization_0.2.1.png)
## Visualize Khoj Obsidian Plugin Codebase
![](./assets/khoj_obsidian_codebase_visualization_0.2.1.png)
![](/img/khoj_obsidian_codebase_visualization_0.2.1.png)

View File

@@ -0,0 +1,8 @@
{
"label": "Features",
"position": 3,
"link": {
"type": "generated-index",
"description": "Features supported by Khoj"
}
}

View File

@@ -0,0 +1,34 @@
---
sidebar_position: 1
---
# Features
Khoj supports a variety of features, including search and chat with a wide range of data sources and interfaces.
#### [Search](/features/search)
- **Local**: Your personal data stays local. All search and indexing is done on your machine when you [self-host](/get-started/setup)
- **Incremental**: Incremental search for a fast, search-as-you-type experience
#### [Chat](/features/chat)
- **Faster answers**: Find answers faster, smoother than search. No need to manually scan through your notes to find answers.
- **Iterative discovery**: Iteratively explore and (re-)discover your notes
- **Assisted creativity**: Smoothly weave across answers retrieval and content generation
- **Works online or offline**: Chat using online or offline AI chat models
#### General
- **Cloud or Self-Host**: Use [cloud](https://app.khoj.dev/login) to use Khoj anytime from anywhere or [self-host](/get-started/setup) for privacy
- **Natural**: Advanced natural language understanding using Transformer based ML Models
- **Pluggable**: Modular architecture makes it easy to plug in new data sources, frontends and ML models
- **Multiple Sources**: Index your Org-mode, Markdown, PDF, plaintext files, Github repos and Notion pages
- **Multiple Interfaces**: Interact from your Web Browser, Emacs, Obsidian, Desktop app or even Whatsapp
### Supported Interfaces
Khoj is available as a [Desktop app](/clients/desktop), [Emacs package](/clients/emacs), [Obsidian plugin](/clients/obsidian), [Web app](/clients/web) and a [Whatsapp AI](https://khoj.dev/whatsapp).
![](/img/khoj_clients.svg ':size=400px')
### Supported Data Sources
Khoj can understand your org-mode, markdown, PDF, plaintext files, [Github projects](/online-data-sources/github_integration) and [Notion pages](/online-data-sources/notion_integration).
![](/img/khoj_datasources.svg ':size=200px')

View File

@@ -1,4 +1,11 @@
## Khoj Chat
---
sidebar_position: 2
---
# Chat
You can configure Khoj to chat with you about anything. When relevant, it'll use any notes or documents you shared with it to respond.
### Overview
- Creates a personal assistant for you to inquire and engage with your notes
- You can choose to use Online or Offline Chat depending on your requirements
@@ -18,12 +25,17 @@ Offline chat stays completely private and works without internet using open-sour
1. Open your [Khoj offline settings](http://localhost:42110/server/admin/database/offlinechatprocessorconversationconfig/) and click *Enable* on the Offline Chat configuration.
2. Open your [Chat model options](http://localhost:42110/server/admin/database/chatmodeloptions/) and add a new option for the offline chat model you want to use. Make sure to use `Offline` as its type. We currently only support offline models that use the [Llama chat prompt](https://replicate.com/blog/how-to-prompt-llama#wrap-user-input-with-inst-inst-tags) format. We recommend using `mistral-7b-instruct-v0.1.Q4_0.gguf`.
!> **Note**: Offline chat is not supported for a multi-user scenario. The host machine will encounter segmentation faults if multiple users try to use offline chat at the same time.
:::tip[Note]
Offline chat is not supported for a multi-user scenario. The host machine will encounter segmentation faults if multiple users try to use offline chat at the same time.
:::
#### Online Chat
Online chat requires internet to use ChatGPT but is faster, higher quality and less compute intensive.
!> **Warning**: This will enable Khoj to send your chat queries and query relevant notes to OpenAI for processing
:::danger[Warning]
This will enable Khoj to send your chat queries and query relevant notes to OpenAI for processing.
:::
1. Get your [OpenAI API Key](https://platform.openai.com/account/api-keys)
2. Open your [Khoj Online Chat settings](http://localhost:42110/server/admin/database/openaiprocessorconversationconfig/). Add a new setting with your OpenAI API key, and click *Save*. Only one configuration will be used, so make sure that's the only one you have.
@@ -34,9 +46,9 @@ Online chat requires internet to use ChatGPT but is faster, higher quality and l
- **On Web**: Open [/chat](https://app.khoj.dev/chat) in your web browser
- **On Obsidian**: Search for *Khoj: Chat* in the [Command Palette](https://help.obsidian.md/Plugins/Command+palette)
- **On Emacs**: Run `M-x khoj <user-query>`
2. Enter your queries to chat with Khoj. Use [slash commands](#commands) and [query filters](./advanced.md#query-filters) to change what Khoj uses to respond
2. Enter your queries to chat with Khoj. Use [slash commands](#commands) and [query filters](/miscellaneous/advanced#query-filters) to change what Khoj uses to respond
![](./assets/khoj_chat_on_web.png ':size=400px')
![](/img/khoj_chat_on_web.png ':size=400px')
#### Details
1. Your query is used to retrieve the most relevant notes, if any, using Khoj search
@@ -47,4 +59,6 @@ Slash commands allows you to change what Khoj uses to respond to your query
- **/notes**: Limit chat to only respond using your notes, not just Khoj's general world knowledge as reference
- **/general**: Limit chat to only respond using Khoj's general world knowledge, not using your notes as reference
- **/default**: Allow chat to respond using your notes or it's general knowledge as reference. It's the default behavior when no slash command is used
- **/online**: Use online information and incorporate it in the prompt to the LLM to send you a response.
- **/image**: Generate an image in response to your query.
- **/help**: Use /help to get all available commands and general information about Khoj

View File

@@ -1,10 +1,17 @@
## Khoj Search
---
sidebar_position: 3
---
# Search
Take advantage of super fast search to find relevant notes and documents from your Second Brain.
### Use
1. Open Khoj Search
- **On Web**: Open <https://app.khoj.dev/> in your web browser
- **On Web**: Open https://app.khoj.dev/ in your web browser
- **On Obsidian**: Click the *Khoj search* icon 🔎 on the [Ribbon](https://help.obsidian.md/User+interface/Workspace/Ribbon) or Search for *Khoj: Search* in the [Command Palette](https://help.obsidian.md/Plugins/Command+palette)
- **On Emacs**: Run `M-x khoj <user-query>`
2. Query using natural language to find relevant entries from your knowledge base. Use [query filters](./advanced.md#query-filters) to limit entries to search
2. Query using natural language to find relevant entries from your knowledge base. Use [query filters](/miscellaneous/advanced#query-filters) to limit entries to search
### Demo
![](./assets/khoj_search_on_web.png ':size=400px')
![](/img/khoj_search_on_web.png ':size=400px')

View File

@@ -0,0 +1,8 @@
{
"label": "Get Started",
"position": 1,
"link": {
"type": "generated-index",
"description": "Learn how to get started with using Khoj"
}
}

View File

@@ -1,22 +1,22 @@
## Demos
---
sidebar_position: 2
---
# Demos
Check out a couple of demos and screenshots of Khoj in action.
### Screenshots
#### Web
![](./assets/khoj_search_on_web.png ':size=300px')
![](./assets/khoj_chat_on_web.png ':size=300px')
#### Obsidian
![](./assets/khoj_search_on_obsidian.png ':size=300px')
![](./assets/khoj_chat_on_obsidian.png ':size=300px')
#### Emacs
![](./assets/khoj_search_on_emacs.png ':size=300px')
![](./assets/khoj_chat_on_emacs.png ':size=400px')
| Web | Obsidian | Emacs |
|:---:|:--------:|:-----:|
| ![](/img/khoj_search_on_web.png ':size=300px') | ![](/img/khoj_search_on_obsidian.png ':size=300px') | ![](/img/khoj_search_on_emacs.png ':size=300px') |
| ![](/img/khoj_chat_on_web.png ':size=300px') | ![](/img/khoj_chat_on_obsidian.png ':size=300px') | ![](/img/khoj_chat_on_emacs.png ':size=400px') |
### Videos
#### Khoj in Obsidian
[KhojObsidian](https://github-production-user-asset-6210df.s3.amazonaws.com/6413477/240061700-3e33d8ea-25bb-46c8-a3bf-c92f78d0f56b.mp4 ':include :type=mp4')
[Link to Video](https://github-production-user-asset-6210df.s3.amazonaws.com/6413477/240061700-3e33d8ea-25bb-46c8-a3bf-c92f78d0f56b.mp4)
##### Installation
@@ -33,7 +33,7 @@
- Jump to the [search result](https://marcus.se.net/obsidian-plugin-docs/publishing/submit-your-plugin)
#### Khoj in Emacs, Browser
[KhojEmacs](https://user-images.githubusercontent.com/6413477/184735169-92c78bf1-d827-4663-9087-a1ea194b8f4b.mp4 ':include :type=mp4')
[Link to Video](https://user-images.githubusercontent.com/6413477/184735169-92c78bf1-d827-4663-9087-a1ea194b8f4b.mp4)
##### Installation

View File

@@ -0,0 +1,52 @@
---
sidebar_position: 0
slug: /
---
# Overview
<p align="center"><img src="/img/khoj-logo-sideways-500.png" width="200" alt="Khoj Logo"></img></p>
<div align="center">
<b>An AI copilot for your Second Brain</b>
</div>
<br />
<div align="center">
[📜 Explore Code](https://github.com/khoj-ai/khoj)
<span>&nbsp;&nbsp;•&nbsp;&nbsp;</span>
[🌍 Try Khoj Cloud](https://khoj.dev)
<span>&nbsp;&nbsp;•&nbsp;&nbsp;</span>
[💬 Get Involved](https://discord.gg/BDgyabRM6e)
</div>
## Introduction
Welcome to the Khoj Docs! This is the best place to get setup and explore Khoj's features.
- Khoj is an open source, personal AI
- You can [chat](/features/chat) with it about anything. It'll use files you shared with it to respond, when relevant
- Quickly [find](/features/search) relevant notes and documents using natural language
- It understands pdf, plaintext, markdown, org-mode files, [notion pages](/online-data-sources/notion_integration) and [github repositories](/online-data-sources/github_integration)
- Access it from your [Emacs](/clients/emacs), [Obsidian](/clients/obsidian), [Web browser](/clients/web) or the [Khoj Desktop app](/clients/desktop)
- Use [cloud](https://app.khoj.dev/login) to access your Khoj anytime from anywhere, [self-host](/get-started/setup) on consumer hardware for privacy
## Quickstart
- [Try Khoj Cloud](https://app.khoj.dev) to get started quickly
- [Read these instructions](/get-started/setup) to self-host a private instance of Khoj
## At a Glance
<img src="https://docs.khoj.dev/img/khoj_search_on_web.png" width="400px" />
<span>&nbsp;&nbsp;</span>
<img src="https://docs.khoj.dev/img/khoj_chat_on_web.png" width="400px" />
#### [Search](/features/search)
- **Natural**: Use natural language queries to quickly find relevant notes and documents.
- **Incremental**: Incremental search for a fast, search-as-you-type experience
#### [Chat](/features/chat)
- **Faster answers**: Find answers faster, smoother than search. No need to manually scan through your notes to find answers.
- **Iterative discovery**: Iteratively explore and (re-)discover your notes
- **Assisted creativity**: Smoothly weave across answers retrieval and content generation
- **Online or Offline**: Choose online or offline chat depending on your requirements

View File

@@ -1,10 +1,22 @@
---
sidebar_position: 1
---
# Self-Host
Learn about how to self-host Khoj on your own machine.
```mdx-code-block
import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';
```
## Setup
These are the general setup instructions for Khoj.
- Make sure [python](https://realpython.com/installing-python/) and [pip](https://pip.pypa.io/en/stable/installation/) are installed on your machine
- Check the [Khoj Emacs docs](/emacs?id=setup) to setup Khoj with Emacs<br />
- Check the [Khoj Emacs docs](/clients/emacs#setup) to setup Khoj with Emacs<br />
It's simpler as it can skip the server *install*, *run* and *configure* step below.
- Check the [Khoj Obsidian docs](/obsidian?id=_2-setup-plugin) to setup Khoj with Obsidian<br />
- Check the [Khoj Obsidian docs](/clients/obsidian#setup) to setup Khoj with Obsidian<br />
Its simpler as it can skip the *configure* step below.
For Installation, you can either use Docker or install Khoj locally.
@@ -33,63 +45,49 @@ Khoj should now be running at http://localhost:42110. You can see the web UI in
Khoj uses the `pgvector` package to store embeddings of your index in a Postgres database. In order to use this, you need to have Postgres installed.
<!-- tabs:start -->
#### **MacOS**
```mdx-code-block
<Tabs groupId="operating-systems">
<TabItem value="macos" label="MacOS">
Install [Postgres.app](https://postgresapp.com/). This comes pre-installed with `pgvector` and relevant dependencies.
#### **Windows**
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.
#### **Linux**
From [official instructions](https://wiki.postgresql.org/wiki/Apt)
```bash
sudo apt install -y postgresql-common
sudo /usr/share/postgresql-common/pgdg/apt.postgresql.org.sh
sudo apt install postgres-16 postgresql-16-pgvector
</TabItem>
<TabItem value="win" label="Windows">
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="unix" 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>
```
##### **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. Reproduced instructions below for convenience.
```bash
cd /tmp
git clone --branch v0.5.1 https://github.com/pgvector/pgvector.git
cd pgvector
make
make install # may need sudo
```
<!-- tabs:end -->
##### Create the Khoj database
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.
<!-- tabs:start -->
#### **MacOS**
```bash
```mdx-code-block
<Tabs groupId="operating-systems">
<TabItem value="macos" label="MacOS">
```shell
createdb khoj -U postgres --password
```
#### **Windows**
```bash
```
</TabItem>
<TabItem value="win" label="Windows">
```shell
createdb -U postgres khoj --password
```
#### **Linux**
```bash
```
</TabItem>
<TabItem value="unix" label="Linux">
```shell
sudo -u postgres createdb khoj --password
```
</TabItem>
</Tabs>
```
<!-- tabs:end -->
#### Install package
@@ -98,64 +96,54 @@ sudo -u postgres createdb khoj --password
Run the following command in your terminal to install the Khoj backend.
<!-- tabs:start -->
#### **MacOS**
```shell
```mdx-code-block
<Tabs groupId="operating-systems">
<TabItem value="macos" label="MacOS">
```shell
python -m pip install khoj-assistant
```
#### **Windows**
```shell
py -m pip install khoj-assistant
```
For more detailed Windows installation and troubleshooting, see [Windows Install](./windows_install.md).
#### **Linux**
```shell
```
</TabItem>
<TabItem value="win" label="Windows">
```shell
py -m pip install khoj-assistant
```
</TabItem>
<TabItem value="unix" label="Linux">
```shell
python -m pip install khoj-assistant
```
</TabItem>
</Tabs>
```
<!-- tabs:end -->
##### Local Server Start
Before getting started, configure the following environment variables in your terminal for the first run
<!-- tabs:start -->
#### **MacOS**
```shell
export KHOJ_ADMIN_EMAIL=<your-email>
export KHOJ_ADMIN_PASSWORD=<your-password>
```mdx-code-block
<Tabs groupId="operating-systems">
<TabItem value="macos" label="MacOS">
```shell
export KHOJ_ADMIN_EMAIL=<your-email>
export KHOJ_ADMIN_PASSWORD=<your-password>
```
</TabItem>
<TabItem value="win" label="Windows">
If you're using PowerShell:
```shell
$env:KHOJ_ADMIN_EMAIL="<your-email>"
$env:KHOJ_ADMIN_PASSWORD="<your-password>"
```
</TabItem>
<TabItem value="unix" label="Linux">
```shell
export KHOJ_ADMIN_EMAIL=<your-email>
export KHOJ_ADMIN_PASSWORD=<your-password>
```
</TabItem>
</Tabs>
```
#### **Windows**
If you're using PowerShell:
```shell
$env:KHOJ_ADMIN_EMAIL="<your-email>"
$env:KHOJ_ADMIN_PASSWORD="<your-password>"
```
If you're using a Unix shell:
```shell
export KHOJ_ADMIN_EMAIL="<your-email>"
export KHOJ_ADMIN_PASSWORD="<your-password>"
```
#### **Linux**
```shell
export KHOJ_ADMIN_EMAIL=<your-email>
export KHOJ_ADMIN_PASSWORD=<your-password>
```
<!-- tabs:end -->
Run the following command from your terminal to start the Khoj backend and open Khoj in your browser.
@@ -183,21 +171,24 @@ To use the desktop client, you need to go to your Khoj server's settings page (h
1. Go to http://localhost:42110/server/admin and login with your admin credentials.
1. Go to [OpenAI settings](http://localhost:42110/server/admin/database/openaiprocessorconversationconfig/) in the server admin settings to add an Open AI processor conversation config. This is where you set your API key. Alternatively, you can go to the [offline chat settings](http://localhost:42110/server/admin/database/offlinechatprocessorconversationconfig/) and simply create a new setting with `Enabled` set to `True`.
2. Go to the ChatModelOptions if you want to add additional models for chat. For example, you can specify `gpt-4` if you're using OpenAI or `mistral-7b-instruct-v0.1.Q4_0.gguf` if you're using offline chat. Make sure to configure the `type` field to `OpenAI` or `Offline` respectively.
1. Select files and folders to index [using the desktop client](./setup.md?id=_2-download-the-desktop-client). When you click 'Save', the files will be sent to your server for indexing.
1. Select files and folders to index [using the desktop client](/get-started/setup#2-download-the-desktop-client). When you click 'Save', the files will be sent to your server for indexing.
- Select Notion workspaces and Github repositories to index using the web interface.
> Note: Using Safari on Mac? You might not be able to login to the admin panel. Try using Chrome or Firefox instead.
:::tip[Note]
Using Safari on Mac? You might not be able to login to the admin panel. Try using Chrome or Firefox instead.
:::
### 4. Install Client Plugins (Optional)
Khoj exposes a web interface to search, chat and configure by default.<br />
The optional steps below allow using Khoj from within an existing application like Obsidian or Emacs.
- **Khoj Obsidian**:<br />
[Install](/obsidian?id=_2-setup-plugin) the Khoj Obsidian plugin
[Install](/clients/obsidian#setup) the Khoj Obsidian plugin
- **Khoj Emacs**:<br />
[Install](/emacs?id=setup) khoj.el
[Install](/clients/emacs#setup) khoj.el
#### Setup host URL
To configure your host URL on your clients when self-hosting, use `http://127.0.0.1:42110`. This is the default value for the `KHOJ_HOST` environment variable. Note that `localhost` will not work.
@@ -209,46 +200,62 @@ You can head to http://localhost:42110 to use the web interface. You can also us
## Upgrade
### Upgrade Khoj Server
<!-- tabs:start -->
#### **Local Setup**
```shell
pip install --upgrade khoj-assistant
```mdx-code-block
<Tabs groupId="environment">
<TabItem value="localsetup" label="Local Setup">
```shell
pip install --upgrade khoj-assistant
```
*Note: To upgrade to the latest pre-release version of the khoj server run below command*
</TabItem>
<TabItem value="docker" label="Docker">
From the same directory where you have your `docker-compose` file, this will fetch the latest build and upgrade your server.
```shell
docker-compose up --build
```
</TabItem>
<TabItem value="emacs" label="Emacs">
- Use your Emacs Package Manager to Upgrade
- See [khoj.el package setup](/clients/emacs#setup) for details
</TabItem>
<TabItem value="obsidian" label="Obsidian">
- Upgrade via the Community plugins tab on the settings pane in the Obsidian app
- See the [khoj plugin setup](/clients/obsidian#setup) for details
</TabItem>
</Tabs>
```
*Note: To upgrade to the latest pre-release version of the khoj server run below command*
```shell
# Maps to the latest commit on the master branch
pip install --upgrade --pre khoj-assistant
```
#### **Docker**
From the same directory where you have your `docker-compose` file, this will fetch the latest build and upgrade your server.
```shell
docker-compose up --build
```
<!-- tabs:end -->
### Upgrade Khoj on Emacs
- Use your Emacs Package Manager to Upgrade
- See [khoj.el package setup](/emacs?id=setup) for details
### Upgrade Khoj on Obsidian
- Upgrade via the Community plugins tab on the settings pane in the Obsidian app
- See the [khoj plugin setup](/obsidian.md?id=_2-setup-plugin) for details
## Uninstall
1. (Optional) Hit `Ctrl-C` in the terminal running the khoj server to stop it
2. Delete the khoj directory in your home folder (i.e `~/.khoj` on Linux, Mac or `C:\Users\<your-username>\.khoj` on Windows)
5. You might want to `rm -rf` the following directories:
- `~/.khoj`
- `~/.cache/gpt4all`
3. Uninstall the khoj server with `pip uninstall khoj-assistant`
4. (Optional) Uninstall khoj.el or the khoj obsidian plugin in the standard way on Emacs, Obsidian
### Uninstall Khoj Server
```mdx-code-block
<Tabs groupId="environment">
<TabItem value="localsetup" label="Local Setup">
```shell
# uninstall khoj server
pip uninstall khoj-assistant
# delete khoj postgres db
dropdb khoj -U postgres
```
</TabItem>
<TabItem value="docker" label="Docker">
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.
</TabItem>
</Tabs>
```
## Troubleshoot

View File

@@ -0,0 +1,8 @@
{
"label": "Miscellaneous",
"position": 6,
"link": {
"type": "generated-index",
"description": "Additional resources for learning about Khoj"
}
}

View File

@@ -1,5 +1,8 @@
---
sidebar_position: 3
---
## Advanced Usage
# Advanced Usage
### Search across Different Languages (Self-Hosting)
To search for notes in multiple, different languages, you can use a [multi-lingual model](https://www.sbert.net/docs/pretrained_models.html#multi-lingual-models).<br />

View File

@@ -1,4 +1,9 @@
## Credits
---
sidebar_position: 4
---
# Credits
Many Open Source projects are used to power Khoj. Here's a few of them:
- [Multi-QA MiniLM Model](https://huggingface.co/sentence-transformers/multi-qa-MiniLM-L6-cos-v1), [All MiniLM Model](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) for Text Search. See [SBert Documentation](https://www.sbert.net/examples/applications/retrieve_rerank/README.html)
- [OpenAI CLIP Model](https://github.com/openai/CLIP) for Image Search. See [SBert Documentation](https://www.sbert.net/examples/applications/image-search/README.html)

View File

@@ -1,4 +1,10 @@
## Performance
---
sidebar_position: 2
---
# Performance
Here are some top-level performance metrics for Khoj. These are rough estimates and will vary based on your hardware and data.
### Search performance

View File

@@ -1,4 +1,8 @@
# Telemetry (self-hosting)
---
sidebar_position: 1
---
# Telemetry
We collect some high level, anonymized metadata about usage of Khoj. This includes:
- Client (Web, Emacs, Obsidian)

View File

@@ -0,0 +1,8 @@
{
"label": "Online Data Sources",
"position": 5,
"link": {
"type": "generated-index",
"description": "Online data sources for indexing via Khoj"
}
}

View File

@@ -1,4 +1,4 @@
# 🧑🏾‍💻 Setup the Github integration
# Setup the Github integration
The Github integration allows you to index as many repositories as you want. It's currently default configured to index Issues, Commits, and all Markdown/Org files in each repository. For large repositories, this takes a fairly long time, but it works well for smaller projects.

View File

@@ -1,6 +1,6 @@
## 📜 Notion Integration
# Notion Integration
Khoj now supports search/chat with pages in your Notion workspaces. [Notion](notion.so/) is a platform people use for taking notes, especially for collaboration.
The Notion integration allows you to search/chat with your Notion workspaces. [Notion](https://notion.so/) is a platform people use for taking notes, especially for collaboration.
We haven't setup a fancy integration with OAuth yet, so this integration still requires some effort on your end to generate an API key.

View File

@@ -0,0 +1,187 @@
// @ts-check
// `@type` JSDoc annotations allow editor autocompletion and type checking
// (when paired with `@ts-check`).
// There are various equivalent ways to declare your Docusaurus config.
// See: https://docusaurus.io/docs/api/docusaurus-config
import {themes as prismThemes} from 'prism-react-renderer';
/** @type {import('@docusaurus/types').Config} */
const config = {
title: 'Khoj AI',
tagline: 'An AI copilot for your Second Brain',
staticDirectories: ['assets'],
favicon: 'img/favicon-128x128.ico',
// Set the production url of your site here
url: 'https://docs.khoj.dev',
// Set the /<baseUrl>/ pathname under which your site is served
// For GitHub pages deployment, it is often '/<projectName>/'
baseUrl: '/',
// GitHub pages deployment config.
// If you aren't using GitHub pages, you don't need these.
organizationName: 'khoj-ai', // Usually your GitHub org/user name.
projectName: 'khoj', // Usually your repo name.
onBrokenLinks: 'throw',
onBrokenMarkdownLinks: 'warn',
// Even if you don't use internationalization, you can use this field to set
// useful metadata like html lang. For example, if your site is Chinese, you
// may want to replace "en" with "zh-Hans".
i18n: {
defaultLocale: 'en',
locales: ['en'],
},
presets: [
[
'classic',
/** @type {import('@docusaurus/preset-classic').Options} */
({
docs: {
sidebarPath: './sidebars.js',
routeBasePath: '/',
// Please change this to your repo.
// Remove this to remove the "edit this page" links.
editUrl:
'https://github.com/khoj-ai/khoj/tree/master/documentation/',
},
blog: {
showReadingTime: true,
// Please change this to your repo.
// Remove this to remove the "edit this page" links.
editUrl:
'https://github.com/khoj-ai/khoj/tree/master/documentation/blog/',
},
theme: {
customCss: './src/css/custom.css',
},
}),
],
],
themeConfig:
/** @type {import('@docusaurus/preset-classic').ThemeConfig} */
({
image: 'img/khoj-logo-sideways-500.png',
metadata: [
{name: 'keywords', content: 'khoj, khoj ai, chatgpt, open ai, open source, productivity'},
{name: 'og:title', content: 'Khoj Documentation'},
{name: 'og:type', content: 'website'},
{name: 'og:site_name', content: 'Khoj Documentation'},
{name: 'og:description', content: 'Quickly get started with using or self-hosting Khoj'},
{name: 'og:image', content: 'https://khoj-web-bucket.s3.amazonaws.com/link_preview_docs.png'},
{name: 'og:url', content: 'https://docs.khoj.dev'},
{name: 'keywords', content: 'khoj, khoj ai, chatgpt, open ai, open source, productivity'}
],
navbar: {
title: 'Khoj',
logo: {
alt: 'Khoj AI',
src: 'img/favicon-128x128.ico',
},
items: [
{
href: 'https://github.com/khoj-ai/khoj',
label: '📜 Code',
position: 'right',
},
{
href: 'https://app.khoj.dev/login',
label: '🌍 Cloud',
position: 'right',
},
{
href: 'https://discord.gg/BDgyabRM6e',
label: '💬 Discord',
position: 'right',
},
],
},
footer: {
style: 'dark',
links: [
{
title: 'Docs',
items: [
{
label: 'Get Started',
to: '/',
},
{
label: 'Features',
to: '/features/all_features',
},
{
label: 'Client Apps',
to: '/category/clients',
},
{
label: 'Self-Hosting',
to: '/get-started/setup',
},
{
label: 'Contributing',
to: '/contributing/development',
},
],
},
{
title: 'Community',
items: [
{
label: 'Discord',
href: 'https://discord.gg/BDgyabRM6e',
},
{
label: 'LinkedIn',
href: 'https://www.linkedin.com/company/khoj-ai/'
},
{
label: 'Twitter',
href: 'https://twitter.com/khoj_ai',
},
],
},
{
title: 'More',
items: [
// {
// label: 'Blog',
// to: '/blog',
// },
{
label: 'Cloud',
href: 'https://app.khoj.dev/login',
},
{
label: 'Code',
href: 'https://github.com/khoj-ai/khoj',
},
{
label: 'Website',
href: 'https://khoj.dev',
},
],
},
],
copyright: `Copyright © ${new Date().getFullYear()} Khoj, Inc.`,
},
prism: {
theme: prismThemes.github,
darkTheme: prismThemes.dracula,
},
algolia: {
appId: "NBR0FXJNGW",
apiKey: "8841b34192a28b2d06f04dd28d768017",
indexName: "khoj",
contextualSearch: false,
}
}),
};
export default config;

14629
documentation/package-lock.json generated Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,44 @@
{
"name": "documentation",
"version": "0.0.0",
"private": true,
"scripts": {
"docusaurus": "docusaurus",
"start": "docusaurus start",
"build": "docusaurus build",
"swizzle": "docusaurus swizzle",
"deploy": "docusaurus deploy",
"clear": "docusaurus clear",
"serve": "docusaurus serve",
"write-translations": "docusaurus write-translations",
"write-heading-ids": "docusaurus write-heading-ids"
},
"dependencies": {
"@docusaurus/core": "3.1.0",
"@docusaurus/preset-classic": "3.1.0",
"@mdx-js/react": "^3.0.0",
"clsx": "^2.0.0",
"prism-react-renderer": "^2.3.0",
"react": "^18.0.0",
"react-dom": "^18.0.0"
},
"devDependencies": {
"@docusaurus/module-type-aliases": "3.1.0",
"@docusaurus/types": "3.1.0"
},
"browserslist": {
"production": [
">0.5%",
"not dead",
"not op_mini all"
],
"development": [
"last 3 chrome version",
"last 3 firefox version",
"last 5 safari version"
]
},
"engines": {
"node": ">=18.0"
}
}

33
documentation/sidebars.js Normal file
View File

@@ -0,0 +1,33 @@
/**
* Creating a sidebar enables you to:
- create an ordered group of docs
- render a sidebar for each doc of that group
- provide next/previous navigation
The sidebars can be generated from the filesystem, or explicitly defined here.
Create as many sidebars as you want.
*/
// @ts-check
/** @type {import('@docusaurus/plugin-content-docs').SidebarsConfig} */
const sidebars = {
// By default, Docusaurus generates a sidebar from the docs folder structure
tutorialSidebar: [{type: 'autogenerated', dirName: '.'}],
// But you can create a sidebar manually
/*
tutorialSidebar: [
'intro',
'hello',
{
type: 'category',
label: 'Tutorial',
items: ['tutorial-basics/create-a-document'],
},
],
*/
};
export default sidebars;

View File

@@ -0,0 +1,11 @@
.features {
display: flex;
align-items: center;
padding: 2rem 0;
width: 100%;
}
.featureSvg {
height: 200px;
width: 200px;
}

View File

@@ -0,0 +1,37 @@
/**
* Any CSS included here will be global. The classic template
* bundles Infima by default. Infima is a CSS framework designed to
* work well for content-centric websites.
*/
@import url('https://fonts.googleapis.com/css2?family=Source+Sans+3&display=swap');
/* You can override the default Infima variables here. */
:root {
--ifm-color-primary: #fcc50b;
--ifm-color-primary-dark: #fcc50b;
--ifm-color-primary-darker: #fcc50b;
--ifm-color-primary-darkest: #fcc50b;
--ifm-color-primary-light: #fcc50b;
--ifm-color-primary-lighter: #fcc50b;
--ifm-color-primary-lightest: #fcc50b;
--ifm-code-font-size: 95%;
--ifm-heading-font-family: 'Source Sans 3', sans-serif;
--docusaurus-highlighted-code-line-bg: rgba(0, 0, 0, 0.1);
}
/* For readability concerns, you should choose a lighter palette in dark mode. */
[data-theme='dark'] {
--ifm-color-primary: #fcc50b;
--ifm-color-primary-dark: #fcc50b;
--ifm-color-primary-darker: #fcc50b;
--ifm-color-primary-darkest: #fcc50b;
--ifm-color-primary-light: #fcc50b;
--ifm-color-primary-lighter: #fcc50b;
--ifm-color-primary-lightest: #fcc50b;
--docusaurus-highlighted-code-line-bg: rgba(0, 0, 0, 0.3);
}
body {
font-family: 'Source Sans 3', sans-serif;
}

8344
documentation/yarn.lock Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -1,7 +1,7 @@
{
"id": "khoj",
"name": "Khoj",
"version": "1.2.0",
"version": "1.2.1",
"minAppVersion": "0.15.0",
"description": "An AI copilot for your Second Brain",
"author": "Khoj Inc.",

View File

@@ -62,8 +62,8 @@ dependencies = [
"pymupdf >= 1.23.5",
"django == 4.2.7",
"authlib == 1.2.1",
"gpt4all >= 2.0.0; platform_system == 'Linux' and platform_machine == 'x86_64'",
"gpt4all >= 2.0.0; platform_system == 'Windows' or platform_system == 'Darwin'",
"gpt4all >= 2.1.0; platform_system == 'Linux' and platform_machine == 'x86_64'",
"gpt4all >= 2.1.0; platform_system == 'Windows' or platform_system == 'Darwin'",
"itsdangerous == 2.1.2",
"httpx == 0.25.0",
"pgvector == 0.2.4",

View File

@@ -1,6 +1,6 @@
{
"name": "Khoj",
"version": "1.2.0",
"version": "1.2.1",
"description": "An AI copilot for your Second Brain",
"author": "Saba Imran, Debanjum Singh Solanky <team@khoj.dev>",
"license": "GPL-3.0-or-later",

View File

@@ -6,7 +6,7 @@
;; Saba Imran <saba@khoj.dev>
;; Description: An AI copilot for your Second Brain
;; Keywords: search, chat, org-mode, outlines, markdown, pdf, image
;; Version: 1.2.0
;; Version: 1.2.1
;; Package-Requires: ((emacs "27.1") (transient "0.3.0") (dash "2.19.1"))
;; URL: https://github.com/khoj-ai/khoj/tree/master/src/interface/emacs

View File

@@ -1,7 +1,7 @@
{
"id": "khoj",
"name": "Khoj",
"version": "1.2.0",
"version": "1.2.1",
"minAppVersion": "0.15.0",
"description": "An AI copilot for your Second Brain",
"author": "Khoj Inc.",

View File

@@ -1,6 +1,6 @@
{
"name": "Khoj",
"version": "1.2.0",
"version": "1.2.1",
"description": "An AI copilot for your Second Brain",
"author": "Debanjum Singh Solanky, Saba Imran <team@khoj.dev>",
"license": "GPL-3.0-or-later",

View File

@@ -30,5 +30,6 @@
"1.0.0": "0.15.0",
"1.0.1": "0.15.0",
"1.1.0": "0.15.0",
"1.2.0": "0.15.0"
"1.2.0": "0.15.0",
"1.2.1": "0.15.0"
}

View File

@@ -144,7 +144,15 @@ def configure_server(
state.cross_encoder_model = dict()
for model in search_models:
state.embeddings_model.update({model.name: EmbeddingsModel(model.bi_encoder)})
state.embeddings_model.update(
{
model.name: EmbeddingsModel(
model.bi_encoder,
model.embeddings_inference_endpoint,
model.embeddings_inference_endpoint_api_key,
)
}
)
state.cross_encoder_model.update({model.name: CrossEncoderModel(model.cross_encoder)})
state.SearchType = configure_search_types()

View File

@@ -0,0 +1,22 @@
# Generated by Django 4.2.7 on 2024-01-15 18:12
from django.db import migrations, models
class Migration(migrations.Migration):
dependencies = [
("database", "0024_alter_entry_embeddings"),
]
operations = [
migrations.AddField(
model_name="searchmodelconfig",
name="embeddings_inference_endpoint",
field=models.CharField(blank=True, default=None, max_length=200, null=True),
),
migrations.AddField(
model_name="searchmodelconfig",
name="embeddings_inference_endpoint_api_key",
field=models.CharField(blank=True, default=None, max_length=200, null=True),
),
]

View File

@@ -110,6 +110,8 @@ class SearchModelConfig(BaseModel):
model_type = models.CharField(max_length=200, choices=ModelType.choices, default=ModelType.TEXT)
bi_encoder = models.CharField(max_length=200, default="thenlper/gte-small")
cross_encoder = models.CharField(max_length=200, default="cross-encoder/ms-marco-MiniLM-L-6-v2")
embeddings_inference_endpoint = models.CharField(max_length=200, default=None, null=True, blank=True)
embeddings_inference_endpoint_api_key = models.CharField(max_length=200, default=None, null=True, blank=True)
class TextToImageModelConfig(BaseModel):

View File

@@ -123,9 +123,9 @@ def filter_questions(questions: List[str]):
def converse_offline(
references,
online_results,
user_query,
references=[],
online_results=[],
conversation_log={},
model: str = "mistral-7b-instruct-v0.1.Q4_0.gguf",
loaded_model: Union[Any, None] = None,

View File

@@ -21,9 +21,11 @@ def download_model(model_name: str):
# Try load chat model to GPU if:
# 1. Loading chat model to GPU isn't disabled via CLI and
# 2. Machine has GPU
# 3. GPU has enough free memory to load the chat model
# 3. GPU has enough free memory to load the chat model with max context length of 4096
device = (
"gpu" if state.chat_on_gpu and gpt4all.pyllmodel.LLModel().list_gpu(chat_model_config["path"]) else "cpu"
"gpu"
if state.chat_on_gpu and gpt4all.pyllmodel.LLModel().list_gpu(chat_model_config["path"], 4096)
else "cpu"
)
except ValueError:
device = "cpu"
@@ -35,7 +37,7 @@ def download_model(model_name: str):
raise e
# Now load the downloaded chat model onto appropriate device
chat_model = gpt4all.GPT4All(model_name=model_name, device=device, allow_download=False)
chat_model = gpt4all.GPT4All(model_name=model_name, n_ctx=4096, device=device, allow_download=False)
logger.debug(f"Loaded chat model to {device.upper()}.")
return chat_model

View File

@@ -1,23 +1,69 @@
import logging
from typing import List
import requests
import tqdm
from sentence_transformers import CrossEncoder, SentenceTransformer
from torch import nn
from khoj.utils.helpers import get_device
from khoj.utils.rawconfig import SearchResponse
logger = logging.getLogger(__name__)
class EmbeddingsModel:
def __init__(self, model_name: str = "thenlper/gte-small"):
def __init__(
self,
model_name: str = "thenlper/gte-small",
embeddings_inference_endpoint: str = None,
embeddings_inference_endpoint_api_key: str = None,
):
self.encode_kwargs = {"normalize_embeddings": True}
self.model_kwargs = {"device": get_device()}
self.model_name = model_name
self.inference_endpoint = embeddings_inference_endpoint
self.api_key = embeddings_inference_endpoint_api_key
self.embeddings_model = SentenceTransformer(self.model_name, **self.model_kwargs)
def embed_query(self, query):
if self.api_key is not None and self.inference_endpoint is not None:
target_url = f"{self.inference_endpoint}"
payload = {"inputs": [query]}
headers = {"Authorization": f"Bearer {self.api_key}", "Content-Type": "application/json"}
response = requests.post(target_url, json=payload, headers=headers)
return response.json()["embeddings"][0]
return self.embeddings_model.encode([query], show_progress_bar=False, **self.encode_kwargs)[0]
def embed_documents(self, docs):
if self.api_key is not None and self.inference_endpoint is not None:
target_url = f"{self.inference_endpoint}"
if "huggingface" not in target_url:
logger.warning(
f"Using custom inference endpoint {target_url} is not yet supported. Please us a HuggingFace inference endpoint."
)
return self.embeddings_model.encode(docs, show_progress_bar=True, **self.encode_kwargs).tolist()
# break up the docs payload in chunks of 1000 to avoid hitting rate limits
headers = {
"Authorization": f"Bearer {self.api_key}",
"Content-Type": "application/json",
}
with tqdm.tqdm(total=len(docs)) as pbar:
for i in range(0, len(docs), 1000):
payload = {"inputs": docs[i : i + 1000]}
response = requests.post(target_url, json=payload, headers=headers)
try:
response.raise_for_status()
except requests.exceptions.HTTPError as e:
print(f"Error: {e}")
print(f"Response: {response.json()}")
raise e
if i == 0:
embeddings = response.json()["embeddings"]
else:
embeddings += response.json()["embeddings"]
pbar.update(1000)
return embeddings
return self.embeddings_model.encode(docs, show_progress_bar=True, **self.encode_kwargs).tolist()

View File

@@ -6,6 +6,7 @@ import os
import time
import uuid
from typing import Any, Dict, List, Optional, Union
from urllib.parse import unquote
from asgiref.sync import sync_to_async
from fastapi import APIRouter, Depends, File, HTTPException, Request, UploadFile
@@ -704,6 +705,7 @@ async def chat(
rate_limiter_per_day=Depends(ApiUserRateLimiter(requests=10, subscribed_requests=600, window=60 * 60 * 24)),
) -> Response:
user: KhojUser = request.user.object
q = unquote(q)
await is_ready_to_chat(user)
conversation_command = get_conversation_command(query=q, any_references=True)

View File

@@ -1,3 +1,4 @@
import os
import urllib.parse
from urllib.parse import quote
@@ -53,6 +54,7 @@ def test_chat_with_no_chat_history_or_retrieved_content_gpt4all(client_offline_c
# ----------------------------------------------------------------------------------------------------
@pytest.mark.skipif(os.getenv("SERPER_DEV_API_KEY") is None, reason="requires SERPER_DEV_API_KEY")
@pytest.mark.chatquality
@pytest.mark.django_db(transaction=True)
def test_chat_with_online_content(chat_client):

View File

@@ -30,5 +30,6 @@
"1.0.0": "0.15.0",
"1.0.1": "0.15.0",
"1.1.0": "0.15.0",
"1.2.0": "0.15.0"
"1.2.0": "0.15.0",
"1.2.1": "0.15.0"
}